{"as_of":"2026-08-08T09:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ff1830e1474c109b55eeffb8025ac3a570ffb5437c54c1922f24d40b048e677c","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:53:59.231906Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.20643/citation-record","integrity":"/paper/2505.20643/integrity","json":"/paper/2505.20643/citation-record.json","paper":"/paper/2505.20643"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T13:53:55.010369Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.010369Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:4102d4aa2fd196d52bb2ad56389ddefdb493bb2eac3a67aa2992f791cda6fc7e","observation_id":"e79aa794-4e35-4392-a350-6b02571a7a8e","resolution":{"observed_at":"2026-08-07T13:53:55.010369Z","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":"2026-08-07T13:54:00.718455Z","title":"Near-duplicate question detection","venue":null,"work_id":"58cdde10-78ca-4c3e-8df5-8e363c382807","year":2024},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.585444Z"},"links":{"citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:258f7bf9675b90d1587addb69339b4142977c2e806b890f8a1f8def7e322f576","observation_id":"65ff566f-2321-4744-9e42-1c66abb55d86","resolution":{"observed_at":"2026-08-07T13:54:00.838170Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08164","last_updated":"2021-09-08T20:44:44Z","snapshot_observed_at":"2026-08-07T07:18:37.623241Z","submitted_at":"2021-04-16T15:24:42Z","title":"Editing Factual Knowledge in Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08164","snapshot_observed_at":"2026-08-07T13:53:55.692399Z","title":"Editing factual knowledge in language models.arXiv preprint arXiv:2104.08164,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.692399Z"},"links":{"cited_paper":"/paper/2104.08164","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:e01d6e1a2e189c6d393b3b4edaeaa8ff6d18a93ea9ac35bc3dcbb6b7c38bfb41","observation_id":"1e361abd-1865-4666-8d4c-6960c0b93880","resolution":{"observed_at":"2026-08-07T13:53:55.692399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02355","last_updated":"2025-04-22T16:15:47Z","snapshot_observed_at":"2026-08-07T08:26:37.732830Z","submitted_at":"2024-10-03T10:06:27Z","title":"AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02355","snapshot_observed_at":"2026-08-07T13:53:55.857065Z","title":"Alphaedit: Null-space constrained knowledge editing for language models.arXiv preprint arXiv:2410.02355,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.857065Z"},"links":{"cited_paper":"/paper/2410.02355","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:2c2921283a9c0d0043d148c79b1481b0cbe515ce89ba4f2a90721da2199097a8","observation_id":"e4bff9ed-02ec-4ea1-8fc9-246b38f280d0","resolution":{"observed_at":"2026-08-07T13:53:55.857065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17179","last_updated":"2024-02-09T00:13:46Z","snapshot_observed_at":"2026-07-06T16:25:25.534843Z","submitted_at":"2023-09-29T12:20:19Z","title":"Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17179","snapshot_observed_at":"2026-08-07T13:53:55.952185Z","title":"Alphazero-like tree-search can guide large language model decoding and training.arXiv preprint arXiv:2309.17179,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.952185Z"},"links":{"cited_paper":"/paper/2309.17179","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:81a1aa149ba8418086365a2e4d2887bdb44c94175f4d25468f774883973e73fb","observation_id":"db427559-1d5c-4206-92ed-026d48eec8af","resolution":{"observed_at":"2026-08-07T13:53:55.952185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.11738","last_updated":"2024-02-21T12:59:21Z","snapshot_observed_at":"2026-07-31T18:12:14.483728Z","submitted_at":"2023-05-19T15:19:44Z","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.11738","snapshot_observed_at":"2026-08-07T13:53:56.052600Z","title":"Critic: Large language models can self-correct with tool-interactive critiquing.arXiv preprint