How Post-Training Shapes Biological Reasoning Models | Paper Citation Record

Observation a20c7d98-b4c3-4b32-ae5d-991e3b9dc530 · outbound

This paper cites Bioreason: Incentivizing multi- modal biological reasoning within a dna-llm model.arXiv preprint arXiv:2505.23579.

How Post-Training Shapes Biological Reasoning Models Bioreason: Incentivizing multi- modal biological reasoning within a dna-llm model.arXiv preprint arXiv:2505.23579

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.012328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ee550f2-3500-41be-8ffe-6fa307534992 · outbound

This paper cites rbio1-training scientific reasoning llms with biological world models as soft verifiers.bioRxiv, pages 2025–08.

How Post-Training Shapes Biological Reasoning Models rbio1-training scientific reasoning llms with biological world models as soft verifiers.bioRxiv, pages 2025–08

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.724283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b29dd336-f399-489e-aaa5-104c838e8949 · outbound

This paper cites Bioreason-pro: Advancing protein function prediction with multimodal biological reasoning.bioRxiv, pages 2026–03.

How Post-Training Shapes Biological Reasoning Models Bioreason-pro: Advancing protein function prediction with multimodal biological reasoning.bioRxiv, pages 2026–03

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.828151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 816c229b-c3c4-47dc-a2c3-46e266c7810f · outbound

This paper cites Evolm: In search of lost language model training dynamics.

How Post-Training Shapes Biological Reasoning Models Evolm: In search of lost language model training dynamics

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.665407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 499ecdb0-624d-4737-9ecb-075955457fbc · outbound

This paper cites Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638.

How Post-Training Shapes Biological Reasoning Models Deepseek-r1 incentivizes reasoning in llms through reinforcement learning.Nature, 645(8081):633–638

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.758610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f1bbcac1-8a10-4861-89e9-2b8793c6b517 · outbound

This paper cites Reinforcement Learning for Reasoning in Large Language Models with One Training Example.

How Post-Training Shapes Biological Reasoning Models Reinforcement Learning for Reasoning in Large Language Models with One Training Example

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-01T07:55:31.008268Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 01f37643-6cbc-4316-8061-43b2abeb325a · outbound

This paper cites Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? NeurIPS, 2025.

How Post-Training Shapes Biological Reasoning Models Does reinforcement learning really incentivize reasoning capacity in llms beyond the base model? NeurIPS, 2025

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.716775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c207318a-eee8-496e-8268-a0f6e2abae2c · outbound

This paper cites MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning.

How Post-Training Shapes Biological Reasoning Models MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.053037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5c6daebd-6c49-45fc-a62f-820dd64a65fb · outbound

This paper cites OpenThoughts: data recipes for reasoning models.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models OpenThoughts: data recipes for reasoning models.ICLR, 2026

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.806378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c9507af8-2762-4e0e-bfb0-40d57a35795e · outbound

This paper cites Scaling large language models for next-generation single-cell analysis.BioRxiv, pages 2025–04, 2026.

How Post-Training Shapes Biological Reasoning Models Scaling large language models for next-generation single-cell analysis.BioRxiv, pages 2025–04, 2026

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.750766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 257b801a-42a2-4ede-96e9-14f9eb5e0e7d · outbound

This paper cites an unresolved cited work.

How Post-Training Shapes Biological Reasoning Models Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-07-06T14:32:35.763077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c6dbf461-4e3b-4668-8bf3-f00b16fc8ff6 · outbound

This paper cites Unleashing scientific reasoning for bio-experimental protocol generation via structured component-based reward mechanism.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models Unleashing scientific reasoning for bio-experimental protocol generation via structured component-based reward mechanism.ICLR, 2026

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.744790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 85be97a7-5171-49e1-90d4-78255164f763 · outbound

This paper cites Sci-verifier: Scientific verifier with thinking.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models Sci-verifier: Scientific verifier with thinking.ICLR, 2026

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.811973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b42d105a-06c1-46e3-96ca-a5e50693e051 · outbound

This paper cites Cellduality: Un- locking biological reasoning in LLMs with self-supervised RLVR.

