{"as_of":"2026-08-13T04:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ff4e0ece1ef6df350e10c6f9fb3d4fc249cf02e65be3d25f3485e546868b0ae","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:26:46.703436Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T01:17:11.892636Z","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":"2026-05-18T21:16:50.920862Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"cited_work":{"arxiv_id":"2501.01668","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.01668","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"30061ad0-876e-429e-a073-c65bb2cdb210","year":2025},"citing_paper":{"arxiv_id":"2509.00084","last_updated":"2026-04-27T15:34:36Z","snapshot_observed_at":"2026-08-11T14:24:53.285716Z","submitted_at":"2025-08-27T06:51:48Z","title":"Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-05-18T21:16:15.703057Z"},"links":{"cited_paper":"/paper/2501.01668","citing_paper":"/paper/2509.00084"},"observation_digest":"sha256:66856caabd7b82ab60504563a675d1cc1a188344f502efc7c3097e94279fdd51","observation_id":"3a311ddc-4393-407b-a334-0c7fa940f2fc","resolution":{"observed_at":"2026-05-18T21:16:50.924055Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01668","snapshot_observed_at":"2026-08-03T01:17:11.892636Z","title":"Cot- based synthesizer: Enhancing llm performance through answer synthesis.arXiv preprint arXiv:2501.01668, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10388","last_updated":"2026-05-29T05:05:29Z","snapshot_observed_at":"2026-08-07T17:40:15.715656Z","submitted_at":"2026-02-11T00:23:13Z","title":"Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T01:17:11.892636Z"},"links":{"cited_paper":"/paper/2501.01668","citing_paper":"/paper/2602.10388"},"observation_digest":"sha256:b01b94c7027d27c0b8ebd56c7c91194399560997c6c2721df975c4e87b8876fd","observation_id":"993da62f-4753-4d28-a49e-9fd0aa2b35af","resolution":{"observed_at":"2026-08-03T01:17:11.892636Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.01668/citation-record","integrity":"/paper/2501.01668/integrity","json":"/paper/2501.01668/citation-record.json","paper":"/paper/2501.01668"},"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":"2026-08-10T22:26:46.480657Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.480657Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:7a24e8edab41e984c973c9ce0c3a443a8d64c359589c027ca3e7da462af4fb33","observation_id":"f3218a38-adcc-451c-a18b-64e95358880e","resolution":{"observed_at":"2026-08-10T22:26:46.480657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21787","last_updated":"2024-12-30T19:03:24Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:57:25Z","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21787","snapshot_observed_at":"2026-08-10T22:26:46.486354Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.486354Z"},"links":{"cited_paper":"/paper/2407.21787","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:622ac1f7d83999599eae18c8e48ebc6bacee2010c26dc3fa26b241058d83b8c5","observation_id":"bde105ec-3fab-4336-9bdb-a7b12467c505","resolution":{"observed_at":"2026-08-10T22:26:46.486354Z","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":"2026-08-10T22:26:46.491515Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.491515Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:85c8997fa08a0aacf49f3897badc5bcc2294c85a6da3a150ed1e8d726761ebd5","observation_id":"efbdc526-5c0b-4a3d-aa88-b998e6110d5b","resolution":{"observed_at":"2026-08-10T22:26:46.491515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.17311","last_updated":"2023-11-29T02:07:09Z","snapshot_observed_at":"2026-08-10T18:24:15.510227Z","submitted_at":"2023-11-29T02:07:09Z","title":"Universal Self-Consistency for Large Language