Add new SentenceTransformer model.

16c59c8 verified 2 months ago

62.7 kB

	---
	base_model: Snowflake/snowflake-arctic-embed-m
	datasets: []
	language: []
	library_name: sentence-transformers
	metrics:
	- cosine_accuracy@5
	- cosine_accuracy@10
	- cosine_precision@5
	- cosine_precision@10
	- cosine_recall@5
	- cosine_recall@10
	- cosine_ndcg@5
	- cosine_ndcg@10
	- cosine_mrr@5
	- cosine_mrr@10
	- cosine_map@5
	- cosine_map@10
	pipeline_tag: sentence-similarity
	tags:
	- sentence-transformers
	- sentence-similarity
	- feature-extraction
	- generated_from_trainer
	- loss:CoSENTLoss
	- dataset_size:7232
	- loss:WeightedMultipleNegativesRankingLoss
	widget:
	- source_sentence: ', antenna, or other sensor to attain mission performance levels
	that

	currently cannot be achieved by a monolithic satellite. Most aspects of this concept
	have been widely studied, but

	the first implementation has yet to be realized, with the exception of a few initial
	experiments.

	A distributed satellite system taxonomy is shown in Fig. 1 with a discussion of
	current and planned systems to

	follow. At the end of this section, a candidate distributed space mission is presented
	as a common reference for

	Table 1 presents a selection of current distributed satellite systems, grouped
	in the four typical mission

	categories'
	sentences:
	- 'What is the precision that the system is aiming for in terms of tracking error?


	'
	- 'What is the main challenge in implementing a distributed satellite system?


	'
	- 'Who are the authors of the NASA document "Space Radiation Cancer Risk Projections
	for Explorative Missions: Uncertainty Reduction and Mitigation"?


	'
	- source_sentence: ':250,000 scale for regional context) . Near-term efforts should
	focus on high-priority locations .

	[16] Terrain hazard (e .g ., slope, surface roughness), line-of-sight (i .e .,
	viewshed), and time-dependent

	illumination maps at appropriate scales (e .g ., best-available supported by the
	data) are high-priority derived products essential in mission planning, and they
	should be made available as soon as possible .

	[17] South polar data products could be initially controlled to coarser data and
	known surface reference points to support early Artemis missions and other surface
	activities, but establishment of a local control network applied to all necessary
	data layers would facilitate interoperability and provide more precision for specific
	sites .

	Higher-order data products are tied to controlled foundational data and are derived
	from source data, such as measurements of elemental abundance, temperature or
	reflectance at multiple wavelengths, observations of solar illumination, and output
	from space weather models . Higher-order data products derived from these source
	data will play an essential role in planning and executing south polar missions
	. Planning the science activities to be carried out on the lunar surface will
	be based on these higher-order data products, and, in turn, the science returned
	by those activities will be used to update those same products . For example,
	geologic maps based on remotely sensed data prior to early Artemis landings will
	be a likely outcome of site assessments and will form the critical basis for traverse
	plans and planning of science tasks . The observations, samples, and measurements
	made during Artemis surface activities will feed back into updating the geologic
	maps, to the benefit of future crewed or robotic missions to the same area . Similarly,
	resource maps will drive the selection of landing sites for missions focused on
	resource discovery, characterization, and utilization, and the findings of those
	missions will be used to iteratively update the resource maps . In these cases,
	and others'
	sentences:
	- 'What are the specifications of the Theia imager that make it suitable for quantitative
	remote sensing studies?


	'
	- 'Who supported the first study?


	'
	- 'What are the essential derived products in mission planning, and why are they
	crucial for south polar missions?


	'
	- source_sentence: ', there are still

	some challenges to be overcome it is shown that it is possible to perform such
	links. Furthermore,

	recommendations for future operations of optical links were provided.

	FLP is also integrated in the educational aspects of the Institute. Many future
	aerospace engineers were

	trained for satellite operations and Earth Observations and the satellite will
	be used to train operators

	Further investigation of the Attitude Control is required for the stabilization
	of the optical links on

	other G/S as Oberpfaffenhofen. However, future projects might benefit from more
	standardization on

	the side of G/S Feedback for optical links. Overall Flying Laptop is a stable
	platform for technology demonstration, Earth Observation, and ed-

	588. [Online]. Available'
	sentences:
	- 'What are the remaining challenges that need to be addressed for the successful
	implementation of optical links?


	'
	- 'What are the benefits of enhancing the radiometric resolution of VLEO satellite
	systems?


	'
	- 'What is the reason for using the uncoupled approach for the radiation calculations
	in this study?


	'
	- source_sentence: ': they are visible on the waterfall plots with a very high amplitude.
	Moreover, some peaks appear on waterfall plots while they are not

	visible on zero speed curves. These peaks correspond to first order unbalance,
	engine orders or wheel eigenmodes. By repeating the tests with different configurations
	(without ventilation, changing the axes, etc...), conclusions have been made and
	are presented in table 4.

	It is necessary to check if the modes presented in table 4 do not cross the order
	1 unbalance or the rocking mode. The visible lines starting from the origin and
	evolving with the rotation speed of the wheel are the engine orders due to the
	imperfections of the wheel. When they cross modes of the wheel, the amplitudes
	corresponding to the crossing are much higher as we can clearly see in Table 2,
	on the x axis waterfall plots at 1050 Hz and 4000 RPM. The waterfall plots allow
	to have a global view on the wheel structure. By looking at these curves, two
	wheels can be compared. For example, higher amplitudes on engine orders mean that
	the wheel has defects. Moreover, a shift of the rocking mode means that the parameters
	of the wheel are different as shown in equations 4.