How Post-Training Shapes Biological Reasoning Models Cellduality: Un- locking biological reasoning in LLMs with self-supervised RLVR

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.726468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1b9f73cb-422a-4c9c-9a95-512ce6215d42 · outbound

This paper cites VCWorld: a biological world model for virtual cell simulation.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models VCWorld: a biological world model for virtual cell simulation.ICLR, 2026

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.822513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 511a44f2-54ac-4500-8c99-60c3aebe3af2 · outbound

This paper cites Helix: Evolutionary reinforcement learning for open-ended scientific problem solving.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models Helix: Evolutionary reinforcement learning for open-ended scientific problem solving.ICLR, 2026

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.815413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a159b424-6f9a-4f14-b82e-8140af61d780 · outbound

This paper cites Reshaping reasoning in llms: A theoretical analysis of rl training dynamics through pattern selection.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models Reshaping reasoning in llms: A theoretical analysis of rl training dynamics through pattern selection.ICLR, 2026

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.746786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 13c30a8b-7aeb-4536-91f1-b8e5e5526430 · outbound

This paper cites Training dynamics impact post- training quantization robustness.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models Training dynamics impact post- training quantization robustness.ICLR, 2026

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.705513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 575be23d-0c70-4665-99c8-ebe38865670a · outbound

This paper cites The coverage principle: How pre-training enables post-training.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models The coverage principle: How pre-training enables post-training.ICLR, 2026

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.718551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e7c480c4-c8c9-4abb-961b-dcdf2f10a011 · outbound

This paper cites Benchmarking algorithms for generalizable single-cell perturbation response prediction.Nature Methods, 23(2):451–464.

How Post-Training Shapes Biological Reasoning Models Benchmarking algorithms for generalizable single-cell perturbation response prediction.Nature Methods, 23(2):451–464

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.820779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a01c3af3-411e-4356-96e6-f3aaf6f4e2c0 · outbound

This paper cites A fully automated benchmarking suite to compare macromolecular complexes.Nature Methods, 23(2):387–394, 2026.

How Post-Training Shapes Biological Reasoning Models A fully automated benchmarking suite to compare macromolecular complexes.Nature Methods, 23(2):387–394, 2026

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.752761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 08b8a02b-a6e4-496f-8e0e-04274492f39e · outbound

This paper cites PLINDER: the protein-ligand interactions dataset and evaluation resource.BioRxiv, pages 2024–07, 2024.

How Post-Training Shapes Biological Reasoning Models PLINDER: the protein-ligand interactions dataset and evaluation resource.BioRxiv, pages 2024–07, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.761050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f0b8d022-7eb5-40b7-81b3-c2dac3b9463f · outbound

This paper cites ProCyon: a multimodal foundation model for protein phenotypes.BioRxiv, pages 2024–12, 2025.

How Post-Training Shapes Biological Reasoning Models ProCyon: a multimodal foundation model for protein phenotypes.BioRxiv, pages 2024–12, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.783200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ce89901b-490e-491e-b055-8a9657b7d5cb · outbound

This paper cites Evaluating generalizability of artificial intelligence models for molecular datasets.

How Post-Training Shapes Biological Reasoning Models Evaluating generalizability of artificial intelligence models for molecular datasets

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.800994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 848fbc79-e7eb-4adc-96ea-a5456fefaa0e · outbound

This paper cites Zero-shot evaluation reveals limitations of single-cell foundation models.Genome Biology, 26(1):101, 2025.

How Post-Training Shapes Biological Reasoning Models Zero-shot evaluation reveals limitations of single-cell foundation models.Genome Biology, 26(1):101, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.785271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a867ed26-1b31-4416-9e05-1c92b4df6512 · outbound

This paper cites Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines.Nature Methods, 22(8):1657–1661.