arXiv:2305.11738,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.052600Z"},"links":{"cited_paper":"/paper/2305.11738","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:d99273714eb65f452fb4ecd4f881b8fba444118844a376e67c94ced32e5d4fd9","observation_id":"bbac63fc-c4f5-4ebc-a82e-05ac9a54ebd9","resolution":{"observed_at":"2026-08-07T13:53:56.052600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04519","last_updated":"2025-01-08T14:12:57Z","snapshot_observed_at":"2026-08-04T20:57:22.329262Z","submitted_at":"2025-01-08T14:12:57Z","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04519","snapshot_observed_at":"2026-08-07T13:53:56.145963Z","title":"rstar-math: Small llms can master math reasoning with self-evolved deep thinking.arXiv preprint arXiv:2501.04519,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.145963Z"},"links":{"cited_paper":"/paper/2501.04519","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:455e5440e9d978feaf3692c501b0d262b4f11d23a4135cc3b98a4f8261f25361","observation_id":"1216ef42-4154-4d8a-b68e-e40f0f23babc","resolution":{"observed_at":"2026-08-07T13:53:56.145963Z","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":"2026-08-07T13:53:56.228651Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.arXiv preprint arXiv:2501.12948,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.228651Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:33aba95813fdb79de86f9cf03fb90867568fa940c608e51770e1b2687a27d09d","observation_id":"5f028e76-2d78-47c7-87e5-ed889179c166","resolution":{"observed_at":"2026-08-07T13:53:56.228651Z","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":"2026-08-07T13:53:56.318910Z","title":"Token- budget-aware llm reasoning.arXiv preprint arXiv:2412.18547,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.318910Z"},"links":{"cited_paper":"/paper/2412.18547","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:e6744c741d8911b5b2c9278c8a8d5845bb92688e89d061e7050957f71ecc09ca","observation_id":"483f4a1e-f312-4f72-9254-651d226aa27c","resolution":{"observed_at":"2026-08-07T13:53:56.318910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.06769","last_updated":"2025-11-03T00:53:34Z","snapshot_observed_at":"2026-08-07T06:05:27.895209Z","submitted_at":"2024-12-09T18:55:56Z","title":"Training Large Language Models to Reason in a Continuous Latent Space","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.06769","snapshot_observed_at":"2026-08-07T13:53:56.411702Z","title":"Training large language models to reason in a continuous latent space.arXiv preprint arXiv:2412.06769,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.411702Z"},"links":{"cited_paper":"/paper/2412.06769","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:03fe81a77e3e40772bdcd707455b145440eb8cc445ee09633a2d90320a954b13","observation_id":"a6b89bf5-751a-47d8-9a99-62b9f5abda79","resolution":{"observed_at":"2026-08-07T13:53:56.411702Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03901","last_updated":"2023-06-07T17:22:22Z","snapshot_observed_at":"2026-08-02T15:32:09.218233Z","submitted_at":"2023-06-06T17:58:24Z","title":"ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03901","snapshot_observed_at":"2026-08-07T13:53:56.509501Z","title":"Chatdb: Augmenting llms with databases as their symbolic memory.arXiv preprint arXiv:2306.03901,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.509501Z"},"links":{"cited_paper":"/paper/2306.03901","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:31daedaffc490aa025af9d9adbe4076e6c4cbb180a70939b5cdc3a6db3e90fbe","observation_id":"481d30a5-c841-4a7c-8ea4-0309164542d0","resolution":{"observed_at":"2026-08-07T13:53:56.509501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-07T13:53:56.693894Z","title":"Openai o1 system card.arXiv preprint arXiv:2412.16720,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.693894Z"},"links":{"cited_paper":"/paper/2412.16720","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:1b3ac94b984c4df8974ade4484adf1edc074677ff6b0ebe0d82bf493280baab0","observation_id":"190ce8af-065a-4b54-9395-41eff6c02270","resolution":{"observed_at":"2026-08-07T13:53:56.693894Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.02497","last_updated":"2025-06-29T06:49:52Z","snapshot_observed_at":"2026-07-06T20:16:44.607678Z","submitted_at":"2025-01-05T10:24:20Z","title":"A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.02497","snapshot_observed_at":"2026-08-07T13:53:56.789043Z","title":"Test-time