	Table 3 summarizes the static and dynamic unbalances calculated on three wheels.
	We notice that they all have the same order of magnitude. Environmental vibration
	and shock tests can vary this value by damaging the wheel. On the other hand,
	bearing defects can be reduced when the wheel is continuously rotated due to the
	running-in process, which can decrease the unbalance value. In general, environmental
	testing has more impact than running-in.

	When the frequencies are low, the wheel has no trouble following the setpoint.
	At high frequencies, the wheel follows the setpoint but with a loss of amplitude
	and a phase shift'
	sentences:
	- 'What are the peaks that appear on waterfall plots but not on zero speed curves?


	'
	- 'Why is separately scheduling the imaging and download tasks a natural choice
	for real-world complex systems?


	'
	- 'What are the dominant orbit determination uncertainties?


	'
	- source_sentence: ': Block diagram of the 7-band CCD-in-CMOS TDI sensor. Each TX
	slice has two serializers and its own PLL.

	The CCD bands operate continuously and time interleaved. The output stages for
	the CCD arrays are implemented both at the top and bottom of each band to support
	the bi-directional operation. All 14 output stages in one column are connected
	to one delta-sigma column-level ADC with digital CDS implemented in the digital
	decimator. The outputs of every 128 ADCs are serialized to one of 32 LVDS outputs.
	Two clock signals are also provided via LVDS to synchronize the channels. These
	outputs are capable of running at an aggregate data rate of >50Gb/s using on-chip
	PLLs.

	The sensor has been processed for Back-Side Illumination and it has been packaged
	in a custom ceramic PGA package. Figure 15 shows a picture of the sensor with
	its 7 bands. The figure shows the front-side and back-side versions of the chip
	side by side.

	(a) (b) Figure 15: 7-band CCD-in-CMOS TDI chip photograph. FSI shown only for
	reference (a) and BSI version (b).

	As a proof-of-concept, an RGB butcher-brick filter has been used as glass lid
	for the sensor, to enable multicolor TDI, although filters may be processed directly
	on the wafer as well [9]. The sensor,

	camera system and a color image captured from the setup are depicted in Figure
	16, providing evidence that multispectral TDI is viable with the sensor.

	Figure 16: Colour TDI image captured from the sensor, sensor with RGB color filter
	and camera set-up.

	Table 3 below shows a comparison of different TDI sensors, including the first
	iteration of our sensor.

	Integrated drivers

	The measurements on the first iteration of the SoC verified'
	sentences:
	- 'What is the primary objective of the Zodiac Pioneer Mission?


	'
	- 'What is the main topic of the papers listed in the context?


	'
	- 'What is the aggregate data rate of the outputs of the 7-band CCD-in-CMOS TDI
	sensor?