Model Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17311","snapshot_observed_at":"2026-08-10T22:26:46.496057Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.496057Z"},"links":{"cited_paper":"/paper/2311.17311","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:739140ed84db8a28474e24be3d7504d92acf920c4cdd18415972d27971c8583e","observation_id":"5cdaf684-235b-418b-b6d8-5f7d2423d4cc","resolution":{"observed_at":"2026-08-10T22:26:46.496057Z","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":"2026-08-10T22:26:46.501302Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.501302Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:1e5cac7ac2a1477c6c74d28dd84409f725902566e4700bb0d3a3c636ced907a8","observation_id":"85c9cd31-e6d5-498d-9041-51fce68d9253","resolution":{"observed_at":"2026-08-10T22:26:46.501302Z","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":"2026-08-10T22:26:46.506349Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.506349Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:8bd377af7fa053609cbf01635406f032b5244e480b0c90135ff7564f25543c92","observation_id":"2dcdb1d3-7c8a-474d-83a7-669635780948","resolution":{"observed_at":"2026-08-10T22:26:46.506349Z","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":"2026-08-10T22:26:46.511508Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.511508Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:c19657141638cd3fdf220752f7a8d7a8e028b0053c95a7d5c4dab28a3fdb5bb0","observation_id":"153a5016-2864-40aa-95ed-41f48e7c55cc","resolution":{"observed_at":"2026-08-10T22:26:46.511508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-10T22:26:46.520445Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.520445Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:7efb3f9b99e2236857578b89b24f1c422dd2a2139ca7dec221f737ada2018c9d","observation_id":"1f7c43ad-7165-41e7-8733-483b1b46764e","resolution":{"observed_at":"2026-08-10T22:26:46.520445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11430","last_updated":"2023-10-17T17:40:21Z","snapshot_observed_at":"2026-07-06T16:34:38.718198Z","submitted_at":"2023-10-17T17:40:21Z","title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.11430","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.11430","snapshot_observed_at":"2026-08-10T22:26:47.133801Z","title":"An Empirical Study of Translation Hypothesis Ensembling with Large Language Models","venue":"cs.CL","work_id":"0bd4a3c0-31a4-4320-aaa3-3ef847729f5e","year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.528371Z"},"links":{"cited_paper":"/paper/2310.11430","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:cb99cb9a1d76a60b4f41b138a2b6974ddcc3f0b88188ce9dcecb12fdfb9b963f","observation_id":"daaad4de-a8d5-47df-8406-54da910de749","resolution":{"observed_at":"2026-08-10T22:26:47.139573Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12793","last_updated":"2024-07-30T03:58:11Z","snapshot_observed_at":"2026-08-07T13:56:34.167869Z","submitted_at":"2024-06-18T16:58:21Z","title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12793","snapshot_observed_at":"2026-08-10T22:26:46.533320Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.533320Z"},"links":{"cited_paper":"/paper/2406.12793","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:c87f04e38112ebef81c8c6e292c315686ddcc2f2119f3a766a15e44c865dadf5","observation_id":"447c96ac-6108-4432-bf4a-9dfa2455fca5","resolution":{"observed_at":"2026-08-10T22:26:46.533320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14008","last_updated":"2024-06-06T13:19:44Z","snapshot_observed_at":"2026-08-03T03:39:09.398343Z","submitted_at":"2024-02-21T18:49:26Z","title":"OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14008","snapshot_observed_at":"2026-08-10T22:26:46.538607Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.538607Z"},"links":{"cited_paper":"/paper/2402.14008","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:f45f91684317021a4f49fe322fa41485f082a3c82c0ee89b91642836b333e6f3","observation_id":"d593ea25-a011-42b8-9e4a-6a23c2f3b5d5","resolution":{"observed_at":"2026-08-10T22:26:46.538607Z","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":"2026-08-10T22:26:46.543487Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.543487Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:273f6fda64f0b673258ef423fec402ad23d8412b977ee27a26747ff314850051","observation_id":"2676796d-eaf7-4792-b407-3b8b6c84a08c","resolution":{"observed_at":"2026-08-10T22:26:46.543487Z","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":"2026-08-10T22:26:46.548091Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.548091Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:1cff2410644e311c3b2711afd7f36ac0228bed04bc84d572284739472e4bcf8b","observation_id":"ebf1ec5a-f62c-48b5-8028-0cef985de5fc","resolution":{"observed_at":"2026-08-10T22:26:46.548091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02561","last_updated":"2023-06-30T21:39:54Z","snapshot_observed_at":"2026-08-10T19:14:51.255301Z","submitted_at":"2023