{"as_of":"2026-08-08T04:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b54e635884ddb0730a0efae8153ee141524c19f5f2ed43ebb4a1adec7d878cfa","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:06:02.936523Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2505.16312/citation-record","integrity":"/paper/2505.16312/integrity","json":"/paper/2505.16312/citation-record.json","paper":"/paper/2505.16312"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.05150","last_updated":"2020-12-02T17:52:35Z","snapshot_observed_at":"2026-07-31T17:17:17.205582Z","submitted_at":"2020-04-10T17:54:09Z","title":"Longformer: The Long-Document Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.05150","snapshot_observed_at":"2026-08-07T15:06:00.169798Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.169798Z"},"links":{"cited_paper":"/paper/2004.05150","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:2b6f537c5a424f2f9b1439aff24f40bb0fc872275de7ce2e6410ddaaefbf923e","observation_id":"4bac04f4-d9c1-4053-9793-980030cea6ba","resolution":{"observed_at":"2026-08-07T15:06:00.169798Z","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":"2026-08-07T15:06:00.231000Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.231000Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:d1c8d67f40cc26fee7b0d77402ce438de37e34a3be41b49ec69af31aa7211dbd","observation_id":"8b1ea5f5-931f-4c33-8e36-00020a2ef9fb","resolution":{"observed_at":"2026-08-07T15:06:00.231000Z","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":"2026-08-07T15:06:00.344797Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.344797Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:641a4f79f4a64d8ccfcb11deaaf560299dd1785f4014eb4ac630a5d68a34c6db","observation_id":"03cdf8a6-895d-4289-9e3b-29b1c21bc425","resolution":{"observed_at":"2026-08-07T15:06:00.344797Z","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":"2026-08-07T15:06:04.336167Z","title":null,"venue":null,"work_id":"d66e3ff3-709e-42dd-8fd9-168caf77a18b","year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.432636Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:e50b8305f0e43d2ba8bfb91560d6accd5b2c4caf364bea83875ef6a45f99d168","observation_id":"afd58930-0df5-4c69-a9df-a45b9e564ef3","resolution":{"observed_at":"2026-08-07T15:06:04.382075Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-07T15:06:00.494598Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.494598Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:d9b52357fe5676315a72845a286304d3ea69894221a0180f7185d84d1429217c","observation_id":"333fd56c-bb05-4c28-993e-e84e8bef6717","resolution":{"observed_at":"2026-08-07T15:06:00.494598Z","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":"2026-08-07T15:06:04.217033Z","title":null,"venue":null,"work_id":"bb3baadb-7aa8-4721-b211-e49bdbbc9e88","year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.556853Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:77f6c2b7a681555a5de2be8f075a09dd341f7b1f210fbc1f0f3313357ada1f8a","observation_id":"28d4f400-0542-45d9-87b6-76f53bd6d694","resolution":{"observed_at":"2026-08-07T15:06:04.278292Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04707","last_updated":"2024-10-07T02:52:30Z","snapshot_observed_at":"2026-07-06T19:28:48.185066Z","submitted_at":"2024-10-07T02:52:30Z","title":"Learning How Hard to Think: Input-Adaptive Allocation of LM Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04707","snapshot_observed_at":"2026-08-07T15:06:00.664496Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.664496Z"},"links":{"cited_paper":"/paper/2410.04707","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:4fedcf7ed0da856e0355a6b5b3bbd4e4dc1e316df1b6a43a15ca954e002bd7f9","observation_id":"15aea0aa-d327-40a5-b8ae-0cf900157896","resolution":{"observed_at":"2026-08-07T15:06:00.664496Z","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":"2026-08-07T15:06:00.737147Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.737147Z"},"links":{"cited_paper":"/paper/2103.03874","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:b895a6af9f7acd8cb71e89bd4610b0276e236611cbdb529501b3d3f0484e4f93","observation_id":"f3b25275-f55d-4610-bd71-fc2f1a01acd3","resolution":{"observed_at":"2026-08-07T15:06:00.737147Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-07T15:06:00.790593Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.790593Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:e60ac24392fca1ca8d386a8e168315cc13da071f76fc0f0d5b0ca02edcca180c","observation_id":"165693ec-2d06-46e1-bf07-24e2b7dc0b05","resolution":{"observed_at":"2026-08-07T15:06:00.790593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.11694","last_updated":"2024-12-31T01:38:12Z","snapshot_observed_at":"2026-07-06T19:52:03.121993Z","submitted_at":"2024-11-18T16:15:17Z","title":"Enhancing LLM Reasoning with Reward-guided Tree Search","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.11694","snapshot_observed_at":"2026-08-07T15:06:00.892822Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.892822Z"},"links":{"cited_paper":"/paper/2411.11694","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:5728db112ea0e7d7cc899083840bb29ec7bc94197f7c77e8f98571c393268f7f","observation_id":"a80ca779-edbd-4c3a-80ff-78034a3c8734","resolution":{"observed_at":"2026-08-07T15:06:00.892822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16265","last_updated":"2024-06-26T14:01:15Z","snapshot_observed_at":"2026-08-01T16:15:24.164308Z","submitted_at":"2024-05-25T15:07:33Z","title":"MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.16265","snapshot_observed_at":"2026-08-07T15:06:00.966760Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:00.966760Z"},"links":{"cited_paper":"/paper/2405.16265","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:14c021a6e9d064d821b980e63987f97711d18b3e6ed5e75508aa8dc73794cd63","observation_id":"fb87154d-ccb3-4aa8-8dda-36f691e3ac8e","resolution":{"observed_at":"2026-08-07T15:06:00.966760Z","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":"2026-08-07T15:06:01.046649Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.046649Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:f3700371178eeac4b133dec63336ac848221bc0cfc7aa1cbde95abb6079be9d4","observation_id":"3fa21872-8e9b-4f01-9e01-259bb8e85781","resolution":{"observed_at":"2026-08-07T15:06:01.046649Z","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":"2026-08-07T15:06:01.098298Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.098298Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:5c93c9490ab8e602de8147fad3cf2a3d74c12138f522a157e4e8864bcd9a4e04","observation_id":"e080776d-63db-4626-9ca2-d9ae7f50e2ac","resolution":{"observed_at":"2026-08-07T15:06:01.098298Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08291","last_updated":"2023-05-15T01:18:23Z","snapshot_observed_at":"2026-07-06T15:27:02.376191Z","submitted_at":"2023-05-15T01:18:23Z","title":"Large Language Model Guided Tree-of-Thought","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.08291","snapshot_observed_at":"2026-08-07T15:06:01.149295Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.149295Z"},"links":{"cited_paper":"/paper/2305.08291","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:97f0271dd3d4631cb0d8a1c42f596209071c21168524974b259f6668ae37663d","observation_id":"8e5022e6-83a3-4d63-be2b-680207c6a4d2","resolution":{"observed_at":"2026-08-07T15:06:01.149295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.06592","last_updated":"2024-12-11T22:59:10Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-05T19:25:40Z","title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06592","snapshot_observed_at":"2026-08-07T15:06:01.199202Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.199202Z"},"links":{"cited_paper":"/paper/2406.06592","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:7cc78a438d9744127b80699e963316a2f5a42714296ed31c8e8083f34186ff63","observation_id":"170e5667-1e97-4f83-ae01-9e166356dde0","resolution":{"observed_at":"2026-08-07T15:06:01.199202Z","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":"2026-08-07T15:06:04.055840Z","title":null,"venue":null,"work_id":"0312b784-a6db-4aa3-8ef3-3718a836bd60","year":2016},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.246237Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:263c7149078556721dcea86b0a470a2e6784cf5c28379133b81fce47809316d5","observation_id":"b976abed-df55-44ce-98a8-8e73efa259a1","resolution":{"observed_at":"2026-08-07T15:06:04.097565Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.00377","last_updated":"2021-05-02T02:10:31Z","snapshot_observed_at":"2026-08-04T09:55:07.881758Z","submitted_at":"2021-05-02T02:10:31Z","title":"MathBERT: A Pre-Trained Model for Mathematical Formula Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.00377","snapshot_observed_at":"2026-08-07T15:06:01.290862Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.290862Z"},"links":{"cited_paper":"/paper/2105.00377","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:e38cc73e5090b139edce1f083e1eb07f180ba2d0b6d653f041b04bb550e18ca1","observation_id":"b149c76d-8f40-4a21-b935-a60d1a12a47d","resolution":{"observed_at":"2026-08-07T15:06:01.290862Z","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":"2026-08-07T15:06:01.330051Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.330051Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:91ecca11c64be14d3514fd993fae426df709bdf09aab3f226425e8d4efa7d6d2","observation_id":"51ef124e-1669-4ed4-a6c5-6596c68b28b8","resolution":{"observed_at":"2026-08-07T15:06:01.330051Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-07T15:06:01.395899Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.395899Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:0a4dc1e6fdf21ccbed374207dc17b74be5d0ec09ed27fe6b7e209003a787a632","observation_id":"1b4b7feb-7bd1-49ac-98af-c6652b3f5eae","resolution":{"observed_at":"2026-08-07T15:06:01.395899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03314","last_updated":"2024-08-06T17:35:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:35:05Z","title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03314","snapshot_observed_at":"2026-08-07T15:06:01.506314Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.506314Z"},"links":{"cited_paper":"/paper/2408.03314","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:9f427588e353fda2b3359a2d3093c03a5e4c159580f195ff882ba1db9f751e1f","observation_id":"ec1658da-06df-4ea4-9cda-22c6194fe792","resolution":{"observed_at":"2026-08-07T15:06:01.506314Z","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