	'
	model-index:
	- name: SentenceTransformer based on Snowflake/snowflake-arctic-embed-m
	results:
	- task:
	type: information-retrieval
	name: Information Retrieval
	dataset:
	name: dim 768
	type: dim_768
	metrics:
	- type: cosine_accuracy@5
	value: 0.8407960199004975
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.8843283582089553
	name: Cosine Accuracy@10
	- type: cosine_precision@5
	value: 0.16815920398009948
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.08843283582089552
	name: Cosine Precision@10
	- type: cosine_recall@5
	value: 0.8407960199004975
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.8843283582089553
	name: Cosine Recall@10
	- type: cosine_ndcg@5
	value: 0.749593576396566
	name: Cosine Ndcg@5
	- type: cosine_ndcg@10
	value: 0.7638900783774348
	name: Cosine Ndcg@10
	- type: cosine_mrr@5
	value: 0.7189676616915421
	name: Cosine Mrr@5
	- type: cosine_mrr@10
	value: 0.7249965450525153
	name: Cosine Mrr@10
	- type: cosine_map@5
	value: 0.7189676616915422
	name: Cosine Map@5
	- type: cosine_map@10
	value: 0.7249965450525152
	name: Cosine Map@10
	- type: cosine_accuracy@5
	value: 0.9198717948717948
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.9551282051282052
	name: Cosine Accuracy@10
	- type: cosine_precision@5
	value: 0.18397435897435896
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.0955128205128205
	name: Cosine Precision@10
	- type: cosine_recall@5
	value: 0.9198717948717948
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.9551282051282052
	name: Cosine Recall@10
	- type: cosine_ndcg@5
	value: 0.786039298615645
	name: Cosine Ndcg@5
	- type: cosine_ndcg@10
	value: 0.7975208279742617
	name: Cosine Ndcg@10
	- type: cosine_mrr@5
	value: 0.740758547008547
	name: Cosine Mrr@5
	- type: cosine_mrr@10
	value: 0.7455369861619862
	name: Cosine Mrr@10
	- type: cosine_map@5
	value: 0.740758547008547
	name: Cosine Map@5
	- type: cosine_map@10
	value: 0.7455369861619863
	name: Cosine Map@10
	- task:
	type: information-retrieval
	name: Information Retrieval
	dataset:
	name: dim 512
	type: dim_512
	metrics:
	- type: cosine_accuracy@5
	value: 0.8345771144278606
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.8781094527363185
	name: Cosine Accuracy@10
	- type: cosine_precision@5
	value: 0.16691542288557212
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.08781094527363183
	name: Cosine Precision@10
	- type: cosine_recall@5
	value: 0.8345771144278606
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.8781094527363185
	name: Cosine Recall@10
	- type: cosine_ndcg@5
	value: 0.7384076037005772
	name: Cosine Ndcg@5
	- type: cosine_ndcg@10
	value: 0.7524024562602603
	name: Cosine Ndcg@10
	- type: cosine_mrr@5
	value: 0.7060530679933663
	name: Cosine Mrr@5
	- type: cosine_mrr@10
	value: 0.7117739674642659
	name: Cosine Mrr@10
	- type: cosine_map@5
	value: 0.7060530679933666
	name: Cosine Map@5
	- type: cosine_map@10
	value: 0.7117739674642659
	name: Cosine Map@10
	- type: cosine_accuracy@5
	value: 0.907051282051282
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.9519230769230769
	name: Cosine Accuracy@10
	- type: cosine_precision@5
	value: 0.1814102564102564
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.09519230769230767
	name: Cosine Precision@10
	- type: cosine_recall@5
	value: 0.907051282051282
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.9519230769230769
	name: Cosine Recall@10
	- type: cosine_ndcg@5
	value: 0.7793612708940784
	name: Cosine Ndcg@5
	- type: cosine_ndcg@10
	value: 0.7942949173487753
	name: Cosine Ndcg@10
	- type: cosine_mrr@5
	value: 0.7363247863247866
	name: Cosine Mrr@5
	- type: cosine_mrr@10
	value: 0.7427375864875867
	name: Cosine Mrr@10
	- type: cosine_map@5
	value: 0.7363247863247864
	name: Cosine Map@5
	- type: cosine_map@10
	value: 0.7427375864875865
	name: Cosine Map@10
	- task:
	type: information-retrieval
	name: Information Retrieval
	dataset:
	name: dim 256
	type: dim_256
	metrics:
	- type: cosine_accuracy@5
	value: 0.8146766169154229
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.8631840796019901
	name: Cosine Accuracy@10
	- type: cosine_precision@5
	value: 0.16293532338308458
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.08631840796019902
	name: Cosine Precision@10
	- type: cosine_recall@5
	value: 0.8146766169154229
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.8631840796019901
	name: Cosine Recall@10
	- type: cosine_ndcg@5
	value: 0.7159371426767726
	name: Cosine Ndcg@5
	- type: cosine_ndcg@10
	value: 0.731814701526023
	name: Cosine Ndcg@10
	- type: cosine_mrr@5
	value: 0.6826907131011605
	name: Cosine Mrr@5
	- type: cosine_mrr@10
	value: 0.6893587617468213
	name: Cosine Mrr@10
	- type: cosine_map@5
	value: 0.6826907131011608
	name: Cosine Map@5
	- type: cosine_map@10
	value: 0.6893587617468214
	name: Cosine Map@10
	- type: cosine_accuracy@5
	value: 0.8846153846153846
	name: Cosine Accuracy@5
	- type: cosine_accuracy@10
	value: 0.9455128205128205
	name: Cosine Accuracy@10
	- type: cosine_precision@5
	value: 0.1769230769230769
	name: Cosine Precision@5
	- type: cosine_precision@10
	value: 0.09455128205128205
	name: Cosine Precision@10
	- type: cosine_recall@5
	value: 0.8846153846153846
	name: Cosine Recall@5
	- type: cosine_recall@10
	value: 0.9455128205128205
	name: Cosine Recall@10
	- type: cosine_ndcg@5
	value: 0.7547512036424451
	name: Cosine Ndcg@5
	- type: cosine_ndcg@10
	value: 0.7747939646301274
	name: Cosine Ndcg@10
	- type: cosine_mrr@5
	value: 0.7107905982905985
	name: Cosine Mrr@5
	- type: cosine_mrr@10
	value: 0.7192778286528287
	name: Cosine Mrr@10
	- type: cosine_map@5
	value: 0.7107905982905982
	name: Cosine Map@5
	- type: cosine_map@10
	value: 0.7192778286528286
	name: Cosine Map@10
	---

	# SentenceTransformer based on Snowflake/snowflake-arctic-embed-m

	This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [Snowflake/snowflake-arctic-embed-m](https://huggingface.co./Snowflake/snowflake-arctic-embed-m). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

	## Model Details

	### Model Description
	- Model Type: Sentence Transformer
	- Base model: [Snowflake/snowflake-arctic-embed-m](https://huggingface.co./Snowflake/snowflake-arctic-embed-m) <!-- at revision 71bc94c8f9ea1e54fba11167004205a65e5da2cc -->
	- Maximum Sequence Length: 512 tokens
	- Output Dimensionality: 768 tokens
	- Similarity Function: Cosine Similarity
	<!-- - Training Dataset: Unknown -->
	<!-- - Language: Unknown -->
	<!-- - License: Unknown -->

	### Model Sources

	- Documentation: [Sentence Transformers Documentation](https://sbert.net)
	- Repository: [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
	- Hugging Face: [Sentence Transformers on Hugging Face](https://huggingface.co./models?library=sentence-transformers)

	### Full Model Architecture

	```
	SentenceTransformer(
	(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
	(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
	(2): Normalize()
	)
	```

	## Usage

	### Direct Usage (Sentence Transformers)

	First install the Sentence Transformers library:

	```bash
	pip install -U sentence-transformers
	```