How Post-Training Shapes Biological Reasoning Models Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines.Nature Methods, 22(8):1657–1661

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.799179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 896eb9a7-0c99-4a86-85ee-8191caf68737 · outbound

This paper cites LoongRL: reinforcement learning for advanced reasoning over long contexts.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models LoongRL: reinforcement learning for advanced reasoning over long contexts.ICLR, 2026

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.764879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b73ba19c-281b-40fb-9d52-4efc77c1b216 · outbound

This paper cites The art of scaling reinforcement learning compute for llms.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models The art of scaling reinforcement learning compute for llms.ICLR, 2026

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.792045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 755c69e7-dfac-4b11-aff4-6cce47a5afb2 · outbound

This paper cites Rethinking LLM reasoning: From explicit trajectories to latent representations.

How Post-Training Shapes Biological Reasoning Models Rethinking LLM reasoning: From explicit trajectories to latent representations

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.797233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 032e4c82-084c-4ab7-bf53-53aaee1aefea · outbound

This paper cites CoT-Evo: evolutionary distillation of chain-of-thought for scientific reasoning.ICLR, 2026.

How Post-Training Shapes Biological Reasoning Models CoT-Evo: evolutionary distillation of chain-of-thought for scientific reasoning.ICLR, 2026

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.819079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b416dea7-b882-4a1d-ac06-b6ea7a33cf7b · outbound

This paper cites scPilot: Large language model reasoning toward automated single-cell analysis and discovery.NeurIPS, 2025.

How Post-Training Shapes Biological Reasoning Models scPilot: Large language model reasoning toward automated single-cell analysis and discovery.NeurIPS, 2025

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.652371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bd4168e3-c90f-4ff7-b800-e511d532242e · outbound

This paper cites AI-researcher: autonomous scientific innovation.NeurIPS, 2025.

How Post-Training Shapes Biological Reasoning Models AI-researcher: autonomous scientific innovation.NeurIPS, 2025

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.663167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fad6bc51-644e-40b9-ad54-89fdaebf3bdc · outbound

This paper cites Training a scientific reasoning model for chemistry.NeurIPS, 2025.

How Post-Training Shapes Biological Reasoning Models Training a scientific reasoning model for chemistry.NeurIPS, 2025

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.770421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a8d2161a-d832-4c5d-ac22-6e8621d226fc · outbound

This paper cites Language models for biological research: a primer.Nature Methods, 21(8):1422–1429.

How Post-Training Shapes Biological Reasoning Models Language models for biological research: a primer.Nature Methods, 21(8):1422–1429

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.777113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6baa52b6-fdba-4d49-a65e-3a400d7c4ad0 · outbound

This paper cites Dnabert: pre-trained bidirectional encoder representations from transformers model for dna-language in genome.Bioinformatics, 37(15):2112–2120.

How Post-Training Shapes Biological Reasoning Models Dnabert: pre-trained bidirectional encoder representations from transformers model for dna-language in genome.Bioinformatics, 37(15):2112–2120

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.773048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2eeb9d5a-7574-4dad-b1c5-9b1cef876972 · outbound

This paper cites DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome.

How Post-Training Shapes Biological Reasoning Models DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.056974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 071b65ba-0a11-45a8-ba57-1b270c13a889 · outbound

This paper cites Sequence modeling and design from molecular to genome scale with evo.Science, 386(6723):eado9336.

How Post-Training Shapes Biological Reasoning Models Sequence modeling and design from molecular to genome scale with evo.Science, 386(6723):eado9336

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.779263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cc7196dc-d36d-4efb-a395-c897fad90770 · outbound

This paper cites Genome modelling and design across all domains of life with evo 2.Nature, pages 1–13.

