{"as_of":"2026-08-10T08:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6a7aba3be79a25c5984ee574a64ca96ed147901a58e2017ccb555b9f4b3b97fc","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T08:38:38.112327Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.04733/citation-record","integrity":"/paper/2607.04733/integrity","json":"/paper/2607.04733/citation-record.json","paper":"/paper/2607.04733"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:34.984658Z","title":"On-policy distillation of language models: Learning from self-generated mistakes","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:34.984658Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:a109bb535d9889ac3f60801d164e2efbd63ad98a7ec9179367ebdf18e5fe2acc","observation_id":"dad7608d-1bd7-405a-b3cc-707d053b5b18","resolution":{"observed_at":"2026-08-02T08:38:34.984658Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-02T08:38:35.046480Z","title":"Evaluating large language models trained on code.arXiv preprint arXiv:2107.03374, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.046480Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:9520d8efabd94ecd4c994f5eba02b529b23bef4578b4f687033c076e0d103027","observation_id":"60bd8eb5-6209-4bbd-bcb3-2e5e9f3a1880","resolution":{"observed_at":"2026-08-02T08:38:35.046480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01377","last_updated":"2024-07-16T03:24:39Z","snapshot_observed_at":"2026-08-02T07:46:40.319683Z","submitted_at":"2023-10-02T17:40:01Z","title":"UltraFeedback: Boosting Language Models with Scaled AI Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01377","snapshot_observed_at":"2026-08-02T08:38:35.145791Z","title":"Ultrafeedback: Boosting language models with scaled ai feedback.arXiv preprint arXiv:2310.01377, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.145791Z"},"links":{"cited_paper":"/paper/2310.01377","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:7d5c1facc75286eeb8e014567d5b8815f3b40c27cbfc31752eeef2057b621296","observation_id":"4b7b6292-20d8-4cf5-b2ab-0b6ca3b5b8da","resolution":{"observed_at":"2026-08-02T08:38:35.145791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:35.327688Z","title":"Entropy-adaptive fine-tuning: Resolving confident conflicts to mitigate forgetting","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.327688Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:49efd6d445c9a8833f5b863aea0e40b5adbefd8d42e74fc83cc3e52845f66424","observation_id":"c73cf419-e4d7-43e9-bbdb-04b5eccb9fe9","resolution":{"observed_at":"2026-08-02T08:38:35.327688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-02T08:38:35.444962Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.444962Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:c91e84480ac720b85b5473a1b3935763fde1e4e9c66c76fbb345ff1f3f37b0bc","observation_id":"26d01718-f7bd-4187-a9a0-a231356c441f","resolution":{"observed_at":"2026-08-02T08:38:35.444962Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:35.605399Z","title":"Minillm: Knowledge distillation of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.605399Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:1c4185820428bb2349b8cb020ff806624fc4a06bc7b8750b7710cc578225ee13","observation_id":"fa09bce4-11bf-47d0-ac11-fcc7820900cc","resolution":{"observed_at":"2026-08-02T08:38:35.605399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.03300","last_updated":"2021-01-12T18:57:11Z","snapshot_observed_at":"2026-08-09T10:28:06.906299Z","submitted_at":"2020-09-07T17:59:25Z","title":"Measuring Massive Multitask Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.03300","snapshot_observed_at":"2026-08-02T08:38:35.723763Z","title":"Measuring massive multitask language understanding.arXiv preprint arXiv:2009.03300, 2020","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.723763Z"},"links":{"cited_paper":"/paper/2009.03300","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:4206a7fb407b509187d3854deaeb3cd3e47525d3a865d90e7687fbf066b104f7","observation_id":"5c11e650-c073-43f7-ad02-07fba81649aa","resolution":{"observed_at":"2026-08-02T08:38:35.723763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03874","last_updated":"2021-11-08T21:30:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-03-05T18:59:39Z","title":"Measuring Mathematical Problem Solving With the MATH Dataset","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03874","snapshot_observed_at":"2026-08-02T08:38:35.892003Z","title":"Measuring mathematical problem solving with the math dataset.arXiv