	Then you can load this model and run inference.
	```python
	from sentence_transformers import SentenceTransformer

	# Download from the 🤗 Hub
	model = SentenceTransformer("federicovolponi/Snowflake-snowflake-arctic-embed-m-space-sup")
	# Run inference
	sentences = [
	': Block diagram of the 7-band CCD-in-CMOS TDI sensor. Each TX slice has two serializers and its own PLL.\nThe CCD bands operate continuously and time interleaved. The output stages for the CCD arrays are implemented both at the top and bottom of each band to support the bi-directional operation. All 14 output stages in one column are connected to one delta-sigma column-level ADC with digital CDS implemented in the digital decimator. The outputs of every 128 ADCs are serialized to one of 32 LVDS outputs. Two clock signals are also provided via LVDS to synchronize the channels. These outputs are capable of running at an aggregate data rate of >50Gb/s using on-chip PLLs.\nThe sensor has been processed for Back-Side Illumination and it has been packaged in a custom ceramic PGA package. Figure 15 shows a picture of the sensor with its 7 bands. The figure shows the front-side and back-side versions of the chip side by side.\n(a) (b) Figure 15: 7-band CCD-in-CMOS TDI chip photograph. FSI shown only for reference (a) and BSI version (b).\nAs a proof-of-concept, an RGB butcher-brick filter has been used as glass lid for the sensor, to enable multicolor TDI, although filters may be processed directly on the wafer as well [9]. The sensor,\ncamera system and a color image captured from the setup are depicted in Figure 16, providing evidence that multispectral TDI is viable with the sensor.\nFigure 16: Colour TDI image captured from the sensor, sensor with RGB color filter and camera set-up.\nTable 3 below shows a comparison of different TDI sensors, including the first iteration of our sensor.\nIntegrated drivers\nThe measurements on the first iteration of the SoC verified',
	'What is the aggregate data rate of the outputs of the 7-band CCD-in-CMOS TDI sensor?\n\n',
	'What is the primary objective of the Zodiac Pioneer Mission?\n\n',
	]
	embeddings = model.encode(sentences)
	print(embeddings.shape)
	# [3, 768]

	# Get the similarity scores for the embeddings
	similarities = model.similarity(embeddings, embeddings)
	print(similarities.shape)
	# [3, 3]
	```

	<!--
	### Direct Usage (Transformers)

	<details><summary>Click to see the direct usage in Transformers</summary>

	</details>
	-->

	<!--
	### Downstream Usage (Sentence Transformers)

	You can finetune this model on your own dataset.

	<details><summary>Click to expand</summary>

	</details>
	-->

	<!--
	### Out-of-Scope Use

	List how the model may foreseeably be misused and address what users ought not to do with the model.
	-->

	## Evaluation

	### Metrics

	#### Information Retrieval
	* Dataset: `dim_768`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:----------\|
	\| cosine_accuracy@5 \| 0.8408 \|
	\| cosine_accuracy@10 \| 0.8843 \|
	\| cosine_precision@5 \| 0.1682 \|
	\| cosine_precision@10 \| 0.0884 \|
	\| cosine_recall@5 \| 0.8408 \|
	\| cosine_recall@10 \| 0.8843 \|
	\| cosine_ndcg@5 \| 0.7496 \|
	\| cosine_ndcg@10 \| 0.7639 \|
	\| cosine_mrr@5 \| 0.719 \|
	\| cosine_mrr@10 \| 0.725 \|
	\| cosine_map@5 \| 0.719 \|
	\| cosine_map@10 \| 0.725 \|

	#### Information Retrieval
	* Dataset: `dim_512`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| cosine_accuracy@5 \| 0.8346 \|
	\| cosine_accuracy@10 \| 0.8781 \|
	\| cosine_precision@5 \| 0.1669 \|
	\| cosine_precision@10 \| 0.0878 \|
	\| cosine_recall@5 \| 0.8346 \|
	\| cosine_recall@10 \| 0.8781 \|
	\| cosine_ndcg@5 \| 0.7384 \|
	\| cosine_ndcg@10 \| 0.7524 \|
	\| cosine_mrr@5 \| 0.7061 \|
	\| cosine_mrr@10 \| 0.7118 \|
	\| cosine_map@5 \| 0.7061 \|
	\| cosine_map@10 \| 0.7118 \|

	#### Information Retrieval
	* Dataset: `dim_256`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| cosine_accuracy@5 \| 0.8147 \|
	\| cosine_accuracy@10 \| 0.8632 \|
	\| cosine_precision@5 \| 0.1629 \|
	\| cosine_precision@10 \| 0.0863 \|
	\| cosine_recall@5 \| 0.8147 \|
	\| cosine_recall@10 \| 0.8632 \|
	\| cosine_ndcg@5 \| 0.7159 \|
	\| cosine_ndcg@10 \| 0.7318 \|
	\| cosine_mrr@5 \| 0.6827 \|
	\| cosine_mrr@10 \| 0.6894 \|
	\| cosine_map@5 \| 0.6827 \|
	\| cosine_map@10 \| 0.6894 \|

	#### Information Retrieval
	* Dataset: `dim_768`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| cosine_accuracy@5 \| 0.9199 \|
	\| cosine_accuracy@10 \| 0.9551 \|
	\| cosine_precision@5 \| 0.184 \|
	\| cosine_precision@10 \| 0.0955 \|
	\| cosine_recall@5 \| 0.9199 \|
	\| cosine_recall@10 \| 0.9551 \|
	\| cosine_ndcg@5 \| 0.786 \|
	\| cosine_ndcg@10 \| 0.7975 \|
	\| cosine_mrr@5 \| 0.7408 \|
	\| cosine_mrr@10 \| 0.7455 \|
	\| cosine_map@5 \| 0.7408 \|
	\| cosine_map@10 \| 0.7455 \|