How Post-Training Shapes Biological Reasoning Models Genome modelling and design across all domains of life with evo 2.Nature, pages 1–13

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.804438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5e5066e0-af51-4f73-94db-ce8e00b3b2d2 · outbound

This paper cites Nucleotide transformer: building and evaluating robust foundation models for human genomics.Nature Methods, 22(2):287–297.

How Post-Training Shapes Biological Reasoning Models Nucleotide transformer: building and evaluating robust foundation models for human genomics.Nature Methods, 22(2):287–297

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.817254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06e0b40c-1c35-4e32-99aa-ec2e705723ef · outbound

This paper cites Alphagenome: advancing regulatory variant effect prediction with a unified dna sequence model.BioRxiv, pages 2025–06, 2025.

How Post-Training Shapes Biological Reasoning Models Alphagenome: advancing regulatory variant effect prediction with a unified dna sequence model.BioRxiv, pages 2025–06, 2025

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.826186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ddc087a6-56aa-42b8-b8be-3db7a9bddf7c · outbound

This paper cites The omg dataset: An open metagenomic corpus for mixed-modality genomic language modeling.bioRxiv, pages 2024–08, 2024.

How Post-Training Shapes Biological Reasoning Models The omg dataset: An open metagenomic corpus for mixed-modality genomic language modeling.bioRxiv, pages 2024–08, 2024

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.712431Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8b5d8dcd-840e-4ffa-80ca-4d551619f7fd · outbound

This paper cites PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?.

How Post-Training Shapes Biological Reasoning Models PhageBench: Can LLMs Understand Raw Bacteriophage Genomes?

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-07-01T07:55:31.060469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8295647-a75c-4943-bcd5-8bb9ba879c3e · outbound

This paper cites Orthrus: toward evolutionary and functional rna foundation models.Nature Methods, pages 1–11, 2026.

How Post-Training Shapes Biological Reasoning Models Orthrus: toward evolutionary and functional rna foundation models.Nature Methods, pages 1–11, 2026

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.654855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c78f641-bbaa-4ece-bbb3-7b7bcd1b7c51 · outbound

This paper cites Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions.

How Post-Training Shapes Biological Reasoning Models Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

Reference 44

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T07:55:31.052546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a7e05066-7bb3-4291-9d24-5eab03f1024d · outbound

This paper cites A cross-species generative cell atlas across 1.5 billion years of evolution: The transcriptformer single-cell model.bioRxiv, pages 2025–04, 2025.

How Post-Training Shapes Biological Reasoning Models A cross-species generative cell atlas across 1.5 billion years of evolution: The transcriptformer single-cell model.bioRxiv, pages 2025–04, 2025

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.708126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4c0de922-8f47-4581-96b9-8310ef5d9f1e · outbound

This paper cites scgpt: toward building a foundation model for single-cell multi-omics using generative ai.

How Post-Training Shapes Biological Reasoning Models scgpt: toward building a foundation model for single-cell multi-omics using generative ai

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.748740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b1cda3db-3dba-4869-aa03-bfabd5156de8 · outbound

This paper cites Transfer learning enables predictions in network biology.Nature, 618(7965):616–624.

How Post-Training Shapes Biological Reasoning Models Transfer learning enables predictions in network biology.Nature, 618(7965):616–624

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.810228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ed4a13bd-39dc-46ee-8f6e-a82e6b13d112 · outbound

This paper cites Predicting cellular responses to perturbation across diverse contexts with state.BioRxiv, pages 2025–06, 2025.

How Post-Training Shapes Biological Reasoning Models Predicting cellular responses to perturbation across diverse contexts with state.BioRxiv, pages 2025–06, 2025

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.710502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 551887b9-4070-4c7f-b6a4-9492b365dfcb · outbound

This paper cites Large-scale foundation model on single-cell transcriptomics.Nature methods, 21(8):1481–1491, 2024.

How Post-Training Shapes Biological Reasoning Models Large-scale foundation model on single-cell transcriptomics.Nature methods, 21(8):1481–1491, 2024

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.756603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d9eceec1-310f-4ba8-9dbc-eafd572fe9fc · outbound

This paper cites scgenept: Is language all you need for modeling single-cell perturbations?bioRxiv, pages 2024–10, 2024.

