{"as_of":"2026-08-07T18:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c776cfb56e4e3ac7bb468872d03c95eaddd87e2f2e31c88429bba2d44f9f74e3","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":25,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:33:13.022126Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T08:46:48.524247Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2403.07691","last_updated":"2024-03-14T07:47:08Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-03-12T14:34:08Z","title":"ORPO: Monolithic Preference Optimization without Reference Model","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-05-16T09:34:04.394588Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2403.07691"},"observation_digest":"sha256:f143a5cbcc495b4e5228e6144b611c2938a4a31db45be3baef2832328857f059","observation_id":"8652dab5-320d-45a8-9562-97b36a84be95","resolution":{"observed_at":"2026-05-16T09:34:04.760451Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2502.10248","last_updated":"2025-02-24T10:12:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-14T15:58:10Z","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","version":3},"reference_index":132,"source":"arxiv_source","source_observed_at":"2026-05-19T08:02:23.002090Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2502.10248"},"observation_digest":"sha256:32cca2248020d2008a0f04bef270b933c501ed24fb90277890890e430d7549a5","observation_id":"b21e0012-0641-440f-8532-01ea455e22b5","resolution":{"observed_at":"2026-05-19T08:02:23.444098Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-07T14:33:13.022126Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18458","last_updated":"2025-06-01T16:00:34Z","snapshot_observed_at":"2026-08-07T17:40:58.113382Z","submitted_at":"2025-05-24T01:57:12Z","title":"A Survey of LLM $\\times$ DATA","version":3},"reference_index":123,"source":"pdf_text","source_observed_at":"2026-08-07T14:33:13.022126Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2505.18458"},"observation_digest":"sha256:6ae072a290309ed8ef8a708cd42423dbb36f36ac3d2ceefc6ca69c6012908afa","observation_id":"3155b6a5-e84c-4b45-8f01-1f64aff0cdf4","resolution":{"observed_at":"2026-08-07T14:33:13.022126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2506.01247","last_updated":"2026-05-26T21:34:46Z","snapshot_observed_at":"2026-08-07T11:44:23.107478Z","submitted_at":"2025-06-02T01:51:20Z","title":"Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-19T11:35:01.836096Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2506.01247"},"observation_digest":"sha256:7005e2f44a5e79a8674ed366653afd32852f1cdb6ef0b396f8db85e6967d40dc","observation_id":"62236847-4015-4dd4-bcd2-c5010dc25482","resolution":{"observed_at":"2026-05-19T11:37:15.841224Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-07T11:53:49.116840Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.01247","last_updated":"2026-05-26T21:34:46Z","snapshot_observed_at":"2026-08-07T11:44:23.107478Z","submitted_at":"2025-06-02T01:51:20Z","title":"Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering","version":3},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T11:53:49.116840Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2506.01247"},"observation_digest":"sha256:08b42e2a4a90b2f707e9da3895f5f796fdb1025b171ec8f9b8b8cba5f3b8412d","observation_id":"26d3e4f4-ff8b-4332-83df-e5bffdaa1fc0","resolution":{"observed_at":"2026-08-07T11:53:49.116840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-07T11:35:43.435240Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02096","last_updated":"2025-06-02T17:45:16Z","snapshot_observed_at":"2026-08-07T12:51:05.147362Z","submitted_at":"2025-06-02T17:45:16Z","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T11:35:43.435240Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2506.02096"},"observation_digest":"sha256:3c81e9e3dc0b62c0cc801fb91e98f36e3b5340fc33ce5f04611ed6b927691c72","observation_id":"0fe375c1-c7b5-484e-a161-31bcf0593054","resolution":{"observed_at":"2026-08-07T11:35:43.435240Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-06T23:12:12.727040Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19469","last_updated":"2025-06-24T09:53:10Z","snapshot_observed_at":"2026-08-07T12:44:11.285996Z","submitted_at":"2025-06-24T09:53:10Z","title":"Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:12:12.727040Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2506.19469"},"observation_digest":"sha256:e5bddeef51ca6fc19b16d267363f4d5bcd90467c8694380adf83032210d62270","observation_id":"cc933ffa-6545-4645-ae21-a3a1bff3e0ed","resolution":{"observed_at":"2026-08-06T23:12:12.727040Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-06T21:52:20.860831Z","title":"How