computing: from system-1 thinking to system-2 thinking.arXiv preprint arXiv:2501.02497,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.789043Z"},"links":{"cited_paper":"/paper/2501.02497","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:402832a2ec09528b5732f3c4f0b501ceee016b0821e6035ee107b342e19e81ae","observation_id":"bc71b582-9553-4a5d-9fae-ab5a1af54ad4","resolution":{"observed_at":"2026-08-07T13:53:56.789043Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.01141","last_updated":"2025-04-01T00:41:36Z","snapshot_observed_at":"2026-08-08T04:02:43.828729Z","submitted_at":"2025-03-03T03:48:20Z","title":"How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approach","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.01141","snapshot_observed_at":"2026-08-07T13:53:56.890817Z","title":"How well do llms compress their own chain-of-thought? a token complexity approach.arXiv preprint arXiv:2503.01141,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.890817Z"},"links":{"cited_paper":"/paper/2503.01141","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:30472df9cdda4f77850f2eae4b2262ed59471ea66f45a2c42583cfbcf0e67e9f","observation_id":"403a5b76-5ee4-4c61-a5f3-96edc1b40eb2","resolution":{"observed_at":"2026-08-07T13:53:56.890817Z","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":"2026-08-07T13:54:00.512780Z","title":"How long can context length of open-source llms truly promise? InNeurIPS 2023 Workshop on Instruction Tuning and Instruction Following,","venue":null,"work_id":"fa0392db-e5fc-4806-b3c5-efe652cf0913","year":2023},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.956683Z"},"links":{"citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:eb2bb16d6c3a93e0813c03999e340f1efbcdeb7285af3dd931e4f449009991d2","observation_id":"92678161-cada-44f8-9df8-7165bec7b729","resolution":{"observed_at":"2026-08-07T13:54:00.614905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14550","last_updated":"2024-11-05T16:51:40Z","snapshot_observed_at":"2026-08-07T19:58:05.905519Z","submitted_at":"2024-06-20T17:57:51Z","title":"GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14550","snapshot_observed_at":"2026-08-07T13:53:57.066714Z","title":"Graphreader: Building graph-based agent to enhance long- context abilities of large language models.arXiv preprint arXiv:2406.14550,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.066714Z"},"links":{"cited_paper":"/paper/2406.14550","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:cef283349d0adbc59c9f9a21d84897dc9f7f2c2f05db0cca6878eb6ed61c9804","observation_id":"41f5bf51-2a7d-4928-bb29-659d5e9e4d8c","resolution":{"observed_at":"2026-08-07T13:53:57.066714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.17419","last_updated":"2025-06-25T02:24:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-24T18:50:52Z","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.17419","snapshot_observed_at":"2026-08-07T13:53:57.137704Z","title":"From system 1 to system 2: A survey of reasoning large language models.arXiv preprint arXiv:2502.17419,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.137704Z"},"links":{"cited_paper":"/paper/2502.17419","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:0368e71c78ca2b56241458d213bda2df38b644ce49ba78af0aaad456f94a7713","observation_id":"3c6dc0ce-f9df-42dc-af0f-393301a3ba99","resolution":{"observed_at":"2026-08-07T13:53:57.137704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03172","last_updated":"2023-11-20T23:09:34Z","snapshot_observed_at":"2026-07-06T15:51:12.179086Z","submitted_at":"2023-07-06T17:54:11Z","title":"Lost in the Middle: How Language Models Use Long Contexts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03172","snapshot_observed_at":"2026-08-07T13:53:57.209320Z","title":"Lost in the middle: How language models use long contexts.arXiv preprint