How Post-Training Shapes Biological Reasoning Models scgenept: Is language all you need for modeling single-cell perturbations?bioRxiv, pages 2024–10, 2024

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.787214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 19e5960b-4067-4e18-896a-9f261b3045b2 · outbound

This paper cites Evolutionary-scale prediction of atomic-level protein structure with a language model.Science, 379(6637):1123–1130.

How Post-Training Shapes Biological Reasoning Models Evolutionary-scale prediction of atomic-level protein structure with a language model.Science, 379(6637):1123–1130

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.808395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dccdf8fe-4535-4ab0-bcc7-4bbebdb27c4c · outbound

This paper cites Simulating 500 million years of evolution with a language model.Science, 387(6736):850–858.

How Post-Training Shapes Biological Reasoning Models Simulating 500 million years of evolution with a language model.Science, 387(6736):850–858

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.824434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3b2f2671-9088-408d-ae26-d2e0736f6242 · outbound

This paper cites Progen2: exploring the boundaries of protein language models.Cell systems, 14(11):968–978.

How Post-Training Shapes Biological Reasoning Models Progen2: exploring the boundaries of protein language models.Cell systems, 14(11):968–978

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.701409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b6d63400-b20d-4151-8746-e38f823624ae · outbound

This paper cites Unified rational protein engineering with sequence-based deep representation learning.

How Post-Training Shapes Biological Reasoning Models Unified rational protein engineering with sequence-based deep representation learning

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.767928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d45e374-085d-4059-9001-c2f43a8fb6e0 · outbound

This paper cites Multimodal learning enables chat-based exploration of single-cell data.Nature Biotechnology, pages 1–11.

How Post-Training Shapes Biological Reasoning Models Multimodal learning enables chat-based exploration of single-cell data.Nature Biotechnology, pages 1–11

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.660354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b0033596-67b7-40e5-9396-11162249271c · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744.

How Post-Training Shapes Biological Reasoning Models Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.738517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2b5eb6f2-2725-4b83-8286-9a22ed96748e · outbound

This paper cites D-cpt law: Domain-specific continual pre-training scaling law for large language models.Advances in Neural Information Processing Systems, 37:90318–90354, 2024.

How Post-Training Shapes Biological Reasoning Models D-cpt law: Domain-specific continual pre-training scaling law for large language models.Advances in Neural Information Processing Systems, 37:90318–90354, 2024

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.813782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 72363057-8c18-4cc9-9655-7f1b18f974c4 · outbound

This paper cites Understanding the effects of RLHF on LLM generalisation and diversity.

How Post-Training Shapes Biological Reasoning Models Understanding the effects of RLHF on LLM generalisation and diversity

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.728496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7ecf1744-098d-48de-ba3d-415a441462f9 · outbound

This paper cites Don’t stop pretraining: Adapt language models to domains and tasks.

How Post-Training Shapes Biological Reasoning Models Don’t stop pretraining: Adapt language models to domains and tasks

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.649349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ab08da76-09d0-4933-ada7-d1ed2e027c0e · outbound

This paper cites Scaling Laws for Neural Language Models.

How Post-Training Shapes Biological Reasoning Models Scaling Laws for Neural Language Models

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-07-01T07:55:31.024748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5f10e1e4-de71-4874-b727-e30b5e443897 · outbound

This paper cites Training compute-optimal large language models.

How Post-Training Shapes Biological Reasoning Models Training compute-optimal large language models

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.732234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fdce36f1-ba12-4b03-943d-6b308e16b38d · outbound

This paper cites Pythia: A suite for analyzing large language models across training and scaling.