	#### Information Retrieval
	* Dataset: `dim_512`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| cosine_accuracy@5 \| 0.9071 \|
	\| cosine_accuracy@10 \| 0.9519 \|
	\| cosine_precision@5 \| 0.1814 \|
	\| cosine_precision@10 \| 0.0952 \|
	\| cosine_recall@5 \| 0.9071 \|
	\| cosine_recall@10 \| 0.9519 \|
	\| cosine_ndcg@5 \| 0.7794 \|
	\| cosine_ndcg@10 \| 0.7943 \|
	\| cosine_mrr@5 \| 0.7363 \|
	\| cosine_mrr@10 \| 0.7427 \|
	\| cosine_map@5 \| 0.7363 \|
	\| cosine_map@10 \| 0.7427 \|

	#### Information Retrieval
	* Dataset: `dim_256`
	* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)

	\| Metric \| Value \|
	\|:--------------------\|:-----------\|
	\| cosine_accuracy@5 \| 0.8846 \|
	\| cosine_accuracy@10 \| 0.9455 \|
	\| cosine_precision@5 \| 0.1769 \|
	\| cosine_precision@10 \| 0.0946 \|
	\| cosine_recall@5 \| 0.8846 \|
	\| cosine_recall@10 \| 0.9455 \|
	\| cosine_ndcg@5 \| 0.7548 \|
	\| cosine_ndcg@10 \| 0.7748 \|
	\| cosine_mrr@5 \| 0.7108 \|
	\| cosine_mrr@10 \| 0.7193 \|
	\| cosine_map@5 \| 0.7108 \|
	\| cosine_map@10 \| 0.7193 \|

	<!--
	## Bias, Risks and Limitations

	What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.
	-->

	<!--
	### Recommendations

	What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.
	-->

	## Training Details

	### Training Dataset

	#### Unnamed Dataset


	* Size: 7,232 training samples
	* Columns: <code>positive</code> and <code>anchor</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| positive \| anchor \|
	\|:--------\|:------------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 5 tokens</li><li>mean: 354.69 tokens</li><li>max: 512 tokens</li></ul> \| <ul><li>min: 9 tokens</li><li>mean: 19.21 tokens</li><li>max: 40 tokens</li></ul> \|
	* Samples:
	\| positive \| anchor \|
	\|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:-----------------------------------------------------------------------------------------------------------------------------\|
	\| <code>, using diverse software or hardware designs may double design and veriﬁcation costs due to having to build two different components for the same functionality. Hence, although DCLS execution also halves performance efﬁciency (the corresponding functionality is executed twice), it allows reusing the same design (e.g. the same core design) for the primary and the redundant paths (e.g. with staggered execution), thus containing design and veriﬁcation costs.<br>Redundancy can be applied at different granularities accord- ing to the sphere of replication (SoR). Choosing the right SoR depends on several tradeoffs like area overheads, re- design costs, fault detection time, and overall system costs. In the context of DCLS, the SoR is placed at the level of the CPU (core), as done for the AURIX processors. This requires including two replicas of the same core and compare their memory transactions, which requires roughly duplicating com- putational resources in the chip and being able to ensure that replicas can provide independent behavior. On the other hand, storage (memories, caches) and communication means (buses, crossbars) do not need to be fully replicated and can build upon Error Correction Codes (ECC) and Cyclic Redundancy Check (CRC) as a form of lightweight redundancy with diversity.<br>HPC ASIL-D capable platforms typically combine a low- performance microcontroller amenable for the automotive do- main (i.e. ASIL-D capable) and an HPC accelerator deliv- ering high computation throughput, but whose adherence to ISO26262 requirements is unknown, so its appropriate use for ASIL-C/D systems needs to be investigated. Without loss of generality, we consider an NVIDIA GPU accelerator, thus analogous to those in NVIDIA Drive and Xavier families for the automotive domain. However, the ﬁndings in this paper can easily be extrapolated to other products.<br>Software faults and some hardware faults are regarded as systematic, and it must be proven that their failure risk is residual. However, random hardware faults cannot be avoided, and means are required to prevent them from causing hazards. Those faults can be caused by, for example, voltage droops</code> \| <code>What are the advantages of using the same design for the primary and redundant paths in DCLS execution?<br><br></code> \|
	\| <code>: First, the TT&C spectrum requirements of the new satellites shall be assessed. Second, the utilization of existing TT&C frequency allocations and their potential to incorporate the future number of satellites is studied. Only for the case that this study results in the need for new spectrum, the study groups were asked to investigate new potential TT&C frequency allocations in the frequency ranges 150.05-174 MHz and 400.15-420 MHz. The studies shall be completed for WRC-19.<br>This paper presents the intermediate results of the study groups. A study of the spectrum requirements of small satellites has been completed. The required spectrum for TT&C is expected to be less than 2.5 MHz for downlink and less than 1 MHz for uplink. Consequently, the study groups conducted sharing studies in various bands which will be summarized and evaluated from a satellite developer’s perspective.<br>After the Cubesat design standard was introduced in 1999 and first satellites of this new class have been launched in the subsequent years, small satellites have become increasingly popular in the past five years. Today not only universities use small satellite platforms for education and technology demonstration, but also commercial operators started to develop and deploy satellites with masses of typically less than 50 kg and reasonably short development times. Currently more than hundred new satellites are currently launched into space per year. The increase of launches was recognized by the International Telecommunication Union (ITU) which is responsible for the coordination of the shared use of frequencies. As the first Cubesats were mainly launched by new entrants into the space sector, mandatory regulatory procedures like frequency coordination were omitted or underestimated by the developers. Additionally, the new developers complaint that the existing regulatory procedures are too complicated and time-consuming for satellites with short development times. The ITU therefore decided at the WRC-12 to study the characteristics of picosatellites and nanosatellites and their current practice in filing satellites to the ITU. The studies were concluded in 2015 with two reports on the characteristics [1] and current filing practice [2]. In these reports it was identified that the characteristics that define small satellites (low mass, small dimensions, low power, …) are not relevant from a frequency coordination perspective and that the short development times are still long enough to properly file the systems to the ITU. As a result</code> \| <code>What are the spectrum requirements for TT&C of small satellites?<br><br></code> \|
	\| <code>:287–299, Dec 2019.<br>[20] Tam´as Vink´o and Dario Izzo. Global optimi- sation heuristics and test problems for prelimi- nary spacecraft trajectory design. Technical re- port, 2008.<br>[21] Matej Petkovic, Luke Lucas, Dragi Kocev, Saˇso Dˇzeroski, Redouane Boumghar, and Nikola Simidjievski. Quantifying the effects of gyro- less flying of the mars express spacecraft with machine learning. In 2019 IEEE International<br>[22] Janhavi H. Borse, Dipti D. Patil, Vinod Kumar, and Sudhir Kumar. Soft landing parameter measurements for candidate navigation trajec- tories using deep learning and ai-enabled plan- etary descent. Mathematical Problems in Engi- neering, 2022</code> \| <code>What are some of the research topics and methods explored in the provided references?<br><br></code> \|
	* Loss: <code>losses.WeightedMultipleNegativesRankingLoss</code> with these parameters:
	```json
	{
	"scale": 20,
	"similarity_fct": "cos_sim"
	}
	```

