{"as_of":"2026-08-08T16:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c81699e0222908de2651435aa1263a1da8cf63f3ad0cc6a76cfdfec66b0bd7ee","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:35:30.421456Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T16:33:56.991972Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T16:34:02.652999Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"cited_work":{"arxiv_id":"2505.24461","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.24461","snapshot_observed_at":"2026-08-06T16:34:02.652999Z","title":"Logits-Based Finetuning","venue":"cs.LG","work_id":"9c54c771-5580-4891-8a4c-9cd8f440d20e","year":2025},"citing_paper":{"arxiv_id":"2507.13348","last_updated":"2025-07-17T17:59:55Z","snapshot_observed_at":"2026-08-07T12:51:41.116234Z","submitted_at":"2025-07-17T17:59:55Z","title":"VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T16:33:56.991972Z"},"links":{"cited_paper":"/paper/2505.24461","citing_paper":"/paper/2507.13348"},"observation_digest":"sha256:a66b2936342ac4d5372b6e9e54d0b71dc6e1ac351b84123985a9a5e17363cc36","observation_id":"d20b9ee4-5029-447d-bb24-61ac7af57067","resolution":{"observed_at":"2026-08-06T16:34:02.719238Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.24461/citation-record","integrity":"/paper/2505.24461/integrity","json":"/paper/2505.24461/citation-record.json","paper":"/paper/2505.24461"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2306.13649","last_updated":"2024-01-17T03:23:23Z","snapshot_observed_at":"2026-08-06T11:19:43.438106Z","submitted_at":"2023-06-23T17:56:26Z","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.13649","snapshot_observed_at":"2026-08-07T12:35:25.220360Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.220360Z"},"links":{"cited_paper":"/paper/2306.13649","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:2dbcac1f2b49c4cf4fb2897e8d94a465554ae8b225e01a63b3954b010e7f223e","observation_id":"1e023453-c6c6-47ca-a4c5-989fffdc47ce","resolution":{"observed_at":"2026-08-07T12:35:25.220360Z","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":"2026-08-07T12:35:25.345835Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.345835Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:d3b26600aff88b9e632db796df21502dd245c798369cb91503224fc07e2509be","observation_id":"789625cf-ba38-4c7b-8e59-124cb39fd41f","resolution":{"observed_at":"2026-08-07T12:35:25.345835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10403","last_updated":"2023-09-13T20:35:45Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-17T17:46:53Z","title":"PaLM 2 Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10403","snapshot_observed_at":"2026-08-07T12:35:25.475660Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.475660Z"},"links":{"cited_paper":"/paper/2305.10403","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:269367ce05ce9bd1cf0371afbbd6343849099e3a1ed6c13c8ca29a376d3ee8af","observation_id":"ea99574d-a17c-4963-a801-5e5df5795c80","resolution":{"observed_at":"2026-08-07T12:35:25.475660Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:34.822649Z","title":null,"venue":null,"work_id":"ffe976a0-caf9-43dd-b0eb-3c74a03b3463","year":2020},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.624414Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:5747f99e0ff558bf21f1f5f479c7bc60cf9f6e8fdcc16d717f4903224803a415","observation_id":"6a56c3e7-2680-45ae-81d3-2021701b4e72","resolution":{"observed_at":"2026-08-07T12:35:34.961497Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:25.761266Z","title":"Gonzalez, Ion Stoica, and Eric P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.761266Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:658e37d229472940034281b69ef97465aef2086edb36788d9b24baecff8f5a18","observation_id":"cb7ec06b-8fb3-4ba3-90f3-7650930f92d4","resolution":{"observed_at":"2026-08-07T12:35:25.761266Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02311","last_updated":"2022-10-05T06:02:24Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-05T16:11:45Z","title":"PaLM: Scaling Language Modeling with