How Post-Training Shapes Biological Reasoning Models Pythia: A suite for analyzing large language models across training and scaling

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.781141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fea5dd5f-9af4-4673-af6b-0a8c9d4ab3a7 · outbound

This paper cites When scaling meets LLM finetuning: The effect of data, model and finetuning method.

How Post-Training Shapes Biological Reasoning Models When scaling meets LLM finetuning: The effect of data, model and finetuning method

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.742642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f108a764-8d7c-4684-bfc9-62af0f54910c · outbound

This paper cites Continual Pre-Training of Large Language Models: How to (re)warm your model?.

How Post-Training Shapes Biological Reasoning Models Continual Pre-Training of Large Language Models: How to (re)warm your model?

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.039643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0e975219-56d7-4054-bb91-6b67d87a5fb2 · outbound

This paper cites Simple and Scalable Strategies to Continually Pre-train Large Language Models.

How Post-Training Shapes Biological Reasoning Models Simple and Scalable Strategies to Continually Pre-train Large Language Models

Reference 65

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T07:55:31.044759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 18fcd226-fa99-4f15-8010-3f13a9de0adf · outbound

This paper cites Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models.

How Post-Training Shapes Biological Reasoning Models Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models

Reference 66

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.048963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6984a660-002e-4fb4-b5e5-71f4bfe32bb6 · outbound

This paper cites Continual pre-training of language models.

How Post-Training Shapes Biological Reasoning Models Continual pre-training of language models

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.740716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7117178-3b1a-4c95-b591-54621d51d14f · outbound

This paper cites Adapting Large Language Models to Domains via Reading Comprehension.

How Post-Training Shapes Biological Reasoning Models Adapting Large Language Models to Domains via Reading Comprehension

Reference 68

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T07:55:31.040486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 308dd23d-ddd4-4092-a582-633c43cd30d2 · outbound

This paper cites Composer 2 technical report, 2026.

How Post-Training Shapes Biological Reasoning Models Composer 2 technical report, 2026

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.730144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 12a49980-a0ab-400a-a6ba-96471262abcc · outbound

This paper cites Sft memorizes, rl generalizes: A comparative study of foundation model post-training.

How Post-Training Shapes Biological Reasoning Models Sft memorizes, rl generalizes: A comparative study of foundation model post-training

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.722288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d362e53c-7dd7-4d5f-8c51-88397c8c4b75 · outbound

This paper cites Gene-r1: Reasoning with data- augmented lightweight llms for gene set analysis.

How Post-Training Shapes Biological Reasoning Models Gene-r1: Reasoning with data- augmented lightweight llms for gene set analysis

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.657209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ca5363fa-0429-4cc9-82e4-98d5859b14cb · outbound

This paper cites Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning.

How Post-Training Shapes Biological Reasoning Models Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning

Reference 72

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.065267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 27a3d72a-1056-459c-bf2c-a4096d5a5c20 · outbound

This paper cites Medea: An omics ai agent for therapeutic discovery.bioRxiv, pages 2026–01, 2026.

How Post-Training Shapes Biological Reasoning Models Medea: An omics ai agent for therapeutic discovery.bioRxiv, pages 2026–01, 2026

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.795469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4889816c-966e-4027-bf87-512056324207 · outbound

This paper cites Interpro in 2022.Nucleic acids research, 51(D1):D418–D427, 2023.

How Post-Training Shapes Biological Reasoning Models Interpro in 2022.Nucleic acids research, 51(D1):D418–D427, 2023

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.829995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 115bece9-112f-4e64-875e-965b38192a47 · outbound

This paper cites Qwen3 Technical Report.

How Post-Training Shapes Biological Reasoning Models Qwen3 Technical Report

Reference 75

Resolution: verified exact; local_arxiv, observed 2026-07-01T07:55:31.034809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f64de101-63c8-4b4b-bfc9-25925a4b8f4d · outbound

This paper cites an unresolved cited work.

How Post-Training Shapes Biological Reasoning Models Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-07-06T14:32:35.802667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9679af1-fdbf-4e86-bb53-5b93f05a84f9 · outbound

This paper cites FineFineWeb: A comprehensive study on fine- grained domain web corpus.