	### Evaluation Dataset

	#### Unnamed Dataset


	* Size: 804 evaluation samples
	* Columns: <code>positive</code> and <code>anchor</code>
	* Approximate statistics based on the first 1000 samples:
	\| \| positive \| anchor \|
	\|:--------\|:------------------------------------------------------------------------------------\|:----------------------------------------------------------------------------------\|
	\| type \| string \| string \|
	\| details \| <ul><li>min: 4 tokens</li><li>mean: 351.15 tokens</li><li>max: 512 tokens</li></ul> \| <ul><li>min: 8 tokens</li><li>mean: 19.36 tokens</li><li>max: 45 tokens</li></ul> \|
	* Samples:
	\| positive \| anchor \|
	\|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------\|:--------------------------------------------------------------------------------------------------------------------------------------------\|
	\| <code>, the total number of test thermocouples has been rationalized taking into account redundancy needs, accommodation constraints and hardware passivation needs for flight. The test is subdivided into 19 phases (see Figure 12) with two phases before and after the test for the health check functional tests under room conditions. Functional tests demonstrate anomalies such as the PCDU Reset and operational malfunctions of the RAX instrument at its high temperatures. The PCDU Reset anomaly was solved during the test by a software patch and validated during the final hot and cold plateaus. To address the RAX anomaly at hot, various test configurations were simulated using the thermal numerical model during the test to actually perform RAX functional test at an intermediate plateau facilitating mission operational constraints for flight. Data collected from hot and cold thermal balance test phases, as well as the rover OFF transition from hot to cold, are the inputs for correlation activities conducted post-TV/TB test. The thermal numerical model updates mainly focus on conductive couplings</code> \| <code>What was the solution to the PCDU Reset anomaly during the test?<br><br></code> \|
	\| <code>, where +Z axis orients to the earth, and sun pointing attitude mode during day time<br>orienting -Z axis to the sun. Therefore, attitude control subsystem is required to maneuver the satellite attitude twice per revolution around its pitch axis. Figure 6 shows concept of the attitude maneuverer. Another attitude maneuverer is necessary to perform SAR observation and SAR data download to a to ground station, because X-band transmit antenna is oriented to +Z, so the satellite has to offset its attitude to orient the X-band transmit antenna toward the ground station.<br>3.4 High pointing accuracy<br>Disturbance torque and system momentum profiles during few revolutions were estimated as shown in Figure 7 and 8. Four micro reaction wheels, which can respond to these profiles were selected which enable attitude maneuvers within a short period of time. In order to perform a pitch attitude maneuver quickly, two wheels are located on pitch axis while one wheel was located on each of the remaining roll and yaw axes. Figure 9 shows the satellite attitudes during SAR observation. There are three kinds of attitude, strip map mode, sliding spot light mode, and spotlight mode. Large change of momentum is required for pitch axis when the satellite is in spotlight mode. However, two pitch reaction wheels do not generate enough momentum to execute spotlight mode. So, sliding spotlight mode was selected for high resolution SAR observation mode instead of spotlight mode, in order to relax the torque and momentum requirements to the pitch wheels. In addition, two pitch<br>Figure 7. Disturbance torque profile Figure 8. System momentum profile<br>reaction wheels are accelerated to plus direction or minus direction by using magnet torque before observation. In order to obtain a high resolution SAR data, high attitude control accuracy is required for spotlight mode observation. To achieve high pointing accuracy against a defined ground target point, the attitude control loop applied feed forward compensation with estimated attitude angle and rate. Figure 10 shows an example of dynamic error during a spotlight mode observation maneuver.[4]<br>Equipment for SAR mission consumes total large power more than 1300W, therefore PCDU has a risk of causing electrical and RF influence to the bus power and signal line. In order to research the system, electrical interface check was performed using bread board model of PCDU, battery</code> \| <code>What is the reason for selecting sliding spotlight mode instead of spotlight mode for high resolution SAR observation?<br><br></code> \|
	\| <code>, body shape and motion assumptions. Then, ORSAT uses DCA to determine the reentry risk posed to the Earth’s<br>population based on the year of reentry and orbit inclination. It also predicts impact kinetic energy (impact velocity and impact mass) of objects that survive reentry[18]. ORSAT has been in use for the last decade and currently in its 6.0 version. However, unlike DAS, OR-<br>SAT is not readily available. Only personnel at the Johnson Space Center, Orbital Debris Program Oﬃce run ORSAT. ORSAT is limited to ballistic reentry, only tumbling motions or<br>stable orientations of objects are allowed which produce no lift. Partial melting of objects is considered by a demise factor and almost all materials in the database are temperature de- pendent. Heating by oxidation is also considered [20]. Therefore, ORSAT determines when<br>and if a reentry object demises by using integrated trajectory, atmospheric, aerodynamic, aero-thermodynamic, and thermal models as outlined in section 3.1 [17, 18, 20].<br>Reentry demisability analysis using DAS requires the spacecraft to be deﬁned to the level of each individual hardware part constituting the spacecraft. This step facilitates population<br>of the DAS Spacecraft Deﬁnition Module . Section 3.2.1 illustrates a generic spacecraft subdivision approach that can be followed to itemize the individual parts spacecraft parts.<br>Subsequently, non-demisable parts are identiﬁed before or by the actual reentry analysis as explained in section 3.2.2.<br>Itemization of the demisable spacecraft basic parts can be best approached by decompos- ing the spacecraft according to the Hierarchical System Terminology deﬁned in the NASA Systems Engineering Handbook [14]. Tables 3.2, 3.3 and 3.4 illustrate a generic approach<br>to decompose a spacecraft into basic parts [29, 30, 9] excluding the payload. Description of the speciﬁc product for the basic part identiﬁed completes the process. Though slight vari-<br>ations are likely to occur in the decomposition of diﬀerent missions, the Generic Spacecraft Subsystems Hierarchical Subdivision approach is robust, hence</code> \| <code>What is the limitation of ORSAT in terms of object motion?<br><br></code> \|
	* Loss: <code>losses.WeightedMultipleNegativesRankingLoss</code> with these parameters:
	```json
	{
	"scale": 20,
	"similarity_fct": "cos_sim"
	}
	```