arXiv:2307.03172,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.209320Z"},"links":{"cited_paper":"/paper/2307.03172","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:ea74454044cbb666a54a1dc3cb7ce29995fd871b214bd495e571efb88f0b2bfd","observation_id":"01720339-1bdc-4556-b785-4f68c4ac6eb1","resolution":{"observed_at":"2026-08-07T13:53:57.209320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06703","last_updated":"2025-02-10T17:30:23Z","snapshot_observed_at":"2026-08-05T04:32:32.994993Z","submitted_at":"2025-02-10T17:30:23Z","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06703","snapshot_observed_at":"2026-08-07T13:53:57.290694Z","title":"Can 1b llm surpass 405b llm? rethinking compute-optimal test-time scaling.arXiv preprint arXiv:2502.06703,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.290694Z"},"links":{"cited_paper":"/paper/2502.06703","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:d8ca9cb9dbadbe229e6d5db533c86ba9b6b51c028a2ec739c9765fa6b5e1f630","observation_id":"c08a3bb2-51a6-464e-bd4b-23b5a2357fc3","resolution":{"observed_at":"2026-08-07T13:53:57.290694Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08747","last_updated":"2025-01-05T04:09:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-17T02:53:23Z","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08747","snapshot_observed_at":"2026-08-07T13:53:57.428704Z","title":"An empirical study of catastrophic forgetting in large language models during continual fine-tuning.arXiv preprint arXiv:2308.08747,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.428704Z"},"links":{"cited_paper":"/paper/2308.08747","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:1efd881f8dab08a7a5e671bc8dc5a4e320e8a3eca3df4f001f2a7c851c638da0","observation_id":"8c49f7fd-9a84-4aa2-850a-a0dcda3dc45e","resolution":{"observed_at":"2026-08-07T13:53:57.428704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11309","last_updated":"2022-06-13T23:26:16Z","snapshot_observed_at":"2026-08-03T23:42:31.942314Z","submitted_at":"2021-10-21T17:41:56Z","title":"Fast Model Editing at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.11309","snapshot_observed_at":"2026-08-07T13:53:57.519013Z","title":"Fast model editing at scale.arXiv preprint arXiv:2110.11309,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.519013Z"},"links":{"cited_paper":"/paper/2110.11309","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:b03097726e9af85aa739682e15c256e5ee0b6260c807629e5dcc5a436b0091ff","observation_id":"55fbb7ce-d022-45f1-8e90-a4e0ac86edf3","resolution":{"observed_at":"2026-08-07T13:53:57.519013Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19393","last_updated":"2025-03-01T06:07:39Z","snapshot_observed_at":"2026-07-06T20:29:11.710285Z","submitted_at":"2025-01-31T18:48:08Z","title":"s1: Simple test-time scaling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.19393","snapshot_observed_at":"2026-08-07T13:53:57.585308Z","title":"s1: Simple test-time scaling","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.585308Z"},"links":{"cited_paper":"/paper/2501.19393","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:6290951dd4a29469458f8c8ae7dd8c1fd7eb6bd1ff6148a50855e8509d79b224","observation_id":"844595f0-86a4-4edd-856f-3eefa4587210","resolution":{"observed_at":"2026-08-07T13:53:57.585308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20122","last_updated":"2025-06-10T10:54:28Z","snapshot_observed_at":"2026-08-08T01:06:04.764010Z","submitted_at":"2025-02-27T14:14:50Z","title":"Self-Training Elicits Concise Reasoning in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20122","snapshot_observed_at":"2026-08-07T13:53:57.717067Z","title":"Self- training elicits concise reasoning in large language models.arXiv preprint arXiv:2502.20122,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.717067Z"},"links":{"cited_paper":"/paper/2502.20122","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:e53b15d0ef90c4807123c8f9d469e8d07e02360c4ac416224aa3704411707fb0","observation_id":"9606b1ba-afb5-415c-818d-f2e611fb28dd","resolution":{"observed_at":"2026-08-07T13:53:57.717067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.12521","last_updated":"2025-02-18T04:11:29Z","snapshot_observed_at":"2026-08-07T18:10:14.927590Z","submitted_at":"2025-02-18T04:11:29Z","title":"Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12521","snapshot_observed_at":"2026-08-07T13:53:57.803026Z","title":"Inference-time computations