-06-05T03:32:26Z","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02561","snapshot_observed_at":"2026-08-10T22:26:46.552835Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.552835Z"},"links":{"cited_paper":"/paper/2306.02561","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:3bbdc969980bef00a276850b4cf36967aaad076e435ab3151b3c008aabcdaa74","observation_id":"40386902-e541-426e-9a78-c22e8d3252b8","resolution":{"observed_at":"2026-08-10T22:26:46.552835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.18702","last_updated":"2024-06-26T07:44:11Z","snapshot_observed_at":"2026-07-06T16:55:05.210009Z","submitted_at":"2023-11-30T16:52:42Z","title":"CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.18702","snapshot_observed_at":"2026-08-10T22:26:46.557670Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.557670Z"},"links":{"cited_paper":"/paper/2311.18702","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:d5723c447e086c03f2d44a32657d05aec4c95f4205fe04f3bbe7c8bf783a2602","observation_id":"55ca9be0-ee1b-491c-ab33-3e8c8803fd75","resolution":{"observed_at":"2026-08-10T22:26:46.557670Z","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":"2026-08-10T22:26:46.562733Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.562733Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:70b02528bb61f94255da8c9818041acdb5c9732851e05fd8fea0ad39fb47b901","observation_id":"a13c29e7-735d-4fe3-a800-5e0e9b61814f","resolution":{"observed_at":"2026-08-10T22:26:46.562733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13787","last_updated":"2024-06-08T16:40:12Z","snapshot_observed_at":"2026-08-13T00:49:16.605081Z","submitted_at":"2024-03-20T17:49:54Z","title":"RewardBench: Evaluating Reward Models for Language Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13787","snapshot_observed_at":"2026-08-10T22:26:46.567236Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.567236Z"},"links":{"cited_paper":"/paper/2403.13787","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:199f6d81baffa9a78ae1c76e47f1baefe434330333531a4ec5267114779663fd","observation_id":"05fc499e-68bf-450f-bead-04f9a17a100d","resolution":{"observed_at":"2026-08-10T22:26:46.567236Z","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":"2026-08-10T22:26:46.571978Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.571978Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:84208a8922fea05e259236be6a223464cdc5ea49214aa046fa1146a7f3f66486","observation_id":"7c161c32-d818-4361-a582-896e0c7978f5","resolution":{"observed_at":"2026-08-10T22:26:46.571978Z","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":"2026-08-10T22:26:46.576682Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.576682Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:012a290be8304860488cd58edc9e3c50ae10b11d87cc645bacf20a3867962a63","observation_id":"19d4d9ca-8eae-4ef2-81e6-c82999ddb5a1","resolution":{"observed_at":"2026-08-10T22:26:46.576682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-10T22:26:46.580856Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.580856Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:383999a219e694aba2f41f88be5e0306902ace3556933244399bcd10fd60174d","observation_id":"398f051f-7066-4517-b7eb-ac178b24bcd6","resolution":{"observed_at":"2026-08-10T22:26:46.580856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09332","last_updated":"2022-06-01T19:08:11Z","snapshot_observed_at":"2026-08-07T17:14:39.278754Z","submitted_at":"2021-12-17T05:43:43Z","title":"WebGPT: Browser-assisted question-answering with human feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09332","snapshot_observed_at":"2026-08-10T22:26:46.585138Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.585138Z"},"links":{"cited_paper":"/paper/2112.09332","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:734ac5784ca910812b964d9b581da4b62c841350e99cf2913112b92239dd5f0d","observation_id":"3192a5ca-20dc-4aa3-afef-19ba6eae4aa9","resolution":{"observed_at":"2026-08-10T22:26:46.585138Z","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":"2026-08-10T22:26:46.589521Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.589521Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:4c783a628fa20b20db56c0fd1e8df422ed698cdf39621329a7fef12193db4980","observation_id":"40fb37c7-bbd4-4e41-894a-f80976204068","resolution":{"observed_at":"2026-08-10T22:26:46.589521