	### Training Hyperparameters
	#### Non-Default Hyperparameters

	- `eval_strategy`: steps
	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 32
	- `learning_rate`: 3e-06
	- `weight_decay`: 0.001
	- `num_train_epochs`: 20
	- `bf16`: True
	- `tf32`: False
	- `load_best_model_at_end`: True
	- `batch_sampler`: no_duplicates

	#### All Hyperparameters
	<details><summary>Click to expand</summary>

	- `overwrite_output_dir`: False
	- `do_predict`: False
	- `eval_strategy`: steps
	- `prediction_loss_only`: True
	- `per_device_train_batch_size`: 32
	- `per_device_eval_batch_size`: 32
	- `per_gpu_train_batch_size`: None
	- `per_gpu_eval_batch_size`: None
	- `gradient_accumulation_steps`: 1
	- `eval_accumulation_steps`: None
	- `learning_rate`: 3e-06
	- `weight_decay`: 0.001
	- `adam_beta1`: 0.9
	- `adam_beta2`: 0.999
	- `adam_epsilon`: 1e-08
	- `max_grad_norm`: 1.0
	- `num_train_epochs`: 20
	- `max_steps`: -1
	- `lr_scheduler_type`: linear
	- `lr_scheduler_kwargs`: {}
	- `warmup_ratio`: 0.0
	- `warmup_steps`: 0
	- `log_level`: passive
	- `log_level_replica`: warning
	- `log_on_each_node`: True
	- `logging_nan_inf_filter`: True
	- `save_safetensors`: True
	- `save_on_each_node`: False
	- `save_only_model`: False
	- `restore_callback_states_from_checkpoint`: False
	- `no_cuda`: False
	- `use_cpu`: False
	- `use_mps_device`: False
	- `seed`: 42
	- `data_seed`: None
	- `jit_mode_eval`: False
	- `use_ipex`: False
	- `bf16`: True
	- `fp16`: False
	- `fp16_opt_level`: O1
	- `half_precision_backend`: auto
	- `bf16_full_eval`: False
	- `fp16_full_eval`: False
	- `tf32`: False
	- `local_rank`: 0
	- `ddp_backend`: None
	- `tpu_num_cores`: None
	- `tpu_metrics_debug`: False
	- `debug`: []
	- `dataloader_drop_last`: False
	- `dataloader_num_workers`: 0
	- `dataloader_prefetch_factor`: None
	- `past_index`: -1
	- `disable_tqdm`: False
	- `remove_unused_columns`: True
	- `label_names`: None
	- `load_best_model_at_end`: True
	- `ignore_data_skip`: False
	- `fsdp`: []
	- `fsdp_min_num_params`: 0
	- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
	- `fsdp_transformer_layer_cls_to_wrap`: None
	- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
	- `deepspeed`: None
	- `label_smoothing_factor`: 0.0
	- `optim`: adamw_torch
	- `optim_args`: None
	- `adafactor`: False
	- `group_by_length`: False
	- `length_column_name`: length
	- `ddp_find_unused_parameters`: None
	- `ddp_bucket_cap_mb`: None
	- `ddp_broadcast_buffers`: False
	- `dataloader_pin_memory`: True
	- `dataloader_persistent_workers`: False
	- `skip_memory_metrics`: True
	- `use_legacy_prediction_loop`: False
	- `push_to_hub`: False
	- `resume_from_checkpoint`: None
	- `hub_model_id`: None
	- `hub_strategy`: every_save
	- `hub_private_repo`: False
	- `hub_always_push`: False
	- `gradient_checkpointing`: False
	- `gradient_checkpointing_kwargs`: None
	- `include_inputs_for_metrics`: False
	- `eval_do_concat_batches`: True
	- `fp16_backend`: auto
	- `push_to_hub_model_id`: None
	- `push_to_hub_organization`: None
	- `mp_parameters`:
	- `auto_find_batch_size`: False
	- `full_determinism`: False
	- `torchdynamo`: None
	- `ray_scope`: last
	- `ddp_timeout`: 1800
	- `torch_compile`: False
	- `torch_compile_backend`: None
	- `torch_compile_mode`: None
	- `dispatch_batches`: None
	- `split_batches`: None
	- `include_tokens_per_second`: False
	- `include_num_input_tokens_seen`: False
	- `neftune_noise_alpha`: None
	- `optim_target_modules`: None
	- `batch_eval_metrics`: False
	- `batch_sampler`: no_duplicates
	- `multi_dataset_batch_sampler`: proportional