for llm reasoning and planning: A benchmark and insights","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.803026Z"},"links":{"cited_paper":"/paper/2502.12521","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:287c9a3d63017f0a36d9e91285ebd31c1d3dfb15dd07b3c2faadd592c7bb3e83","observation_id":"31782a33-d74e-4356-aa41-cca451875cec","resolution":{"observed_at":"2026-08-07T13:53:57.803026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.06682","last_updated":"2024-10-16T23:19:46Z","snapshot_observed_at":"2026-08-07T21:53:38.296252Z","submitted_at":"2024-05-05T18:56:46Z","title":"Self-Reflection in LLM Agents: Effects on Problem-Solving Performance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.06682","snapshot_observed_at":"2026-08-07T13:53:57.901289Z","title":"Self-reflection in llm agents: Effects on problem-solving perfor- mance","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.901289Z"},"links":{"cited_paper":"/paper/2405.06682","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:6ebb6fd41e496a1d9fe2e8d79ac2b3d4494f5d131af234982b62b0be9049ab43","observation_id":"effb7cc5-a379-4d1f-8e80-e2cb6d5dc74d","resolution":{"observed_at":"2026-08-07T13:53:57.901289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10158","last_updated":"2023-12-14T11:49:17Z","snapshot_observed_at":"2026-08-05T23:26:32.216156Z","submitted_at":"2023-10-16T07:58:56Z","title":"Character-LLM: A Trainable Agent for Role-Playing","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10158","snapshot_observed_at":"2026-08-07T13:53:57.972825Z","title":"Character-llm: A trainable agent for role-playing","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.972825Z"},"links":{"cited_paper":"/paper/2310.10158","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:f80f2d115c130df2519f2f54a290c09d266ad084fb4ac6b61b4b0867222b9343","observation_id":"dd31b16e-7ba3-47d7-a301-90e290e04293","resolution":{"observed_at":"2026-08-07T13:53:57.972825Z","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":"2026-08-07T13:53:58.056976Z","title":"Stop overthinking: A survey on efficient reasoning for large language models.arXiv preprint arXiv:2503.16419,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.056976Z"},"links":{"cited_paper":"/paper/2503.16419","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:01d783908fcdd412435a18129d497ef12d2a74520ca8f7feb34d7746945cfce8","observation_id":"144b36bc-e197-4181-a33d-f506da3a6667","resolution":{"observed_at":"2026-08-07T13:53:58.056976Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20290","last_updated":"2024-10-31T18:27:13Z","snapshot_observed_at":"2026-08-03T23:26:49.562857Z","submitted_at":"2024-10-26T23:20:48Z","title":"Fast Best-of-N Decoding via Speculative Rejection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20290","snapshot_observed_at":"2026-08-07T13:53:58.149803Z","title":"Fast best-of-n decoding via speculative rejection.arXiv preprint arXiv:2410.20290,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.149803Z"},"links":{"cited_paper":"/paper/2410.20290","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:b55322d05d3cdc18f2331fc55834ecda4ad99e9613f492b5127be0dc5c198bab","observation_id":"f3eff320-a979-4fb8-88dc-f7affa2d6392","resolution":{"observed_at":"2026-08-07T13:53:58.149803Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.04872","last_updated":"2026-04-29T08:59:56Z","snapshot_observed_at":"2026-07-06T20:48:09.386369Z","submitted_at":"2025-03-06T16:25:53Z","title":"TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.04872","snapshot_observed_at":"2026-08-07T13:53:58.239786Z","title":"Tinyr1-32b-preview: Boosting accuracy with branch-merge distillation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.239786Z"},"links":{"cited_paper":"/paper/2503.04872","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:b5d91c6cf49129c4f5b3b23acb7e25e3ceda71e254c950b9bf4a929c0f7da173","observation_id":"15e10d43-6b50-445b-9d0b-b66d1baecc23","resolution":{"observed_at":"2026-08-07T13:53:58.239786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04317","last_updated":"2024-11-04T13:02:33Z","snapshot_observed_at":"2026-07-06T17:40:54.163034Z","submitted_at":"2024-03-07T08:34:57Z","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04317","snapshot_observed_at":"2026-08-07T13:53:58.345733Z","title":"Online