abilities in large lan- guage models are affected by supervised fine-tuning data composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23219","last_updated":"2025-06-29T13:04:27Z","snapshot_observed_at":"2026-08-07T17:25:28.930681Z","submitted_at":"2025-06-29T13:04:27Z","title":"UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:52:20.860831Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2506.23219"},"observation_digest":"sha256:18c5ec14a87f31f2a5fef623080535cb8f910d3128c01b96dc74f7fd5cb728eb","observation_id":"b09e2d68-1545-4e28-b366-9000934f1574","resolution":{"observed_at":"2026-08-06T21:52:20.860831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-06T15:40:33.211650Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.15281","last_updated":"2025-07-21T06:30:39Z","snapshot_observed_at":"2026-08-07T11:11:48.484672Z","submitted_at":"2025-07-21T06:30:39Z","title":"A Novel Self-Evolution Framework for Large Language Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T15:40:33.211650Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2507.15281"},"observation_digest":"sha256:459f8881f2b9045423604e968ddb35df0b485194285af75c94b62dee3265bb55","observation_id":"1b65bf2a-d1b6-42d3-a027-e421e04ad8f6","resolution":{"observed_at":"2026-08-06T15:40:33.211650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-06T14:13:07.198161Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.19672","last_updated":"2025-07-25T20:52:58Z","snapshot_observed_at":"2026-08-07T12:02:14.124506Z","submitted_at":"2025-07-25T20:52:58Z","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","version":1},"reference_index":250,"source":"arxiv_source","source_observed_at":"2026-08-06T14:13:07.198161Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2507.19672"},"observation_digest":"sha256:89764de1cc4bb34e24959857f5d83e96fb1b1ab1a093b589e01072b29d9de3e4","observation_id":"60a2d3ca-768d-4f57-a969-b2939f99aea6","resolution":{"observed_at":"2026-08-06T14:13:07.198161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2507.21046","last_updated":"2026-01-16T20:59:08Z","snapshot_observed_at":"2026-08-01T06:32:44.461162Z","submitted_at":"2025-07-28T17:59:05Z","title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","version":4},"reference_index":135,"source":"arxiv_source","source_observed_at":"2026-05-14T22:23:14.621091Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2507.21046"},"observation_digest":"sha256:99e52de042479bddbe0137a943c491952967ac199eee7d81bb9755ae22595305","observation_id":"92418225-6887-47ca-b17b-254772fb5a87","resolution":{"observed_at":"2026-05-14T22:23:15.889287Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-06T20:39:30.734150Z","title":"Es, S., James, J., Espinosa-Anke, L., and Schockaert, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21099","last_updated":"2025-07-03T05:36:08Z","snapshot_observed_at":"2026-08-07T13:06:49.523578Z","submitted_at":"2025-07-03T05:36:08Z","title":"Rewrite-to-Rank: Optimizing Ad Visibility via Retrieval-Aware Text Rewriting","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T20:39:30.734150Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2507.21099"},"observation_digest":"sha256:0b274aeb4b94172fefb547e8d04bba76835b5ff6f932730155cd86bc7ebd78a5","observation_id":"4890eba5-3883-4a22-9ed6-28b5bacb4a8c","resolution":{"observed_at":"2026-08-06T20:39:30.734150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-05T18:05:31.908933Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15182","last_updated":"2025-08-21T02:39:14Z","snapshot_observed_at":"2026-08-05T18:05:30.057717Z","submitted_at":"2025-08-21T02:39:14Z","title":"SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-05T18:05:31.908933Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2508.15182"},"observation_digest":"sha256:92a75fcac9544e2e9bf6c253be2e5982dbc14e458479a669d2a90d01da74b625","observation_id":"b733b185-214c-44bc-818b-e692463e14a5","resolution":{"observed_at":"2026-08-05T18:05:31.908933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-05T13:42:11.831627Z","title":"How