How Post-Training Shapes Biological Reasoning Models FineFineWeb: A comprehensive study on fine- grained domain web corpus

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.714422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f2b2cadd-15cc-43e8-bdff-913b75f58cbb · outbound

This paper cites an unresolved cited work.

How Post-Training Shapes Biological Reasoning Models Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-07-06T14:32:35.720343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3eb1caf4-1266-4ae5-8bd1-752a63fbec1e · outbound

This paper cites KEGG: Kyoto Encyclopedia of Genes and Genomes.

How Post-Training Shapes Biological Reasoning Models KEGG: Kyoto Encyclopedia of Genes and Genomes

Reference 79

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.320351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 963eead3-b552-4e9d-b70d-607d94754268 · outbound

This paper cites New approach for understanding genome variations in KEGG.Nucleic Acids Research, 47(D1): D590–D595, 2019.

How Post-Training Shapes Biological Reasoning Models New approach for understanding genome variations in KEGG.Nucleic Acids Research, 47(D1): D590–D595, 2019

Reference 80

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.300204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f2263870-3ce2-4e2c-a3a4-1ee979739682 · outbound

This paper cites ClinVar: improvements to accessing data.Nucleic Acids Research, 48(D1):D835–D844, 2020.

How Post-Training Shapes Biological Reasoning Models ClinVar: improvements to accessing data.Nucleic Acids Research, 48(D1):D835–D844, 2020

Reference 81

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.296561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation af453ed8-14b5-4c3b-ab30-586d8d60a7e4 · outbound

This paper cites dbSNP: the NCBI database of genetic variation.Nucleic Acids Research, 29(1):308–311, 2001.

How Post-Training Shapes Biological Reasoning Models dbSNP: the NCBI database of genetic variation.Nucleic Acids Research, 29(1):308–311, 2001

Reference 82

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.309641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39118bc0-b694-4b11-b83c-d8efa9707d37 · outbound

This paper cites Cosmic: the catalogue of somatic mutations in cancer.Nucleic Acids Re- search, 47(D1):D941–D947.

How Post-Training Shapes Biological Reasoning Models Cosmic: the catalogue of somatic mutations in cancer.Nucleic Acids Re- search, 47(D1):D941–D947

Reference 84

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.312306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 17f97da7-0fc6-4a01-a033-2f712d6b3df1 · outbound

This paper cites CZ CELLxGENE Discover: A single-cell data platform for scalable exploration, analysis and modeling of aggregated data.Nucleic Acids Research, 53(D1):D886–D900, 2025.

How Post-Training Shapes Biological Reasoning Models CZ CELLxGENE Discover: A single-cell data platform for scalable exploration, analysis and modeling of aggregated data.Nucleic Acids Research, 53(D1):D886–D900, 2025

Reference 85

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.323512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ef7371fc-0ffd-4745-ab49-af9da96d986f · outbound

This paper cites The next- generation Open Targets Platform: reimagined, redesigned, rebuilt.Nucleic Acids Research, 51 (D1):D1353–D1359, 2023.

How Post-Training Shapes Biological Reasoning Models The next- generation Open Targets Platform: reimagined, redesigned, rebuilt.Nucleic Acids Research, 51 (D1):D1353–D1359, 2023

Reference 86

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.297363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 273b911b-1949-4021-840b-a863b1963cee · outbound

This paper cites Chembl: a large-scale bioactivity database for drug discovery.Nucleic acids research, 40(D1):D1100– D1107.

How Post-Training Shapes Biological Reasoning Models Chembl: a large-scale bioactivity database for drug discovery.Nucleic acids research, 40(D1):D1100– D1107

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.667864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d644805d-a49c-4ce4-b891-a9688790ff7e · outbound

This paper cites https://doi.org/10.1093/nar/gkac1052.