Pathways","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02311","snapshot_observed_at":"2026-08-07T12:35:25.882013Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.882013Z"},"links":{"cited_paper":"/paper/2204.02311","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:a099e42357254a39ffa4e11d4e54cea1860c762ec06070661f74a718732427c8","observation_id":"5a983ca7-f5a8-4bfd-9af6-a40c524d77fc","resolution":{"observed_at":"2026-08-07T12:35:25.882013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-07T12:35:25.988264Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:25.988264Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:b7b99bacc5fdbc10ef2589f2a50792a2c79030e865096ac3ba527fbfb57df6a5","observation_id":"25b1ce99-05aa-4b5d-b6f6-478b5a3c7ea3","resolution":{"observed_at":"2026-08-07T12:35:25.988264Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08543","last_updated":"2026-01-31T09:16:35Z","snapshot_observed_at":"2026-08-02T20:03:32.798288Z","submitted_at":"2023-06-14T14:44:03Z","title":"MiniLLM: On-Policy Distillation of Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08543","snapshot_observed_at":"2026-08-07T12:35:26.080161Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.080161Z"},"links":{"cited_paper":"/paper/2306.08543","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:0de089c9003533d2db3fdeabf598937a6595474e62348f7cdce0bc0d15722519","observation_id":"bae68dc4-db71-4ac6-a19f-0132d0b44da6","resolution":{"observed_at":"2026-08-07T12:35:26.080161Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:34.612787Z","title":null,"venue":null,"work_id":"5876e1ab-a281-46d5-a52e-27a7d3b09232","year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.170318Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:604b2247d59d231b960ad0d7517f8dbe63dc26cc6b71a0a2b1702c5dce6a201c","observation_id":"79988d1c-05e9-40a7-8778-c6dfb87a3bf5","resolution":{"observed_at":"2026-08-07T12:35:34.691918Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:34.495710Z","title":null,"venue":null,"work_id":"7f23d250-4cbd-4457-983e-356983bdfc01","year":2021},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.287167Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:7109c75cc04f4cd5fbf4539da9a6a967d2095cf0b50de9189628bf511abda0d6","observation_id":"9d43f4d5-0a30-4ca4-a1f3-765cec3b4ab5","resolution":{"observed_at":"2026-08-07T12:35:34.538745Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-07T12:35:26.386664Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.386664Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:750f20260a7bc6d1c97dbbc77e867e3c41b9a5e7769152c5e1cb7987c2dc4c76","observation_id":"8f31d4c0-a544-4879-9529-af4f4325b478","resolution":{"observed_at":"2026-08-07T12:35:26.386664Z","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":"2026-08-07T12:35:26.479150Z","title":"Ku, Qian Liu, and Wenhu Chen","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.479150Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:2171fe09c73de6e97522a10b0131fa7f8c40c9534927eb9e87e71de85c9d48af","observation_id":"8993e1c9-1df4-44ea-871e-4f9b3474b0da","resolution":{"observed_at":"2026-08-07T12:35:26.479150Z","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":"2026-08-07T12:35:26.560650Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.560650Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:c3916273cdf8e3a44c65d79991dee847313e59fc01ddb9d72ed4a9d06bc13af9","observation_id":"4d41563c-74b6-45d1-9121-51349c4c3973","resolution":{"observed_at":"2026-08-07T12:35:26.560650Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:34.263975Z","title":null,"venue":null,"work_id":"a36587e3-ac18-40b9-a2c0-6d19cd596623","year":2020},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.633102Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:b7a830f2f01eab6b79cc233ff053e12c4068f20cae21170d3256b169b87bc890","observation_id":"d2497dfd-2daf-4955-a333-cbbdd7494eb3","resolution":{"observed_at":"2026-08-07T12:35:34.374317Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-07-06T08:52:12.656082Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-07T12:35:26.774337Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.774337Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:2a83068ab0df91596e8620d08712287279e1673e7a5c26fbecf72485c7272b8a","observation_id":"68c7e134-1c42-4e0c-ba0f-28e11732ea79","resolution":{"observed_at":"2026-08-07T12:35:26.774337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.07947","last_updated":"2016-09-22T01:17:12Z","snapshot_observed_at":"2026-07-06T05:01:17.743844Z","submitted_at":"2016-06-25T18:16:39Z","title":"Sequence-Level Knowledge