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.00114","last_updated":"2021-11-30T21:32:46Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-11-30T21:32:46Z","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.00114","snapshot_observed_at":"2026-08-10T22:26:46.593679Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.593679Z"},"links":{"cited_paper":"/paper/2112.00114","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:55294cb0e67ef75056a48f21db5f260c779951a417125b6657798be040170dcf","observation_id":"d322aee8-f92e-4879-9d2a-2be39bdaae40","resolution":{"observed_at":"2026-08-10T22:26:46.593679Z","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":"2026-08-10T22:26:46.598437Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.598437Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:00402d1d5013d075658ed0e5d16041fa8624f6ba99af303d0ae35c062181bc4a","observation_id":"46c0eb61-7904-4aa0-a4ce-05f519b557d4","resolution":{"observed_at":"2026-08-10T22:26:46.598437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1508.00305","last_updated":"2015-08-03T02:53:01Z","snapshot_observed_at":"2026-07-06T04:25:37.491871Z","submitted_at":"2015-08-03T02:53:01Z","title":"Compositional Semantic Parsing on Semi-Structured Tables","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1508.00305","snapshot_observed_at":"2026-08-10T22:26:46.602577Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.602577Z"},"links":{"cited_paper":"/paper/1508.00305","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:866cce304340a4607e6d154614b5864d93ff80bc5ee9cb7ef7e0a49a9537ecfe","observation_id":"3c8e4cd7-397d-4970-aee9-486bf230ef4f","resolution":{"observed_at":"2026-08-10T22:26:46.602577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.11446","last_updated":"2022-01-21T18:39:38Z","snapshot_observed_at":"2026-08-09T14:52:01.161814Z","submitted_at":"2021-12-08T19:41:47Z","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.11446","snapshot_observed_at":"2026-08-10T22:26:46.607101Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.607101Z"},"links":{"cited_paper":"/paper/2112.11446","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:5a792ddd82384a2b990cd9889746383fa89b7069a2db0ef8d9a6af2c28e471b5","observation_id":"1dd01f2b-a5ec-4583-9bdd-6d64260bd6b5","resolution":{"observed_at":"2026-08-10T22:26:46.607101Z","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":"2026-08-10T22:26:47.283557Z","title":null,"venue":null,"work_id":"9eda25f0-9063-4d0a-834d-0ffea19c23df","year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.611934Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:4bc14211fef755ac53a4bc4dde9f3b070965e96c0d618507dd5e1d43ed0d7a38","observation_id":"3405bfce-d3d5-4c4f-9f60-6a7e9e24fcf4","resolution":{"observed_at":"2026-08-10T22:26:47.287734Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03716","last_updated":"2024-07-10T23:15:49Z","snapshot_observed_at":"2026-08-03T14:09:43.107865Z","submitted_at":"2023-10-05T17:38:28Z","title":"A Long Way to Go: Investigating Length Correlations in RLHF","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03716","snapshot_observed_at":"2026-08-10T22:26:46.616014Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.616014Z"},"links":{"cited_paper":"/paper/2310.03716","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:ea5b2bad66946df4611d97b6d4d0a34f06e9802bd984917c806e90d6e72d0ea7","observation_id":"fb2ff56d-3b00-4d5a-b7bf-0229e9336553","resolution":{"observed_at":"2026-08-10T22:26:46.616014Z","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":"2026-08-10T22:26:46.620298Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.620298Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:630ef6e4a573c5687461e326ebc1af1a089ae54e098813d5764c8885a6963ca4","observation_id":"84648f60-39ee-4086-a612-8a9ead00cba5","resolution":{"observed_at":"2026-08-10T22:26:46.620298Z","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":"2026-08-10T22:26:46.624341Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.624341Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:8d021c291dad741a47f2d02b08b45a96fd7fa7f71c71f944c04c5d8d9f41da08","observation_id":"ecb9ca0a-a7fe-4de6-ba3d-f5d562141763","resolution":{"observed_at":"2026-08-10T22:26:46.624341Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13690","last_updated":"2024-12-23T17:32:21Z","snapshot_observed_at