preprint arXiv:2103.03874, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:35.892003Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:c1b08d1c4e916c712df0627ea9675c1cfb3ed85d7b4ab38e829e7d26c449fac0","observation_id":"e033b742-2224-4ccc-a669-2edd5a4e382d","resolution":{"observed_at":"2026-08-02T08:38:35.892003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:36.094767Z","title":"Diversity and evenness: a unifying notation and its consequences.Ecology, 54(2):427–432, 1973","venue":null,"work_id":null,"year":1973},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:36.094767Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:b4f342db49660a445819502cd8a8669b21c40852b26eb65d6ef51f9244b1741c","observation_id":"3c68a778-89c0-443d-8d61-c29bac1a8b0c","resolution":{"observed_at":"2026-08-02T08:38:36.094767Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-02T08:38:36.225463Z","title":"Distilling the knowledge in a neural network.arXiv preprint arXiv:1503.02531, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:36.225463Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:892c6488970288d0692002fca99eddc91b20228b02872a3622215b978ad497fe","observation_id":"4090c7d1-aaea-4e1b-bb4f-17d8fb7019f4","resolution":{"observed_at":"2026-08-02T08:38:36.225463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:36.363081Z","title":"Entropy and diversity.Oikos, 113(2):363–375, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:36.363081Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:4d46dafe2cf2efd43748eaf007261acfa39a5e77e2d579b811b65d53301c81f0","observation_id":"f6597e67-a7cd-47c9-9960-f3f720b841db","resolution":{"observed_at":"2026-08-02T08:38:36.363081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:36.572295Z","title":"Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions.Hugging Face repository, 13(9):9, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:36.572295Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:cd0446a7ce56f1d69150dea16c2232d978428237d0d5edff6b4f193bdad50766","observation_id":"2fc5fab5-817d-4f6e-9067-ab6801677e15","resolution":{"observed_at":"2026-08-02T08:38:36.572295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:36.728501Z","title":"Preserving diversity in supervised fine-tuning of large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:36.728501Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:8ba6792615c4ebc797f445d78c76fb7dcce04cb8d6165808c2b4feb837a79c6e","observation_id":"eb42ce25-3d59-4ce3-befe-ab9a607ef389","resolution":{"observed_at":"2026-08-02T08:38:36.728501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:36.922842Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:36.922842Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:13363080bfbdae4f03d956f7b8f790c06866a8a000e3b617460aef6b5483445d","observation_id":"d577f018-ef09-4022-a5c5-005acbd56acb","resolution":{"observed_at":"2026-08-02T08:38:36.922842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:37.085780Z","title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning.IEEE Transactions on Audio, Speech and Language Processing, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.085780Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:716327a16e9171e79abb294d741b4de84d872b00aca28ff6588bf2e3c2736016","observation_id":"77a38fad-a5fe-4a0c-8dff-7a06acf988fe","resolution":{"observed_at":"2026-08-02T08:38:37.085780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:37.163872Z","title":"Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.163872Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:7fa690f859d451f8fab1a9d64641bb65d9738b98d3541a2dc2edfd9433999a0a","observation_id":"a67413a1-35fa-4ed7-8cab-ed29276cde23","resolution":{"observed_at":"2026-08-02T08:38:37.163872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:37.314921Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.314921Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:9e166a0e4273cecebae8a61684ba56d256cb3b45e54507282199f1e61fefb6c1","observation_id":"f43f6738-ae72-41dd-a3a3-c2185b7810fe","resolution":{"observed_at":"2026-08-02T08:38:37.314921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:37.452964Z","title":"Self-instruct: Aligning language models with self-generated instructions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.452964Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:a7951dbf5e17cb0ce622574db0aed8d48b18173ffd2aecdd712dd55675ebaa0d","observation_id":"081ceec4-cb1c-44db-ad2d-5e71351963f9","resolution":{"observed_at":"2026-08-02T08:38:37.452964Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.20255","last_updated":"2026-05-28T06:29:39Z","snapshot_observed_at":"2026-08-03T07:22:22.213004Z","submitted_at":"2026-01-28T05:03:24Z","title":"HE-SNR: Uncovering Latent Logic via Entropy for Guiding Mid-Training on SWE-bench","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.20255","snapshot_observed_at":"2026-08-02T08:38:37.532639Z","title":"He-snr: Uncovering latent logic via entropy for guiding mid-training on swe-bench.arXiv preprint arXiv:2601.20255, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.532639Z"},"links":{"cited_paper":"/paper/2601.20255","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:864dd0f2172aa39601693dc79d7517d3a83896142991b1d19e51f7ff732dff60","observation_id":"9d59ce80-0e5b-4a26-9b82-fafcca550ba8","resolution":{"observed_at":"2026-08-02T08:38:37.532639Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.02120","last_updated":"2024-06-07T02:50:56Z","snapshot_observed_at":"2026-07-06T16:56:46.051958Z","submitted_at":"2023-12-04T18:50:35Z","title":"Magicoder: Empowering Code Generation with OSS-Instruct","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.02120","snapshot_observed_at":"2026-08-02T08:38:37.623072Z","title":"Magicoder: Empowering code generation with oss-instruct.arXiv preprint arXiv:2312.02120, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.623072Z"},"links":{"cited_paper":"/paper/2312.02120","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:03952cf122edb31d495636f403e9f4086e2e8458b726b0ae481ddaba34199e7e","observation_id":"5a604c43-fab8-4055-bc57-229852a92f21","resolution":{"observed_at":"2026-08-02T08:38:37.623072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.04319","last_updated":"2019-09-26T23:57:44Z","snapshot_observed_at":"2026-08-05T17:26:35.920382Z","submitted_at":"2019-08-12T18:09:04Z","title":"Neural Text Generation with Unlikelihood Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.04319","snapshot_observed_at":"2026-08-02T08:38:37.781693Z","title":"Neural text generation with unlikelihood training.arXiv preprint arXiv:1908.04319, 2019","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.781693Z"},"links":{"cited_paper":"/paper/1908.04319","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:572e597d3d66ac02e858b2d8d94253554c65e8dcfd3bb49e715fe110090d3e52","observation_id":"b8f00bbc-86a1-4398-906c-23b5739303d6","resolution":{"observed_at":"2026-08-02T08:38:37.781693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:37.881481Z","title":"On the generalization of sft: A reinforcement learning perspective with reward rectification.arXiv preprint arXiv:2508.05629, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.881481Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:53f4a311d8ea1e93e2612f28fc39561341cf0a63d4c31b408e6b2f7ffe259d1b","observation_id":"71f84657-bd2f-4f81-a023-059ce3b6b30d","resolution":{"observed_at":"2026-08-02T08:38:37.881481Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09388","last_updated":"2025-05-14T13:41:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-14T13:41:34Z","title":"Qwen3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09388","snapshot_observed_at":"2026-08-02T08:38:37.944918Z","title":"Qwen3 technical report.arXiv preprint arXiv:2505.09388, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:37.944918Z"},"links":{"cited_paper":"/paper/2505.09388","citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:eaa6dda99de42dc2414214376d1f3590fb55f92cd2e5ab9c809455917595e359","observation_id":"66dc21ed-9028-458f-91fa-012871efa06a","resolution":{"observed_at":"2026-08-02T08:38:37.944918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T08:38:38.112327Z","title":"Risk perceptions and safety compliance of workers employed in agriculture, forestry, and fishing","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T08:38:38.112327Z"},"links":{"citing_paper":"/paper/2607.04733"},"observation_digest":"sha256:73a6f6ca2ee092ece36c3638c80b4ade20a87bc2df8dbcf415afac09fd7536c1","observation_id":"58a8abad-04f2-48b1-84a7-a8805f96f5ad","resolution":{"observed_at":"2026-08-02T08:38:38.112327Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.04733","last_updated":"2026-07-21T04:39:38Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T13:17:41.894926Z","submitted_at":"2026-07-06T07:14:22Z","title":"LP-SFT: Local-Preserving Supervised Fine-Tuning via Multimodal Entropy Structure"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.04733."}