Distillation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.07947","snapshot_observed_at":"2026-08-07T12:35:26.914723Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.914723Z"},"links":{"cited_paper":"/paper/1606.07947","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:2d3c47b4a5fc82f88a91d4e41d7ae4d6817e22407df24eedbab2ca6c36001a51","observation_id":"2e142498-0e00-4117-af1c-78789ce34675","resolution":{"observed_at":"2026-08-07T12:35:26.914723Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:34.071843Z","title":null,"venue":null,"work_id":"005a28da-ad70-4a05-a0c9-8ae0d441ffa4","year":2016},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:26.987109Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:966717836203ed53e1582d57be8cf92769b0f23883fe3461945a1586fc88a5f9","observation_id":"e8fcdce3-95d3-4a7e-a36d-ef6eb34c7a36","resolution":{"observed_at":"2026-08-07T12:35:34.135151Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:33.917917Z","title":"Distillm: Towards streamlined distillation for large language models","venue":null,"work_id":"a5085117-7f03-43d1-91b6-2c9160c6eb92","year":null},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.080195Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:34359327a2381773c95617981e3814d4faa976f7686834c03f4c3b9611c72167","observation_id":"83d53156-598d-4d12-b87b-537ce3be741d","resolution":{"observed_at":"2026-08-07T12:35:33.975405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:27.192435Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.192435Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:a0fc20c9fbf5d10782be0a85ee28c8aaf7f5e8957de936be184b3340bc1a166b","observation_id":"9adc4bf8-2a93-4491-8a7d-940d404d2828","resolution":{"observed_at":"2026-08-07T12:35:27.192435Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:33.709935Z","title":null,"venue":null,"work_id":"236264ae-6cb6-4fad-9552-006e2ddf77a4","year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.322947Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:00d9433e2bf1505b481d7205d327540286b8bf99739221cea8e3272abb22a34e","observation_id":"83cb6056-da8d-4c41-b955-9ae3fbe17ea4","resolution":{"observed_at":"2026-08-07T12:35:33.788052Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03757","last_updated":"2024-06-06T05:41:47Z","snapshot_observed_at":"2026-07-06T18:26:15.151211Z","submitted_at":"2024-06-06T05:41:47Z","title":"RoboCoder: Robotic Learning from Basic Skills to General Tasks with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.03757","snapshot_observed_at":"2026-08-07T12:35:27.409535Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.409535Z"},"links":{"cited_paper":"/paper/2406.03757","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:66e015cf73682613e17dcdefddc9690f3dcc717758e117d660df7af078647309","observation_id":"ed2977d3-2600-40ef-ac3e-1a8b852c639a","resolution":{"observed_at":"2026-08-07T12:35:27.409535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.15960","last_updated":"2025-03-30T09:32:03Z","snapshot_observed_at":"2026-08-06T08:26:39.975858Z","submitted_at":"2023-12-26T08:49:57Z","title":"MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.15960","snapshot_observed_at":"2026-08-07T12:35:27.504273Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.504273Z"},"links":{"cited_paper":"/paper/2312.15960","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:540e89d9936dc834027ea3e101c7c87e2f95e3454dc196575b7fd0eb59464920","observation_id":"9a6bbefa-3390-4f52-b281-2a48912fe05f","resolution":{"observed_at":"2026-08-07T12:35:27.504273Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:33.540931Z","title":null,"venue":null,"work_id":"614fdbd8-edbc-4a7e-b6ba-0c370724475a","year":2021},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.657806Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:dbff5909da08b6ce72c7489fe453768c4a996a05004122186c17ea5cf2a241a6","observation_id":"81e670e1-dd6c-4a90-b0b3-cf323c9207d6","resolution":{"observed_at":"2026-08-07T12:35:33.599013Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:33.399074Z","title":null,"venue":null,"work_id":"5e2d2b4c-ecc0-42c1-9013-44f782038a3f","year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.770807Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:abdc5c9379ae877f54d967265deaa6ec1e4af645d4b4f0ca9dd34a4fcd389471","observation_id":"4c88e4e5-dfa2-4ac4-8210-bba9d0297cd7","resolution":{"observed_at":"2026-08-07T12:35:33.456734Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:27.876783Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.876783Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:14afdd3e49a567ec376fba7ef931fef4a5873ba4fae5aead77bcb5f2ef3c06ba","observation_id":"daf5ad79-db0a-412d-bce2-f40d61192f28","resolution":{"observed_at":"2026-08-07T12:35:27.876783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T12:35:27.993748Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:27.993748Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:593f10b9d5e8f08002d619678c5542af67df2ea5501361fe3f270508fea1c386","observation_id":"f6d3c959-a973-4cd3-95d8-a3a79e27787b","resolution":{"observed_at":"2026-08-07T12:35:27.993748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02155","last_updated":"2022-03-04T07:04:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-03-04T07:04:42Z","title":"Training language models to follow instructions with human feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.02155","snapshot_observed_at":"2026-08-07T12:35:28.164592Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.164592Z"},"links":{"cited_paper":"/paper/2203.02155","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:421dee48ad3d1179c5bc7bbd182a9cd5b87c7bb98c03963a120ac3b2f66bd4be","observation_id":"9c82f887-87f9-48c8-8cea-271f8b6a274c","resolution":{"observed_at":"2026-08-07T12:35:28.164592Z","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":"2026-08-07T12:35:28.260182Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.260182Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:39b0d89b504529c1c8f092f4f01b26dcad9eb9edd41f1c3c022ec72312e800fd","observation_id":"2688cd50-54b3-434a-9508-0872dae3e38a","resolution":{"observed_at":"2026-08-07T12:35:28.260182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03277","last_updated":"2023-04-06T17:58:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-06T17:58:09Z","title":"Instruction Tuning with GPT-4","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.03277","snapshot_observed_at":"2026-08-07T12:35:28.406163Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.406163Z"},"links":{"cited_paper":"/paper/2304.03277","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:5fef4420ed09c3d7ff7efa07445491033c8c190abf4abbe65e6dd26606337fe0","observation_id":"eb221fd9-652b-4544-9174-8bc1d869c06d","resolution":{"observed_at":"2026-08-07T12:35:28.406163Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06295","last_updated":"2016-01-07T18:43:03Z","snapshot_observed_at":"2026-07-06T04:37:06.738855Z","submitted_at":"2015-11-19T18:38:47Z","title":"Policy Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06295","snapshot_observed_at":"2026-08-07T12:35:28.496327Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.496327Z"},"links":{"cited_paper":"/paper/1511.06295","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:8641170fb229ffe8598cf2316b1fa9c742c34e036104bbdf98f1df17a26b2bfe","observation_id":"f918e1c1-3bca-4a8b-aea3-41469c281c3a","resolution":{"observed_at":"2026-08-07T12:35:28.496327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-07T12:35:28.601234Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.601234Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:0f8aee72d3c899f1e2603a32c578f8f96938f17f861986dffbff99b338d924fc","observation_id":"e81bb259-7a8b-41e9-9a82-27826561241d","resolution":{"observed_at":"2026-08-07T12:35:28.601234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.12817","last_updated":"2020-04-27T14:00:09Z","snapshot_observed_at":"2026-07-06T09:15:32.509412Z","submitted_at":"2020-04-27T14:00:09Z","title":"LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.12817","snapshot_observed_at":"2026-08-07T12:35:28.706911Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.706911Z"},"links":{"cited_paper":"/paper/2004.12817","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:915402a41ada4067f3440d39b7176fbdf6c91fe916401dc2fd863e877897da13","observation_id":"16d42b5c-80f7-4e11-82ae-b23db5ccf6dd","resolution":{"observed_at":"2026-08-07T12:35:28.706911Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:33.201070Z","title":null,"venue":null,"work_id":"7e91d07f-3ee4-45c3-aa57-eb4e0c958b44","year":2019},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.822433Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:83554b9f88f000fca40470523546f6f0ee5ef6a685ee18e38ef286509705762c","observation_id":"614279ea-2376-41d3-bee4-81bf9f6833d7","resolution":{"observed_at":"2026-08-07T12:35:33.297754Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:33.049444Z","title":null,"venue":null,"work_id":"52fa3697-aa8e-4854-8b87-bf16c24e85d1","year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.907177Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:bea813b9b9408c5fccba154281778ce234139efe3542f3f0cfd4a750f0baac47","observation_id":"4a2bc33f-806a-4adf-b0ef-6b9399a0a70d","resolution":{"observed_at":"2026-08-07T12:35:33.105482Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:32.888530Z","title":"Hashimoto","venue":null,"work_id":"a309debf-29de-4e19-af99-cf9651abe0f4","year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:28.989388Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:b78d9ab36f27ceef79625b4bf08119c2eb95c02534bc54ceb7f4226c4ee3e260","observation_id":"04b57564-323c-4d8e-bd5c-4b8eb6793f74","resolution":{"observed_at":"2026-08-07T12:35:32.958596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.08239","last_updated":"2022-02-10T16:30:11Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-20T15:44:37Z","title":"LaMDA: Language Models for Dialog Applications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.08239","snapshot_observed_at":"2026-08-07T12:35:29.076870Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.076870Z"},"links":{"cited_paper":"/paper/2201.08239","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:6ada84bcd430b491b3d37cae0a90246ce724cbc8664772da50ae45ec51e5314b","observation_id":"649dc917-1a4b-4bb8-a317-5d3554552a8a","resolution":{"observed_at":"2026-08-07T12:35:29.076870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01560","last_updated":"2024-10-05T03:54:22Z","snapshot_observed_at":"2026-07-06T19:26:02.193680Z","submitted_at":"2024-10-02T14:00:09Z","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01560","snapshot_observed_at":"2026-08-07T12:35:29.183602Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.183602Z"},"links":{"cited_paper":"/paper/2410.01560","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:a011e83c3cad4b4385ac946aa2d708214f2b22d4704ca29258ababb7bdfd8dd8","observation_id":"a0f53829-2463-429f-aa1c-39577a4c724a","resolution":{"observed_at":"2026-08-07T12:35:29.183602Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:32.697469Z","title":null,"venue":null,"work_id":"51ac7da4-3364-44eb-8273-1f7cc19c958e","year":2021},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.262575Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:b6fdf76af422806131e9cdba3c2b6c1690b0d2d48af41401fba826b932f84ff2","observation_id":"327c5b70-8696-4a03-b004-72ffc84addc0","resolution":{"observed_at":"2026-08-07T12:35:32.764729Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:32.487570Z","title":null,"venue":null,"work_id":"0799adc1-10a9-4068-947b-57f0e81fe95d","year":2020},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.424027Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:79e34a97777d47636c8da8d6c6a1cba3dbd317c77ca701e42a02cb083856feb9","observation_id":"5f584b8b-9e30-4b22-9aad-583801230c2d","resolution":{"observed_at":"2026-08-07T12:35:32.569335Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:32.304888Z","title":null,"venue":null,"work_id":"f7823056-e012-47d0-b9e8-07ecfab59583","year":2022},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.532571Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:34b081399e6bf962bb27a8ce0af32e6d5bae11103c0e60661ad33e8690472eea","observation_id":"6d654e64-de0d-49bb-b20d-07563107ad2d","resolution":{"observed_at":"2026-08-07T12:35:32.385377Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:32.090887Z","title":null,"venue":null,"work_id":"05643fb7-0dfa-46c1-811d-b3803ad79cff","year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.666866Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:74853f64b85b21e0628680bd6c06e57f06bda7345acdd70287944a2ea05444f3","observation_id":"2fcd710e-df0f-4527-8512-ad54f3797d70","resolution":{"observed_at":"2026-08-07T12:35:32.201008Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:29.774128Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.774128Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:47c5767de473e3c164af0e7321f893