How Post-Training Shapes Biological Reasoning Models https://doi.org/10.1093/nar/gkac1052

Reference 88

Resolution: metadata mismatch; doi, observed 2026-07-01T07:55:30.288407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3921d0a8-9247-49cb-b915-025c85957f6b · outbound

This paper cites KEGG as a reference resource for gene and protein annotation.

How Post-Training Shapes Biological Reasoning Models KEGG as a reference resource for gene and protein annotation

Reference 89

Resolution: malformed identifier; doi_truncated, observed 2026-07-01T07:55:30.288618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf264506-d2d5-4e3b-a1d1-5641d988beb8 · outbound

This paper cites https://doi.org/10.1093/GENETICS/IYAD031 [Wang2022] Wang, J.

How Post-Training Shapes Biological Reasoning Models https://doi.org/10.1093/GENETICS/IYAD031 [Wang2022] Wang, J

Reference 90

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.306594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d4a9903-cb1b-4fca-8a0c-cdf575108c3b · outbound

This paper cites The string database in 2025: protein networks with directional- ity of regulation.Nucleic Acids Research, 53(D1):D730–D737, 01 2025.

How Post-Training Shapes Biological Reasoning Models The string database in 2025: protein networks with directional- ity of regulation.Nucleic Acids Research, 53(D1):D730–D737, 01 2025

Reference 91

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.294209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e2d9e3a3-3369-4b5f-ab7d-083f34ff6684 · outbound

This paper cites A large- scale evaluation of computational protein function prediction.Nature Methods, 10(3):221–227,.

How Post-Training Shapes Biological Reasoning Models A large- scale evaluation of computational protein function prediction.Nature Methods, 10(3):221–227,

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.736457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26c048d7-6c17-47d1-9959-9040faa5fdc1 · outbound

This paper cites Radivojac, W.

How Post-Training Shapes Biological Reasoning Models Radivojac, W

Reference 93

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.317566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7409f7f7-5c56-4a03-a430-4f261268a635 · outbound

This paper cites The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.Genome Biology, 20(1):244, 2019.

How Post-Training Shapes Biological Reasoning Models The CAFA challenge reports improved protein function prediction and new functional annotations for hundreds of genes through experimental screens.Genome Biology, 20(1):244, 2019

Reference 94

Resolution: verified exact; doi, observed 2026-07-01T07:55:30.314880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 42bf3a2b-530c-4da0-8dd5-8b4bf6340fa6 · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

How Post-Training Shapes Biological Reasoning Models LoRA: Low-rank adaptation of large language models

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.733959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cf4bb96a-a23a-4321-8eb2-e42a7f97fc96 · outbound

This paper cites The FineWeb datasets: Decanting the web for the finest text data at scale.

How Post-Training Shapes Biological Reasoning Models The FineWeb datasets: Decanting the web for the finest text data at scale

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.831567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 177e83bb-cff7-4add-8ddc-df7faeb7258d · outbound

This paper cites Decoupled weight decay regularization.

How Post-Training Shapes Biological Reasoning Models Decoupled weight decay regularization

Reference 97

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.754590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 83939c43-0804-4ef7-88d2-5e19336b0378 · outbound

This paper cites Generalized Slow Roll for Tensors.

How Post-Training Shapes Biological Reasoning Models Generalized Slow Roll for Tensors

Reference 98

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T07:55:30.303997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1954ad8b-bf53-4fb5-a941-c065afc68a79 · outbound

This paper cites FlashAttention: Fast and memory-efficient exact attention with IO-awareness.

How Post-Training Shapes Biological Reasoning Models FlashAttention: Fast and memory-efficient exact attention with IO-awareness

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-07-06T14:32:35.789021Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3bee5b8b-92cf-4123-aee4-806b448a2e5a · outbound

This paper cites warm→cos.

How Post-Training Shapes Biological Reasoning Models warm→cos

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-07-01T07:55:31.036741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers