{"as_of":"2026-08-10T17:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0b911b9818c5340d0a58c2f6f2519b2943234d83154615abcab5d02c89f6f259","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:16:41.969791Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":11,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:53:43.839273Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-01T23:26:22.299993Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":"2506.14755","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-07-01T23:26:22.299993Z","title":"Yuanlin Chu, Bo Wang, Xiang Liu, Hong Chen, Aiwei Liu, and Xuming Hu","venue":null,"work_id":"242a7a02-d28b-4da9-b88c-5e49bca6f907","year":2025},"citing_paper":{"arxiv_id":"2503.09567","last_updated":"2025-07-18T15:57:54Z","snapshot_observed_at":"2026-08-08T22:33:20.124926Z","submitted_at":"2025-03-12T17:35:03Z","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","version":5},"reference_index":125,"source":"pdf_text","source_observed_at":"2026-05-12T08:40:40.910461Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2503.09567"},"observation_digest":"sha256:f1ed79bb0da7818499999e44a48109a2292c6adbd7d61921123e050000eb8cb3","observation_id":"f8735614-7068-475b-93c4-0fa1d1519b56","resolution":{"observed_at":"2026-05-12T08:40:41.983748Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-08-06T17:53:43.839273Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09662","last_updated":"2025-07-13T14:51:59Z","snapshot_observed_at":"2026-08-07T01:15:50.475193Z","submitted_at":"2025-07-13T14:51:59Z","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T17:53:43.839273Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2507.09662"},"observation_digest":"sha256:4bba923d6b38d3e1232de17c60557181c26f0b5e2b9eba75dc1e93ae9b8fc4d2","observation_id":"bc6ab941-4ace-481f-bf7d-10f787ff3438","resolution":{"observed_at":"2026-08-06T17:53:43.839273Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-08-06T05:14:37.093116Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.02178","last_updated":"2026-06-29T02:19:28Z","snapshot_observed_at":"2026-08-07T20:42:16.632978Z","submitted_at":"2025-08-04T08:22:14Z","title":"Reconsidering Overthinking: Penalizing Internal and External Redundancy in CoT Reasoning","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T05:14:37.093116Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2508.02178"},"observation_digest":"sha256:4f0a41159f38ba5af8f79ee93d0506ebe4783625184d37380817a5967da91371","observation_id":"6f69fd12-2d08-439a-a3b7-f2c67786832a","resolution":{"observed_at":"2026-08-06T05:14:37.093116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-08-06T05:08:11.949845Z","title":"Optimizing length compression in large reasoning models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.02186","last_updated":"2025-08-04T08:31:45Z","snapshot_observed_at":"2026-08-07T08:59:18.880121Z","submitted_at":"2025-08-04T08:31:45Z","title":"Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T05:08:11.949845Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2508.02186"},"observation_digest":"sha256:9147203c8a4eeca491926f2f17c2124f6f788e85f3ea2c7628032eac146f18ac","observation_id":"e4466a45-860c-4843-ac05-09dab89649c4","resolution":{"observed_at":"2026-08-06T05:08:11.949845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":"2506.14755","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-07-01T23:26:22.299993Z","title":"Yuanlin Chu, Bo Wang, Xiang Liu, Hong Chen, Aiwei Liu, and Xuming Hu","venue":null,"work_id":"242a7a02-d28b-4da9-b88c-5e49bca6f907","year":2025},"citing_paper":{"arxiv_id":"2510.19669","last_updated":"2026-05-08T14:25:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-10-22T15:16:06Z","title":"DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-18T04:31:40.360872Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2510.19669"},"observation_digest":"sha256:843d6e6356c16eed08ada59f21182bef9992d238960e6e1ad91deac2d26247f3","observation_id":"30e538f9-3651-454a-afb4-d2086c23c59c","resolution":{"observed_at":"2026-05-18T04:32:23.125817Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-08-03T05:43:53.133475Z","title":"Optimizing length compression in large reasoning models.arXiv preprint arXiv:2506.14755, 2025b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.01472","last_updated":"2026-06-24T08:53:47Z","snapshot_observed_at":"2026-08-03T05:43:51.520535Z","submitted_at":"2026-02-01T22:31:19Z","title":"ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-03T05:43:53.133475Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2602.01472"},"observation_digest":"sha256:9853f9019e66899a610b1be4d3670422618c05bcf8c07e4d10d0431c6ef22cea","observation_id":"a6ceeae9-b58d-436c-8a4c-899f5ae407d6","resolution":{"observed_at":"2026-08-03T05:43:53.133475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-08-02T20:44:44.123438Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.22642","last_updated":"2026-06-18T19:10:56Z","snapshot_observed_at":"2026-08-04T14:01:22.477463Z","submitted_at":"2026-02-26T05:47:30Z","title":"Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T20:44:44.123438Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2602.22642"},"observation_digest":"sha256:cdcd0a5242d0b47553795e1586f60f2c2cfc900d3407d52a164f38e29953886c","observation_id":"45d69a29-7726-45c5-8cff-81d125af72f0","resolution":{"observed_at":"2026-08-02T20:44:44.123438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":"2506.14755","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-07-01T23:26:22.299993Z","title":"Yuanlin Chu, Bo Wang, Xiang Liu, Hong Chen, Aiwei Liu, and Xuming Hu","venue":null,"work_id":"242a7a02-d28b-4da9-b88c-5e49bca6f907","year":2025},"citing_paper":{"arxiv_id":"2605.07316","last_updated":"2026-05-08T06:25:08Z","snapshot_observed_at":"2026-07-06T23:19:41.053744Z","submitted_at":"2026-05-08T06:25:08Z","title":"Implicit Compression Regularization: Concise Reasoning via Internal Shorter Distributions in RL Post-Training","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-11T01:12:20.864362Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2605.07316"},"observation_digest":"sha256:309976b8ff0f4add985e051c37bcb050b116236fcce0fcc90bb791ba0dea8cd9","observation_id":"0809db36-c9f9-448e-83e8-83e98ef3a1c4","resolution":{"observed_at":"2026-05-11T04:35:59.740619Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":"2506.14755","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-07-01T23:26:22.299993Z","title":"Yuanlin Chu, Bo Wang, Xiang Liu, Hong Chen, Aiwei Liu, and Xuming Hu","venue":null,"work_id":"242a7a02-d28b-4da9-b88c-5e49bca6f907","year":2025},"citing_paper":{"arxiv_id":"2605.30832","last_updated":"2026-05-29T04:37:49Z","snapshot_observed_at":"2026-07-06T23:40:03.151978Z","submitted_at":"2026-05-29T04:37:49Z","title":"SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T22:27:30.783923Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2605.30832"},"observation_digest":"sha256:1654c771e48a83b8cf724d412280d199c2860d68d798c281651387d2e5c81315","observation_id":"916a2bcc-8e1c-4cc7-a6a6-229d9c34f5d9","resolution":{"observed_at":"2026-06-28T22:32:44.405373Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":"2506.14755","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-07-01T23:26:22.299993Z","title":"Yuanlin Chu, Bo Wang, Xiang Liu, Hong Chen, Aiwei Liu, and Xuming Hu","venue":null,"work_id":"242a7a02-d28b-4da9-b88c-5e49bca6f907","year":2025},"citing_paper":{"arxiv_id":"2606.02871","last_updated":"2026-06-01T20:36:06Z","snapshot_observed_at":"2026-07-06T23:43:12.737017Z","submitted_at":"2026-06-01T20:36:06Z","title":"Adaptive Latent Agentic Reasoning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-06-28T14:24:22.855486Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2606.02871"},"observation_digest":"sha256:10d2e91d50d6ad60e3ea60f3f4c22525d775c03ab249a0afa61f3eaccbbd2ada","observation_id":"1038563c-6048-40bb-a459-256a1afe1383","resolution":{"observed_at":"2026-07-01T23:26:22.302073Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.14755","snapshot_observed_at":"2026-08-01T11:17:40.210209Z","title":"Optimizing length compression in large reasoning models.arXiv preprint arXiv:2506.14755,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19962","last_updated":"2026-07-22T09:40:22Z","snapshot_observed_at":"2026-08-07T20:22:22.916584Z","submitted_at":"2026-07-22T09:40:22Z","title":"EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T11:17:40.210209Z"},"links":{"cited_paper":"/paper/2506.14755","citing_paper":"/paper/2607.19962"},"observation_digest":"sha256:5d3cd97865c306a7896ebdf7e3f333773255b606e1f53f872ef35cda6411fd28","observation_id":"5b0eb710-8d34-4a72-aadd-14e25293efe4","resolution":{"observed_at":"2026-08-01T11:17:40.210209Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.14755/citation-record","integrity":"/paper/2506.14755/integrity","json":"/paper/2506.14755/citation-record.json","paper":"/paper/2506.14755"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.16720","last_updated":"2026-04-30T02:46:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-21T18:04:31Z","title":"OpenAI o1 System Card","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16720","snapshot_observed_at":"2026-08-07T00:16:34.294760Z","title":"Openai o1 system card","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:34.294760Z"},"links":{"cited_paper":"/paper/2412.16720","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:5d37d4b247ff105352f24f5813e9dac69f7d64ea77b8d7107aba008429e29480","observation_id":"5f088494-e6d3-4e84-b081-e36e596379e3","resolution":{"observed_at":"2026-08-07T00:16:34.294760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T00:16:34.414892Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:34.414892Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:59d6e06c6a9555aaacf3564a6e9b7134033c81f2c0e698061aa34229fdbfc249","observation_id":"b4439320-2078-4bf0-b3fe-86f786b38ebb","resolution":{"observed_at":"2026-08-07T00:16:34.414892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-07T00:16:34.559238Z","title":"Chain-of-thought prompting elicits reasoning in large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:34.559238Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:0a6290f66ac9d8dfa25f5bc6d914fbb98bec09df6054525af19d82ee632a6172","observation_id":"89d51a15-4e5a-4647-9fec-6f37330f7719","resolution":{"observed_at":"2026-08-07T00:16:34.559238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.21380","last_updated":"2026-04-12T10:37:12Z","snapshot_observed_at":"2026-08-02T16:04:50.458535Z","submitted_at":"2025-03-27T11:20:17Z","title":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.21380","snapshot_observed_at":"2026-08-07T00:16:34.774873Z","title":"Challenging the boundaries of reasoning: An olympiad-level math benchmark for large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:34.774873Z"},"links":{"cited_paper":"/paper/2503.21380","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:6320d0b4b40887a879aa737155476c30dfaecd17d237ac99922d428057d56990","observation_id":"33c7ab18-a6ef-40bc-9d60-d1372ff176ce","resolution":{"observed_at":"2026-08-07T00:16:34.774873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.03065","last_updated":"2024-01-05T20:53:51Z","snapshot_observed_at":"2026-07-06T17:12:10.787061Z","submitted_at":"2024-01-05T20:53:51Z","title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.03065","snapshot_observed_at":"2026-08-07T00:16:34.874959Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:34.874959Z"},"links":{"cited_paper":"/paper/2401.03065","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:697b52763c35c18a6079829bde84fc750d06c1048070fd525572f61771d743fc","observation_id":"3e96a6a6-9cb1-4f5f-99e5-ba5ddc646335","resolution":{"observed_at":"2026-08-07T00:16:34.874959Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.09567","last_updated":"2025-07-18T15:57:54Z","snapshot_observed_at":"2026-08-08T22:33:20.124926Z","submitted_at":"2025-03-12T17:35:03Z","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.09567","snapshot_observed_at":"2026-08-07T00:16:34.992049Z","title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:34.992049Z"},"links":{"cited_paper":"/paper/2503.09567","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:a68cc548fcd98a5a9bcd38d749f7e2e97b7d6937debbaa7f19f81bdd060340a4","observation_id":"e9b21e14-5bb1-43b6-a3a1-7c78f6920f82","resolution":{"observed_at":"2026-08-07T00:16:34.992049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.04697","last_updated":"2025-10-03T01:55:58Z","snapshot_observed_at":"2026-08-06T08:53:09.095000Z","submitted_at":"2025-03-06T18:43:29Z","title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.04697","snapshot_observed_at":"2026-08-07T00:16:35.199105Z","title":"L1: Controlling how long a reasoning model thinks with reinforcement learning, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:35.199105Z"},"links":{"cited_paper":"/paper/2503.04697","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:83bb96caf76c06d2434c9d2d46588f8544c3f4b8d090dc1710bd2f1e0d7a4913","observation_id":"f3584a7e-8a9a-4129-9cd8-a13062862e19","resolution":{"observed_at":"2026-08-07T00:16:35.199105Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.21187","last_updated":"2025-02-01T07:57:37Z","snapshot_observed_at":"2026-08-01T16:43:44.704797Z","submitted_at":"2024-12-30T18:55:12Z","title":"Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.21187","snapshot_observed_at":"2026-08-07T00:16:35.304750Z","title":"Do not think that much for 2+ 3=? on the overthinking of o1-like llms","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:35.304750Z"},"links":{"cited_paper":"/paper/2412.21187","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:8be8c5414d61b215023b9d15af914d152cbc65964f00177130f82fcbf7dc92db","observation_id":"712f7048-528a-4983-8c02-fe24f208b870","resolution":{"observed_at":"2026-08-07T00:16:35.304750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16419","last_updated":"2025-08-21T19:14:40Z","snapshot_observed_at":"2026-08-07T04:27:23.738927Z","submitted_at":"2025-03-20T17:59:38Z","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.16419","snapshot_observed_at":"2026-08-07T00:16:35.420864Z","title":"Stop overthinking: A survey on efficient reasoning for large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:35.420864Z"},"links":{"cited_paper":"/paper/2503.16419","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:f3e31a2f44d095834d22240adfd067e4f0ded0065d904bf0b8cbb1a62bd99ffd","observation_id":"0dea06ee-b610-4019-8a8e-b261135bf6c2","resolution":{"observed_at":"2026-08-07T00:16:35.420864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.08235","last_updated":"2025-02-12T09:23:26Z","snapshot_observed_at":"2026-08-10T00:41:29.483613Z","submitted_at":"2025-02-12T09:23:26Z","title":"The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.08235","snapshot_observed_at":"2026-08-07T00:16:35.589321Z","title":"The danger of overthinking: Examining the reasoning-action dilemma in agentic tasks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:35.589321Z"},"links":{"cited_paper":"/paper/2502.08235","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:35647e68dd4bf65ac830b9f71affb7ee7713f473884d40ce4e71a7d63dd73be7","observation_id":"120bf619-4a70-4da5-8dd9-d6c89a99ea69","resolution":{"observed_at":"2026-08-07T00:16:35.589321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21659","last_updated":"2025-05-21T11:59:38Z","snapshot_observed_at":"2026-08-07T15:57:54.877503Z","submitted_at":"2025-04-30T14:01:45Z","title":"Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.21659","snapshot_observed_at":"2026-08-07T00:16:35.851356Z","title":"Adar1: From long-cot to hybrid-cot via bi-level adaptive reasoning optimization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:35.851356Z"},"links":{"cited_paper":"/paper/2504.21659","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:bdf2b8c7cb8c0ef839c84760da0ca6a94a6b85d848a76db3354ce8db4922ea1d","observation_id":"1e88d015-97c9-42d1-abe1-132fa0ae08f6","resolution":{"observed_at":"2026-08-07T00:16:35.851356Z","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":"2026-08-07T00:16:36.038609Z","title":"Dast: Difficulty-adaptive slow-thinking for large reasoning models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:36.038609Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:6c367d6c7ea072e3dbbf3b00613855955013d24302f688135b442752e460cd73","observation_id":"93ea9e9c-6744-4ae5-ba05-57ccc23e01d0","resolution":{"observed_at":"2026-08-07T00:16:36.038609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.01296","last_updated":"2025-04-02T01:59:26Z","snapshot_observed_at":"2026-07-30T08:40:23.849282Z","submitted_at":"2025-04-02T01:59:26Z","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.01296","snapshot_observed_at":"2026-08-07T00:16:36.272468Z","title":"Thinkprune: Pruning long chain-of-thought of llms via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:36.272468Z"},"links":{"cited_paper":"/paper/2504.01296","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:b4ae572058261c8901417e8de8612a8e4e1166769bc90a5e6a773e12b50688d7","observation_id":"75a755da-d28c-4fb1-b311-69119183b68c","resolution":{"observed_at":"2026-08-07T00:16:36.272468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12570","last_updated":"2025-01-29T03:11:03Z","snapshot_observed_at":"2026-08-10T17:00:34.555363Z","submitted_at":"2025-01-22T01:35:11Z","title":"O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12570","snapshot_observed_at":"2026-08-07T00:16:36.460522Z","title":"O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:36.460522Z"},"links":{"cited_paper":"/paper/2501.12570","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:40d42e8fb9cbef96201f1a1c42db156a46a6b11c700b765ed03bacd001ec311c","observation_id":"d4f074ad-f484-40d5-a52f-46a73029bace","resolution":{"observed_at":"2026-08-07T00:16:36.460522Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12599","last_updated":"2025-06-03T02:14:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T02:48:14Z","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12599","snapshot_observed_at":"2026-08-07T00:16:36.629497Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:36.629497Z"},"links":{"cited_paper":"/paper/2501.12599","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:fe766cda0e83a182349557f413298327a75c1b26e8e3c92c8254b6ac031345d2","observation_id":"2961ff79-d1cf-4858-8fef-0ab6c80564bf","resolution":{"observed_at":"2026-08-07T00:16:36.629497Z","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":"2026-08-07T00:16:36.824756Z","title":"Qwen3, April 2025 a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:36.824756Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:5e515e11c902737d968ec0f908780b0f24830420cf22981cdc78bdf78109b9ae","observation_id":"7f89dd32-f6ee-47d2-9bd2-b45f823a1ba2","resolution":{"observed_at":"2026-08-07T00:16:36.824756Z","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":"2026-08-07T00:16:36.954415Z","title":"Qwq-32b: Embracing the power of reinforcement learning, March 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:36.954415Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:067a94ac6e6a5c485a45db46234a63aaa38936685cfbcb9cf138cde5b2f0d505","observation_id":"a4175192-5b96-4246-9807-955760c3ef7e","resolution":{"observed_at":"2026-08-07T00:16:36.954415Z","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":"2026-08-07T00:16:37.050135Z","title":"Yian Zhang, and Chris Alexiuk","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.050135Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:3abcb3c137fd3c03580e097caa29d072369c50277970e87018e11d797435d34d","observation_id":"9a06e2db-7bb2-4d27-af3d-2753ad4fb1a5","resolution":{"observed_at":"2026-08-07T00:16:37.050135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20783","last_updated":"2025-10-06T09:30:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-26T17:59:14Z","title":"Understanding R1-Zero-Like Training: A Critical Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20783","snapshot_observed_at":"2026-08-07T00:16:37.170150Z","title":"Understanding r1-zero-like training: A critical perspective, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.170150Z"},"links":{"cited_paper":"/paper/2503.20783","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:b9abb7452001e460cd79676568676e6cf92b1dc2f9627e5e4c7f8713d6f5adab","observation_id":"d85e9749-6942-477e-9bf0-09814794ec59","resolution":{"observed_at":"2026-08-07T00:16:37.170150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14476","last_updated":"2025-05-20T01:37:34Z","snapshot_observed_at":"2026-08-02T01:40:54.187278Z","submitted_at":"2025-03-18T17:49:06Z","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14476","snapshot_observed_at":"2026-08-07T00:16:37.300234Z","title":"Dapo: An open-source llm reinforcement learning system at scale","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.300234Z"},"links":{"cited_paper":"/paper/2503.14476","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:ff12931a8b52dc5fc2dd35562e4629c99d6042e44e009a9cf33ef05ae362410b","observation_id":"469a9ed3-d746-493e-b24d-b71a743a9376","resolution":{"observed_at":"2026-08-07T00:16:37.300234Z","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":"2026-08-07T00:16:37.586642Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.586642Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:27a28ab9b62d8bef8670d37a71f1c07f639b3b5a3c3a16290a08d9e2ff40935a","observation_id":"1084e068-3583-46d5-afa5-f139d2c780c7","resolution":{"observed_at":"2026-08-07T00:16:37.586642Z","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":"2026-08-07T00:16:46.684754Z","title":null,"venue":null,"work_id":"849d85b8-8b89-4985-a7e6-2b3358be3974","year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.774912Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:c487fb5c749d4487f8f095f0928fcc1d19e14d2e4e87b2954a8a694dbe8b0cca","observation_id":"8e43b95e-bfea-4e51-ba53-23576d3ad9df","resolution":{"observed_at":"2026-08-07T00:16:46.942335Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:16:46.085715Z","title":"Gemini 2.5 pro","venue":null,"work_id":"a4671a69-2c35-4c12-8a65-3c22d3dc4112","year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.894763Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:d87a82b763263cf74d45a88ebab93d40495be33fc58aaa79e5beddeae9bba41f","observation_id":"bf58d799-9ca6-40be-915e-140198c3ef84","resolution":{"observed_at":"2026-08-07T00:16:46.394029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.21318","last_updated":"2025-04-30T05:05:09Z","snapshot_observed_at":"2026-08-08T08:43:53.657438Z","submitted_at":"2025-04-30T05:05:09Z","title":"Phi-4-reasoning Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.21318","snapshot_observed_at":"2026-08-07T00:16:37.970746Z","title":"Phi-4-reasoning technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:37.970746Z"},"links":{"cited_paper":"/paper/2504.21318","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:ab508c21b5b2b87fc87dbdbdb93a8cbd919259cdb8a293995acaf9796a7ebc93","observation_id":"78625bac-9355-4a45-bafa-f054c59bceb5","resolution":{"observed_at":"2026-08-07T00:16:37.970746Z","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":"2026-08-07T00:16:38.087650Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:38.087650Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:c12bce07e83381e27b45706f567b630378c889f3208f319aa1160fc3c2f51c5a","observation_id":"efb6ea44-37c4-45b7-8254-04f4c018447c","resolution":{"observed_at":"2026-08-07T00:16:38.087650Z","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":"2026-08-07T00:16:38.240809Z","title":"Code-r1: Reproducing r1 for code with reliable rewards","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:38.240809Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:739fd689488af421ac478bb4f69204e25f555139ebd08f1e0fb169cb78c77f92","observation_id":"3eb0a07e-f09d-43e0-bcc9-20b8c51841fc","resolution":{"observed_at":"2026-08-07T00:16:38.240809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.03262","last_updated":"2025-11-10T15:11:13Z","snapshot_observed_at":"2026-08-02T05:27:47.490711Z","submitted_at":"2025-01-04T02:08:06Z","title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.03262","snapshot_observed_at":"2026-08-07T00:16:38.344742Z","title":"Reinforce++: An efficient rlhf algorithm with robustness to both prompt and reward models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:38.344742Z"},"links":{"cited_paper":"/paper/2501.03262","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:f585cca539f49c74d993eb2f8c8a2b14d4a9a2fdf038a97442dbb3d830ae2c58","observation_id":"4db18859-aa05-471b-904c-f18d7c90c1e0","resolution":{"observed_at":"2026-08-07T00:16:38.344742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09601","last_updated":"2025-02-13T18:52:36Z","snapshot_observed_at":"2026-08-08T03:37:50.177168Z","submitted_at":"2025-02-13T18:52:36Z","title":"CoT-Valve: Length-Compressible Chain-of-Thought Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09601","snapshot_observed_at":"2026-08-07T00:16:38.481897Z","title":"Cot-valve: Length-compressible chain-of-thought tuning, 2025 a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:38.481897Z"},"links":{"cited_paper":"/paper/2502.09601","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:24cf6fd69d4071d15fb54e0378438625ad578ec55d6380dfb53216536371a262","observation_id":"99b6b155-0ea3-45c2-ace2-ab26c7811333","resolution":{"observed_at":"2026-08-07T00:16:38.481897Z","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":"2026-08-07T00:16:38.644310Z","title":"Training language models to reason efficiently, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:38.644310Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:70af54f4be728023ff01350af697304e08768c746c6f739e89c26d7ed188454f","observation_id":"e02e288c-9bd8-498c-b2ba-06e14266c327","resolution":{"observed_at":"2026-08-07T00:16:38.644310Z","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":"2026-08-07T00:16:38.760328Z","title":"Aytes, Jinheon Baek, and Sung Ju Hwang","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:38.760328Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:bbaa46fd7bcd00658596d6ed6dc7473d8e7c296508acd126d94cd39df5e7440e","observation_id":"d689a26d-22fa-4a44-90c2-c070b3a157bd","resolution":{"observed_at":"2026-08-07T00:16:38.760328Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.18547","last_updated":"2025-06-02T00:44:09Z","snapshot_observed_at":"2026-08-07T19:18:10.858896Z","submitted_at":"2024-12-24T16:55:45Z","title":"Token-Budget-Aware LLM Reasoning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.18547","snapshot_observed_at":"2026-08-07T00:16:39.050549Z","title":"Token-budget-aware llm reasoning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:39.050549Z"},"links":{"cited_paper":"/paper/2412.18547","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:e390289a24284748ff8d0b3b9272430777ec048d4dde1027c85c041b66152cef","observation_id":"e1fcd434-067d-4e68-99dc-ba21fdb8595a","resolution":{"observed_at":"2026-08-07T00:16:39.050549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09858","last_updated":"2025-04-14T04:08:16Z","snapshot_observed_at":"2026-08-08T01:06:59.135762Z","submitted_at":"2025-04-14T04:08:16Z","title":"Reasoning Models Can Be Effective Without Thinking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09858","snapshot_observed_at":"2026-08-07T00:16:39.489542Z","title":"Reasoning models can be effective without thinking, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:39.489542Z"},"links":{"cited_paper":"/paper/2504.09858","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:a635afde5beacc501e08fc086908a3dd230a7f6e0b68dc089bea96f4d3051b7a","observation_id":"4a6c70f4-7e4f-42f7-802d-5ed584658f60","resolution":{"observed_at":"2026-08-07T00:16:39.489542Z","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":"2026-08-07T00:16:39.806016Z","title":"Qwen2.5: A party of foundation models, September 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:39.806016Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:ae2f5f5fef028b95bb029536afb70564f19a61250cace6b56f90e40606ae9af1","observation_id":"c14916c8-48cf-44cf-a3bb-c64dedfcb783","resolution":{"observed_at":"2026-08-07T00:16:39.806016Z","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":"2026-08-07T00:16:45.645134Z","title":"Gemini 2.5 flash","venue":null,"work_id":"d5daa4e2-a4e1-4465-adf0-ed954cea8ec9","year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:40.124618Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:9058992c053c6355019c7878f59fe2823d8d3c32c35be6d4d88b88c0b103a440","observation_id":"ab962d8a-9425-4f46-872e-d90be2068435","resolution":{"observed_at":"2026-08-07T00:16:45.792290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.06023","last_updated":"2024-07-24T18:40:36Z","snapshot_observed_at":"2026-08-10T13:49:27.550922Z","submitted_at":"2024-07-08T15:17:46Z","title":"Distilling System 2 into System 1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.06023","snapshot_observed_at":"2026-08-07T00:16:40.762333Z","title":"Distilling system 2 into system 1, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:40.762333Z"},"links":{"cited_paper":"/paper/2407.06023","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:8ce552db6893166e12c0c63d50f57ae48df8c09c43830191d9d45a3f570eb803","observation_id":"39688aed-efff-45b7-ad48-e0800b7fd641","resolution":{"observed_at":"2026-08-07T00:16:40.762333Z","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":"2026-08-07T00:16:45.289769Z","title":"The 23rd international conference on artificial intelligence in medicine (aime 2025)","venue":null,"work_id":"74ad3267-704f-4d20-ace2-9464f8b114df","year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:40.910314Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:2af52fb79bc5feba8c38e88f8c63936ed8df57fa82ab4457c741a9f8a8f599e3","observation_id":"85106cc2-6c23-4b3d-95a9-82e2e17d417b","resolution":{"observed_at":"2026-08-07T00:16:45.401357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:16:41.034189Z","title":"Let's verify step by step","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:41.034189Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:c085d5479559f349e646812c20fd56f11892aee7defd1a288e50248f74e7a5e7","observation_id":"3ff29671-5909-4025-b45b-11eadd088b61","resolution":{"observed_at":"2026-08-07T00:16:41.034189Z","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":"2026-08-07T00:16:41.187901Z","title":"Training verifiers to solve math word problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:41.187901Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:e3ae4dfe42e632b1e92ca7dca3033d623491acbd4ac2b7f9459895a3b0b46298","observation_id":"97c36842-6304-4b99-b20a-50e3df120191","resolution":{"observed_at":"2026-08-07T00:16:41.187901Z","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":"2026-08-07T00:16:44.925673Z","title":"American mathematics competitions (amc)","venue":null,"work_id":"a384dd8c-9854-4dd0-b3f7-6b24e423b18a","year":2025},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:41.417261Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:d10d651e799b206e81151ec3f4179e4e7a00f3bd38af5428c1a525a88ecd5c24","observation_id":"b0d67b5e-915b-43ae-be87-af0b61220d2c","resolution":{"observed_at":"2026-08-07T00:16:45.052372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:16:41.599885Z","title":"Gpqa: A graduate-level google-proof q&a benchmark","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:41.599885Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:a64f08d591f80a3b6d0994b5cf6067fbeaf77c5e17102218566579a6034873fc","observation_id":"da846939-5b46-4311-aad6-93bc54a38fb9","resolution":{"observed_at":"2026-08-07T00:16:41.599885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07974","last_updated":"2024-06-06T17:41:21Z","snapshot_observed_at":"2026-08-10T03:07:35.408836Z","submitted_at":"2024-03-12T17:58:04Z","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07974","snapshot_observed_at":"2026-08-07T00:16:41.810990Z","title":"Livecodebench: Holistic and contamination free evaluation of large language models for code","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:41.810990Z"},"links":{"cited_paper":"/paper/2403.07974","citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:2f936c3fe5a98c0eb982c38a5ff9c4c2290b73daee96b64c961b9fe086167a36","observation_id":"1486e9fe-5aa5-4901-ae83-19def43b822d","resolution":{"observed_at":"2026-08-07T00:16:41.810990Z","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":"2026-08-07T00:16:41.969791Z","title":"Trl: Transformer reinforcement learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T00:16:41.969791Z"},"links":{"citing_paper":"/paper/2506.14755"},"observation_digest":"sha256:93419e52982cc32d423fb671aaf53572301b0f72b2dcd147528af4af38ed0dc9","observation_id":"07bddb4d-edf0-4b57-a3f4-3caad4c9c18c","resolution":{"observed_at":"2026-08-07T00:16:41.969791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.14755","last_updated":"2025-09-11T02:13:24Z","latest_version":2,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T00:07:24.304900Z","submitted_at":"2025-06-17T17:50:16Z","title":"Optimizing Length Compression in Large Reasoning Models"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":38,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":42},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 11 inbound Pith citation observations for arXiv:2506.14755."}