adaptation of language models with a memory of amortized contexts.arXiv preprint arXiv:2403.04317,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.345733Z"},"links":{"cited_paper":"/paper/2403.04317","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:b0bdadb686ed7e090b94cec2690ce4f2508b613b688c206f9f2edea43d6822b8","observation_id":"50c9288d-24a2-40a5-9ee2-689ce230da04","resolution":{"observed_at":"2026-08-07T13:53:58.345733Z","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":"2026-08-07T13:53:58.464435Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.464435Z"},"links":{"cited_paper":"/paper/2501.12599","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:0d69563a59a250ea8d4b24184e55f0e8dd28279a0c16b17586c1eff8a2e72e17","observation_id":"196d8e17-83c5-413d-b60e-a07ac73b67fd","resolution":{"observed_at":"2026-08-07T13:53:58.464435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.13343","last_updated":"2025-03-18T02:16:56Z","snapshot_observed_at":"2026-08-01T15:59:14.413948Z","submitted_at":"2023-04-26T07:25:31Z","title":"SCM: Enhancing Large Language Model with Self-Controlled Memory Framework","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.13343","snapshot_observed_at":"2026-08-07T13:53:58.558935Z","title":"Enhancing large language model with self-controlled memory framework.arXiv preprint arXiv:2304.13343, 2023a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.558935Z"},"links":{"cited_paper":"/paper/2304.13343","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:675a5abc79a71d3b8029fbe3ee7b9d5db081bb525dd1f9068f7560f305a87876","observation_id":"689bb24c-34cb-4fa2-91fe-82f06f25cdcc","resolution":{"observed_at":"2026-08-07T13:53:58.558935Z","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":"2026-08-07T13:53:58.690570Z","title":"Sampling-efficient test-time scaling: Self-estimating the best-of-n sampling in early decoding.arXiv preprint arXiv:2503.01422,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.690570Z"},"links":{"citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:2d8e175969adc77d48e7455bc611501956e325c99e1925d6bb1d52b2141775df","observation_id":"a1caa4ea-230f-408c-9ad8-64f4a7ba1db8","resolution":{"observed_at":"2026-08-07T13:53:58.690570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18600","last_updated":"2025-03-03T17:08:21Z","snapshot_observed_at":"2026-08-07T17:49:06.764625Z","submitted_at":"2025-02-25T19:36:06Z","title":"Chain of Draft: Thinking Faster by Writing Less","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18600","snapshot_observed_at":"2026-08-07T13:53:58.756755Z","title":"Chain of draft: Thinking faster by writing less","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.756755Z"},"links":{"cited_paper":"/paper/2502.18600","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:72327ce439368b8c06d88b1c1bdc0ca3d3dcc9d502a5218e880516559ea7d089","observation_id":"992584c7-4850-4257-aac8-28332c9690cf","resolution":{"observed_at":"2026-08-07T13:53:58.756755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.03387","last_updated":"2025-07-29T16:23:02Z","snapshot_observed_at":"2026-08-08T04:13:22.884923Z","submitted_at":"2025-02-05T17:23:45Z","title":"LIMO: Less is More for Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.03387","snapshot_observed_at":"2026-08-07T13:53:58.863328Z","title":"Limo: Less is more for reasoning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.863328Z"},"links":{"cited_paper":"/paper/2502.03387","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:87455269b6edbc7af4699d27cd3433f0b95833f9820c439d6a701a39093aaeb2","observation_id":"ed294341-ec12-4716-b109-3a4550ce41d3","resolution":{"observed_at":"2026-08-07T13:53:58.863328Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.04691","last_updated":"2024-10-07T02:12:22Z","snapshot_observed_at":"2026-07-06T19:28:48.185066Z","submitted_at":"2024-10-07T02:12:22Z","title":"Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.04691","snapshot_observed_at":"2026-08-07T13:53:58.992261Z","title":"Deeper insights