aacd93af3f826febccf352d2d4f4a582ee","observation_id":"1adc23b1-0d1f-4bff-927d-ece3f714f163","resolution":{"observed_at":"2026-08-07T12:35:29.774128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.12284","last_updated":"2024-05-03T17:36:07Z","snapshot_observed_at":"2026-08-02T15:00:50.388422Z","submitted_at":"2023-09-21T17:45:42Z","title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12284","snapshot_observed_at":"2026-08-07T12:35:29.881256Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.881256Z"},"links":{"cited_paper":"/paper/2309.12284","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:4384477ea085c96acef03cc0d18529ddceac783994a4bcb6f0145d08cc1c2d79","observation_id":"42829368-f920-4b0f-a599-eb521f1434f0","resolution":{"observed_at":"2026-08-07T12:35:29.881256Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:35:31.853660Z","title":null,"venue":null,"work_id":"c98e49f1-9666-44a6-b908-aec1162fc481","year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:29.985040Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:e0255c61d0fa7613ab1bf08ce2e820eae67988a5d71f7765b807f004711103fd","observation_id":"da15626d-e2c5-433e-b41b-7f406c7a0fa0","resolution":{"observed_at":"2026-08-07T12:35:31.954666Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02408","last_updated":"2023-06-04T17:02:59Z","snapshot_observed_at":"2026-07-06T15:37:47.140788Z","submitted_at":"2023-06-04T17:02:59Z","title":"Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02408","snapshot_observed_at":"2026-08-07T12:35:30.053700Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:30.053700Z"},"links":{"cited_paper":"/paper/2306.02408","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:ff8bec524c3e5eed5be384b62710bf1b7f5e3239c5ada7163e681e1e2ead9016","observation_id":"4e35878c-c03f-40fc-96c3-87e8a71e6db2","resolution":{"observed_at":"2026-08-07T12:35:30.053700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05010","last_updated":"2023-05-08T19:31:09Z","snapshot_observed_at":"2026-07-06T15:24:45.921232Z","submitted_at":"2023-05-08T19:31:09Z","title":"Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05010","snapshot_observed_at":"2026-08-07T12:35:30.148694Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:30.148694Z"},"links":{"cited_paper":"/paper/2305.05010","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:a0bf5c21bb1c6c3fc957afdc27f8ab43cca5dbc038ea5782ef7b9bf0679b5aea","observation_id":"5aa2c277-7ef9-4d58-9a4a-00bfb30fa759","resolution":{"observed_at":"2026-08-07T12:35:30.148694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14722","last_updated":"2024-11-05T08:22:00Z","snapshot_observed_at":"2026-08-08T09:05:51.885556Z","submitted_at":"2024-05-23T15:51:24Z","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14722","snapshot_observed_at":"2026-08-07T12:35:30.268146Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:30.268146Z"},"links":{"cited_paper":"/paper/2405.14722","citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:42eba084cf25d092556e29a298f1d4f73f662f1af8fd927922b8353c53295402","observation_id":"fd363ea0-0aac-48eb-89ff-a997c44815cd","resolution":{"observed_at":"2026-08-07T12:35:30.268146Z","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":"2026-08-07T12:35:30.343234Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:30.343234Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:188f5361cb70d37b2f601cc3b706d3761ba45725c0cab636389055b8cee94b3e","observation_id":"3892600c-5455-40ed-ae86-4482dd67eba0","resolution":{"observed_at":"2026-08-07T12:35:30.343234Z","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":"2026-08-07T12:35:30.421456Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T12:35:30.421456Z"},"links":{"citing_paper":"/paper/2505.24461"},"observation_digest":"sha256:ce594b3eb70bdd692e82209f711f7a3014d1fd78f89246346eb65df51b6ee3b2","observation_id":"c415dd90-80b3-48be-a8fb-60633f93007a","resolution":{"observed_at":"2026-08-07T12:35:30.421456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.24461","last_updated":"2025-06-11T16:40:39Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T12:19:15.748531Z","submitted_at":"2025-05-30T10:57:09Z","title":"Logits-Based Finetuning"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":0,"verified_fuzzy":2},"total_outbound_references":49},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2505.24461."}