":"2026-08-07T15:06:03.916868Z","title":null,"venue":null,"work_id":"d06739ad-0ea4-49bb-89ab-59d6f33de8e3","year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.611699Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:47a5ae74ec6cade3f972f385a793f066014921f7804632e0dc2145ca857011c1","observation_id":"fdf1c9a9-d35c-4ccf-94c9-46dd440cadb5","resolution":{"observed_at":"2026-08-07T15:06:03.961909Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:06:01.724372Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.724372Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:7b1e0394dc51df66cba5f4b92c3d157370a16cbe6c9f052d87c4487a363d608e","observation_id":"d4a1cbce-f089-480a-967e-0e9a36b4ea16","resolution":{"observed_at":"2026-08-07T15:06:01.724372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00451","last_updated":"2024-06-17T22:11:49Z","snapshot_observed_at":"2026-07-06T18:08:09.361079Z","submitted_at":"2024-05-01T11:10:24Z","title":"Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00451","snapshot_observed_at":"2026-08-07T15:06:01.832895Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.832895Z"},"links":{"cited_paper":"/paper/2405.00451","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:772d2f91d1b99cb7ccc110d84d6aa3f3af0ca48f49ae6a8550b9c846a1205d28","observation_id":"3996829b-ccc4-498e-994f-8efd91710467","resolution":{"observed_at":"2026-08-07T15:06:01.832895Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T15:06:01.922439Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:01.922439Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:6381386bc27c3810589fd4f7411dfb1cd9327bb024830e4af96b78571af06ada","observation_id":"05a49a99-8b54-407f-94ce-a9c86e9a26d3","resolution":{"observed_at":"2026-08-07T15:06:01.922439Z","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":"2026-08-07T15:06:02.037227Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.037227Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:9aeec2ce650aae03695da9db044c6348f2f926cee10fa36faf77a58255181ea4","observation_id":"55751ffd-c5cb-48a6-a87c-e63ba47c68b9","resolution":{"observed_at":"2026-08-07T15:06:02.037227Z","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":"2026-08-07T15:06:03.754002Z","title":null,"venue":null,"work_id":"561be838-5810-47ea-b414-5a2286c090a5","year":2007},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.195248Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:2aed047f54d3be04378e23d7ae090d0d825c445d7f1bb9136d45854d1f85b824","observation_id":"52423769-dd6f-49b7-ab8d-a796611ab521","resolution":{"observed_at":"2026-08-07T15:06:03.818010Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:06:03.613761Z","title":null,"venue":null,"work_id":"58f10c50-75d6-4391-a5d8-d678ce9f67f7","year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.372630Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:6c5e629279b87d9dc4b10235f6619d3445f3ac49ee8cf12493c5013f5c49f715","observation_id":"f0f688d7-5396-4423-a1cc-23aab8e7eb62","resolution":{"observed_at":"2026-08-07T15:06:03.683452Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02884","last_updated":"2024-11-21T07:07:59Z","snapshot_observed_at":"2026-08-07T12:03:21.367108Z","submitted_at":"2024-10-03T18:12:29Z","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02884","snapshot_observed_at":"2026-08-07T15:06:02.552762Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.552762Z"},"links":{"cited_paper":"/paper/2410.02884","citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:a7607c77efc6a8b13ea2db0c628a53cad5c27c0417f44a9480108af2f7d12fe7","observation_id":"3dc80ecb-14b2-40a2-a3be-0fd6924aef7c","resolution":{"observed_at":"2026-08-07T15:06:02.552762Z","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":"2026-08-07T15:06:03.458599Z","title":null,"venue":null,"work_id":"6abab77d-0fe7-4428-be33-1ddf676aacb6","year":2023},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.694169Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:30ad32298fd73b8517eb3e17416e3d387842b9cee6bd6ee086924b4803edb6c5","observation_id":"be3ee6e6-ff67-4855-8833-8eb528b9351b","resolution":{"observed_at":"2026-08-07T15:06:03.532587Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:06:02.824737Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.824737Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:4497270bf9b3b45b83d825e6e4bbf71b95961d441680e6d5127c8cd0070b9591","observation_id":"48df969a-e970-42ac-ae90-0225b8bd5200","resolution":{"observed_at":"2026-08-07T15:06:02.824737Z","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":"2026-08-07T15:06:02.936523Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T15:06:02.936523Z"},"links":{"citing_paper":"/paper/2505.16312"},"observation_digest":"sha256:915ea4450c64b50427fe6a10b2ed29abdd9c012c60726fc2eec8303d5f4eaf23","observation_id":"c8211d67-eb79-469b-a077-f15760781aa4","resolution":{"observed_at":"2026-08-07T15:06:02.936523Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.16312","last_updated":"2026-06-22T14:23:30Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T15:01:12.643871Z","submitted_at":"2025-05-22T07:07:43Z","title":"EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":31},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2505.16312."}