without updates: The power of in-context learning over fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:58.992261Z"},"links":{"cited_paper":"/paper/2410.04691","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:647253bf66461cd2ebf77eb7f4e32f2ac69dae540185ba60208be5a7dada5f0e","observation_id":"bf20a9b4-4ebd-49ae-bc8d-e2f8199f9575","resolution":{"observed_at":"2026-08-07T13:53:58.992261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15266","last_updated":"2024-12-17T04:30:00Z","snapshot_observed_at":"2026-08-07T21:00:32.251986Z","submitted_at":"2024-12-17T04:30:00Z","title":"On the Structural Memory of LLM Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15266","snapshot_observed_at":"2026-08-07T13:53:59.079201Z","title":"Ruihong Zeng, Jinyuan Fang, Siwei Liu, and Zaiqiao Meng","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:59.079201Z"},"links":{"cited_paper":"/paper/2412.15266","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:c16ba78f78126ddbd87723c9fe9be31b67dbd1537936bafa18cea33b81c6a2c6","observation_id":"082e6222-e12c-43cd-bd40-65da9f69ca12","resolution":{"observed_at":"2026-08-07T13:53:59.079201Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17193","last_updated":"2024-02-27T04:18:49Z","snapshot_observed_at":"2026-08-04T05:29:23.231087Z","submitted_at":"2024-02-27T04:18:49Z","title":"When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17193","snapshot_observed_at":"2026-08-07T13:53:59.151322Z","title":"When scaling meets llm finetuning: The effect of data, model and finetuning method.arXiv preprint arXiv:2402.17193, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:59.151322Z"},"links":{"cited_paper":"/paper/2402.17193","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:70699313ed9839f0d7eddd5b643ee36f6a3666178c71d56bc5f35430d60da83a","observation_id":"eb936d18-b3e8-45db-b6e0-b3f147d79c15","resolution":{"observed_at":"2026-08-07T13:53:59.151322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07863","last_updated":"2024-01-19T06:59:26Z","snapshot_observed_at":"2026-07-06T15:42:06.758676Z","submitted_at":"2023-06-13T15:49:41Z","title":"Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07863","snapshot_observed_at":"2026-08-07T13:53:59.231906Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:59.231906Z"},"links":{"cited_paper":"/paper/2306.07863","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:aa70a3a57c7010f51f2c54faa2380af0ce1f8b33031579b5603d767939841a03","observation_id":"fec81309-e0f3-4b9f-9126-c75617c93263","resolution":{"observed_at":"2026-08-07T13:53:59.231906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04363","last_updated":"2025-05-15T10:57:51Z","snapshot_observed_at":"2026-08-04T20:25:50.849634Z","submitted_at":"2024-07-05T09:06:47Z","title":"AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04363","snapshot_observed_at":"2026-08-07T13:53:55.194944Z","title":"Arigraph: Learning knowledge graph world models with episodic memory for llm agents.arXiv preprint arXiv:2407.04363,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":1982,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.194944Z"},"links":{"cited_paper":"/paper/2407.04363","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:889a22fb9e1a986ab4e3197a151f8567e0aecd1c53fe685b48cedeb194ae22c8","observation_id":"9d694ca8-4b0c-4b65-93cf-9384812c92fd","resolution":{"observed_at":"2026-08-07T13:53:55.194944Z","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":"2026-08-08T03:22:47.699927Z","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":"2026-08-07T13:53:57.355274Z","title":"O1-pruner: Length-harmonizing fine-tuning for o1-like reasoning pruning.arXiv preprint arXiv:2501.12570,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":1988,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:57.355274Z"},"links":{"cited_paper":"/paper/2501.12570","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:4f5bebffb4d416b5ac74e9d148326c10d0959bf1b8fc6879b465fd456c35dee9","observation_id":"8239878e-cccd-480f-8f3f-cdb8a8cdf616","resolution":{"observed_at":"2026-08-07T13:53:57.355274Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-07T13:53:55.389279Z","title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models.arXiv