	</details>

	### Training Logs
	\| Epoch \| Step \| Training Loss \| loss \| dim_256_cosine_map@10 \| dim_512_cosine_map@10 \| dim_768_cosine_map@10 \|
	\|:------:\|:----:\|:-------------:\|:------:\|:---------------------:\|:---------------------:\|:---------------------:\|
	\| 0.4425 \| 100 \| 0.5883 \| - \| - \| - \| - \|
	\| 0.8850 \| 200 \| 0.2765 \| - \| - \| - \| - \|
	\| 1.3274 \| 300 \| 0.2047 \| - \| - \| - \| - \|
	\| 1.7699 \| 400 \| 0.1628 \| - \| - \| - \| - \|
	\| 2.2124 \| 500 \| 0.1519 \| 0.1204 \| 0.7094 \| 0.7271 \| 0.7266 \|
	\| 2.6549 \| 600 \| 0.1309 \| - \| - \| - \| - \|
	\| 3.0973 \| 700 \| 0.1228 \| - \| - \| - \| - \|
	\| 3.5398 \| 800 \| 0.1062 \| - \| - \| - \| - \|
	\| 3.9823 \| 900 \| 0.097 \| - \| - \| - \| - \|
	\| 4.4248 \| 1000 \| 0.0853 \| 0.1026 \| 0.7281 \| 0.7409 \| 0.7468 \|
	\| 4.8673 \| 1100 \| 0.086 \| - \| - \| - \| - \|
	\| 5.3097 \| 1200 \| 0.0723 \| - \| - \| - \| - \|
	\| 5.7522 \| 1300 \| 0.0678 \| - \| - \| - \| - \|
	\| 6.1947 \| 1400 \| 0.0655 \| - \| - \| - \| - \|
	\| 6.6372 \| 1500 \| 0.0583 \| 0.0970 \| 0.7252 \| 0.7479 \| 0.7502 \|
	\| 7.0796 \| 1600 \| 0.0586 \| - \| - \| - \| - \|
	\| 7.5221 \| 1700 \| 0.0521 \| - \| - \| - \| - \|
	\| 7.9646 \| 1800 \| 0.049 \| - \| - \| - \| - \|
	\| 8.4071 \| 1900 \| 0.0437 \| - \| - \| - \| - \|
	\| 8.8496 \| 2000 \| 0.0443 \| 0.0974 \| 0.7193 \| 0.7427 \| 0.7455 \|


	### Framework Versions
	- Python: 3.12.0
	- Sentence Transformers: 3.0.1
	- Transformers: 4.41.2
	- PyTorch: 2.3.1+cu118
	- Accelerate: 0.31.0
	- Datasets: 2.20.0
	- Tokenizers: 0.19.1

	## Citation

	### BibTeX

	#### Sentence Transformers
	```bibtex
	@inproceedings{reimers-2019-sentence-bert,
	title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
	author = "Reimers, Nils and Gurevych, Iryna",
	booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
	month = "11",
	year = "2019",
	publisher = "Association for Computational Linguistics",
	url = "https://arxiv.org/abs/1908.10084",
	}
	```

	#### WeightedMultipleNegativesRankingLoss
	```bibtex
	@misc{henderson2017efficient,
	title={Efficient Natural Language Response Suggestion for Smart Reply},
	author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
	year={2017},
	eprint={1705.00652},
	archivePrefix={arXiv},
	primaryClass={cs.CL}
	}
	```

	<!--
	## Glossary

	Clearly define terms in order to be accessible across audiences.
	-->

	<!--
	## Model Card Authors

	Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.
	-->

	<!--
	## Model Card Contact

	Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.
	-->