abilities in large lan- guage models are affected by supervised fine-tuning data composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.00425","last_updated":"2025-08-30T09:13:10Z","snapshot_observed_at":"2026-08-05T13:42:10.113088Z","submitted_at":"2025-08-30T09:13:10Z","title":"The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with Camlang","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T13:42:11.831627Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2509.00425"},"observation_digest":"sha256:b894d7b9661a13ad44352d314e980a75f35c2edd33b6e7fd0fe994cb7aee90c4","observation_id":"5d1f6ab6-471e-4570-92e2-b9d1286b8dca","resolution":{"observed_at":"2026-08-05T13:42:11.831627Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2510.09689","last_updated":"2026-04-17T02:42:09Z","snapshot_observed_at":"2026-07-06T22:32:22.953630Z","submitted_at":"2025-10-09T09:44:14Z","title":"When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-18T09:29:14.842228Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2510.09689"},"observation_digest":"sha256:e12a6aa95747cdd3d8827657b9507a1363a9042e7962c2f04627e4255b270ea1","observation_id":"074520f4-70f3-45fe-9b00-ac0876361407","resolution":{"observed_at":"2026-05-18T09:31:11.665009Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-03T02:34:18.740900Z","title":"How abilities in large lan- guage models are affected by supervised fine-tuning data composition.arXiv preprint arXiv:2310.05492,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.17205","last_updated":"2026-07-30T22:57:15Z","snapshot_observed_at":"2026-08-07T16:20:57.572055Z","submitted_at":"2026-03-17T23:11:45Z","title":"OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-03T02:34:18.740900Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2603.17205"},"observation_digest":"sha256:7cd710b0b875a7af078ef3560bd3b919d03d4008abd0ac9dd03358403a64a705","observation_id":"6cea7470-e9d7-484a-b8f4-8affa5e61608","resolution":{"observed_at":"2026-08-03T02:34:18.740900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2604.17184","last_updated":"2026-07-02T22:48:15Z","snapshot_observed_at":"2026-07-12T19:06:03.469874Z","submitted_at":"2026-04-19T01:01:44Z","title":"SynthFix: Adaptive Neuro-Symbolic Code Vulnerability Repair","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-05-10T06:39:29.822371Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2604.17184"},"observation_digest":"sha256:b4d7df94e65526394f6ab860182e250b6e4bbaa58237f8a1e501739c8832845d","observation_id":"221e8487-5d14-4c5e-a37a-3c3b24d4c4ae","resolution":{"observed_at":"2026-05-10T06:41:36.610450Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2605.01123","last_updated":"2026-05-01T21:49:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-01T21:49:20Z","title":"PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-05-09T19:09:07.557773Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2605.01123"},"observation_digest":"sha256:9997346bfdd45d653514597ee210ee6e5a69a507fbae14ea51faa4436ab7c4c9","observation_id":"5872d93f-afc3-4421-8cf0-33a559f0fc59","resolution":{"observed_at":"2026-05-11T15:51:42.679529Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2605.04065","last_updated":"2026-05-07T04:49:30Z","snapshot_observed_at":"2026-07-06T23:16:54.673178Z","submitted_at":"2026-04-11T07:26:04Z","title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","version":2},"reference_index":239,"source":"arxiv_source","source_observed_at":"2026-05-10T16:58:10.013475Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2605.04065"},"observation_digest":"sha256:eb0426f11aef55042214dd3afd7b9ef058568bf9029a7dd391810e0daea4963a","observation_id":"78ccc67a-48e6-4e35-8d02-a5606d69498a","resolution":{"observed_at":"2026-05-11T07:45:59.943636Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2605.04066","last_updated":"2026-05-07T04:57:40Z","snapshot_observed_at":"2026-08-02T15:49:26.057284Z","submitted_at":"2026-04-11T07:34:59Z","title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","version":2},"reference_index":224,"source":"arxiv_source","source_observed_at":"2026-05-10T16:51:19.555272Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2605.04066"},"observation_digest":"sha256:14b49756aa804f0eb10532e2105a41cbd9e6cd021ade2bd3c771fb2a6f04aa37","observation_id":"e3fda278-fdb2-4e59-b928-17a01b6b7640","resolution":{"observed_at":"2026-05-11T08:01:00.877774Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2605.09533","last_updated":"2026-05-10T13:35:16Z","snapshot_observed_at":"2026-07-06T23:21:35.327066Z","submitted_at":"2026-05-10T13:35:16Z","title":"Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-05-12T05:06:43.040359Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2605.09533"},"observation_digest":"sha256:86857b431b2920e5b2c4367b966c8ab7903727a5ed4fd954a05fdac0d0ea7355","observation_id":"1493c519-96aa-45b3-8e58-a64344abda85","resolution":{"observed_at":"2026-05-12T05:41:23.613990Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2605.13225","last_updated":"2026-05-13T09:17:51Z","snapshot_observed_at":"2026-08-02T19:28:51.230887Z","submitted_at":"2026-05-13T09:17:51Z","title":"Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-14T20:17:26.661595Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2605.13225"},"observation_digest":"sha256:426c15a5f77dcd5ae5d2ac1ec975b065b83f0f96501b25d634b8b64a85567994","observation_id":"bd827019-27f3-4948-af22-a7a36a643801","resolution":{"observed_at":"2026-05-14T20:19:27.449276Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":"2310.05492","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-07-02T08:46:48.524247Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":"cc28e604-660c-4b03-853d-dec1e3dac25f","year":2023},"citing_paper":{"arxiv_id":"2607.00604","last_updated":"2026-07-01T08:30:20Z","snapshot_observed_at":"2026-07-07T00:06:14.968413Z","submitted_at":"2026-07-01T08:30:20Z","title":"Vehicle Routing Problem Meets Large Language Models: An Overview and Perspectives","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-02T08:45:04.024510Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2607.00604"},"observation_digest":"sha256:9a7e8171b635537cf09be6f6e7fe4efae4995e7d3b8751a09391256fa3d89bfb","observation_id":"b35529f8-9a29-4ec3-9b61-85ada38193f6","resolution":{"observed_at":"2026-07-02T08:46:48.527680Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-02T09:51:03.574664Z","title":"arXiv:2310.05492 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16252","last_updated":"2026-06-27T03:25:36Z","snapshot_observed_at":"2026-08-03T16:48:30.105983Z","submitted_at":"2026-06-27T03:25:36Z","title":"SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling","version":1},"reference_index":128,"source":"arxiv_source","source_observed_at":"2026-08-02T09:51:03.574664Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2607.16252"},"observation_digest":"sha256:a457fd1920eee4d1ea46cfee2b2709ffac16bdd255f7d43e62f2ff5074a1fd24","observation_id":"e3290840-1b77-4b3f-809d-523422178d8f","resolution":{"observed_at":"2026-08-02T09:51:03.574664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05492","snapshot_observed_at":"2026-08-02T13:56:47.677932Z","title":"How abilities in large language models are affected by supervised fine-tuning data composition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18259","last_updated":"2026-05-15T15:34:48Z","snapshot_observed_at":"2026-08-06T16:40:43.640809Z","submitted_at":"2026-05-15T15:34:48Z","title":"Probabilistic Concept-Aware Steering for Trustworthy LLM Inference","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-02T13:56:47.677932Z"},"links":{"cited_paper":"/paper/2310.05492","citing_paper":"/paper/2607.18259"},"observation_digest":"sha256:c7da454a8ba509e354aab352eeb284c71d2097255cf551575c1a07e5f1d801fb","observation_id":"33529e74-26c6-4c6c-a6e7-1ca3b6d3fb99","resolution":{"observed_at":"2026-08-02T13:56:47.677932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2310.05492/citation-record","integrity":"/paper/2310.05492/integrity","json":"/paper/2310.05492/citation-record.json","paper":"/paper/2310.05492"},"outbound":[],"paper":{"arxiv_id":"2310.05492","last_updated":"2024-06-07T15:51:08Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T16:29:39.982733Z","submitted_at":"2023-10-09T07:56:16Z","title":"How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 25 inbound Pith citation observations for arXiv:2310.05492."}