preprint arXiv:2503.09567,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.389279Z"},"links":{"cited_paper":"/paper/2503.09567","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:73b609b74beaf02e0dab97084f2d5d4f3bdbb6f1c5299ff3122e4cbea2f088a6","observation_id":"f8fef601-be25-411f-95b7-d37a102b3197","resolution":{"observed_at":"2026-08-07T13:53:55.389279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.16235","last_updated":"2025-02-27T06:39:06Z","snapshot_observed_at":"2026-08-07T17:56:27.359357Z","submitted_at":"2025-02-22T14:13:37Z","title":"Dynamic Parallel Tree Search for Efficient LLM Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.16235","snapshot_observed_at":"2026-08-07T13:53:55.776430Z","title":"Dynamic parallel tree search for efficient llm reasoning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.776430Z"},"links":{"cited_paper":"/paper/2502.16235","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:78ab456171a825ac2fac311ba2227da8fd6c37e2877cccc44dcf991fe068e564","observation_id":"b77cf157-2608-437d-b359-00e3add75c2f","resolution":{"observed_at":"2026-08-07T13:53:55.776430Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16505","last_updated":"2024-01-30T03:17:26Z","snapshot_observed_at":"2026-07-06T16:12:38.269310Z","submitted_at":"2023-08-31T07:36:44Z","title":"Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16505","snapshot_observed_at":"2026-08-07T13:53:56.601207Z","title":"Recommender ai agent: Inte- grating large language models for interactive recommendations.arXiv preprint arXiv:2308.16505, 2023a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:56.601207Z"},"links":{"cited_paper":"/paper/2308.16505","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:0b3d290d18525156931b0455a15d6a1b63eda7396ab375fdfaa7163b7f383cfb","observation_id":"3142b187-2d3b-4d93-813f-ddf27c932d0a","resolution":{"observed_at":"2026-08-07T13:53:56.601207Z","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":"2026-08-07T13:53:55.101105Z","title":"L1: Controlling how long a reasoning model thinks with reinforcement learning.arXiv preprint arXiv:2503.04697,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.101105Z"},"links":{"cited_paper":"/paper/2503.04697","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:aa632a8fb2888c14e0cef377637b1e81feebb05a438a7a3f763a1cd1f8d037f3","observation_id":"6b3574d1-32ad-4544-a2f5-e625828add17","resolution":{"observed_at":"2026-08-07T13:53:55.101105Z","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":"2026-08-07T13:53:55.269334Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.269334Z"},"links":{"citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:112de06bbc039e898f17a7e430579d45d06aa270b890b0d5b8ebbdfc7c328095","observation_id":"fa2aaab7-a351-4a90-9081-218a2866ca63","resolution":{"observed_at":"2026-08-07T13:53:55.269334Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13171","last_updated":"2024-12-17T18:50:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-17T18:50:33Z","title":"Compressed Chain of Thought: Efficient Reasoning Through Dense Representations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13171","snapshot_observed_at":"2026-08-07T13:53:55.493682Z","title":"Compressed chain of thought: Efficient reasoning through dense representations.arXiv preprint arXiv:2412.13171,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T13:53:55.493682Z"},"links":{"cited_paper":"/paper/2412.13171","citing_paper":"/paper/2505.20643"},"observation_digest":"sha256:72f1c65575d6c84b3b44867d1e5ae3faaa054057f65a4e5f825a6c6f82fdac87","observation_id":"307cd9db-5382-4e6d-b28e-a91f47090434","resolution":{"observed_at":"2026-08-07T13:53:55.493682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.20643","last_updated":"2025-05-27T02:44:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T21:57:04.990865Z","submitted_at":"2025-05-27T02:44:00Z","title":"Can Past Experience Accelerate LLM Reasoning?"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":45,"verified_exact":0,"verified_fuzzy":2},"total_outbound_references":47},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2505.20643."}