":"2026-08-13T00:20:11.438026Z","submitted_at":"2024-06-18T07:14:02Z","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.13690","snapshot_observed_at":"2026-08-10T22:26:46.628984Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.628984Z"},"links":{"cited_paper":"/paper/2407.13690","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:08e634851b3eafdd1d17be164bc27b4ac9c2ead665391e1a07bb712b43e277a8","observation_id":"7bce2ac7-c49c-414a-b8e0-bb1527294212","resolution":{"observed_at":"2026-08-10T22:26:46.628984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-10T22:26:46.633763Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.633763Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:2e185488cc88d207a446cac62cd03a60f3f342dd042936e38371084ac45662d6","observation_id":"c28b2307-a179-4bc3-81b2-f69c12024b7d","resolution":{"observed_at":"2026-08-10T22:26:46.633763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.14275","last_updated":"2022-11-25T18:19:44Z","snapshot_observed_at":"2026-08-01T02:16:43.109337Z","submitted_at":"2022-11-25T18:19:44Z","title":"Solving math word problems with process- and outcome-based feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.14275","snapshot_observed_at":"2026-08-10T22:26:46.638811Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.638811Z"},"links":{"cited_paper":"/paper/2211.14275","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:d9d3cfa8ceefdd40bb0acf60e144b77c074a967389d49316fb0c92986490e997","observation_id":"d078e063-54ce-4f0e-8769-6f34f8563ce9","resolution":{"observed_at":"2026-08-10T22:26:46.638811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13514","last_updated":"2024-02-01T11:47:57Z","snapshot_observed_at":"2026-07-06T15:31:01.106910Z","submitted_at":"2023-05-22T22:07:50Z","title":"Small Language Models Improve Giants by Rewriting Their Outputs","version":2},"cited_work":{"arxiv_id":"2305.13514","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.13514","snapshot_observed_at":"2026-08-10T22:26:46.885611Z","title":"Small Language Models Improve Giants by Rewriting Their Outputs","venue":"cs.CL","work_id":"6e810487-0d2f-4d2b-8329-c901d47e7227","year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.643570Z"},"links":{"cited_paper":"/paper/2305.13514","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:d2129af3c17bd26503bfc9f3eb704b231b68952d11062d32767b55ca123c7092","observation_id":"7b6a61f5-8954-4943-a62b-832447e86def","resolution":{"observed_at":"2026-08-10T22:26:46.892731Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06688","last_updated":"2024-06-06T17:45:39Z","snapshot_observed_at":"2026-07-06T17:14:53.706063Z","submitted_at":"2024-01-12T16:52:41Z","title":"Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06688","snapshot_observed_at":"2026-08-10T22:26:46.648867Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.648867Z"},"links":{"cited_paper":"/paper/2401.06688","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:66537457b7c8b1ebdd6a14cbf40431f414a95362a55c91ffc9478014bf5d9bd7","observation_id":"f2a667fd-2d63-4450-a3a2-fb078a35d0be","resolution":{"observed_at":"2026-08-10T22:26:46.648867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12845","last_updated":"2024-06-18T17:58:28Z","snapshot_observed_at":"2026-08-12T23:39:50.330661Z","submitted_at":"2024-06-18T17:58:28Z","title":"Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12845","snapshot_observed_at":"2026-08-10T22:26:46.653799Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.653799Z"},"links":{"cited_paper":"/paper/2406.12845","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:84d5052ae3ebaa54d7d135311250610e90650cbcfca2a773cddda27792246873","observation_id":"76dd9384-d843-481b-9c36-4ba97b5fbc21","resolution":{"observed_at":"2026-08-10T22:26:46.653799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-10T22:26:46.658866Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.658866Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:a857c118a3d8b1f67541c3ee2839c4940c12d002c1bb254640c2ec1f4519d8dd","observation_id":"3b0724bd-c528-47ad-803e-d12bb701ac11","resolution":{"observed_at":"2026-08-10T22:26:46.658866Z","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":"2026-08-10T22:26:46.663594Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.663594Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:ec72769d6e1941d4f9df1cef40005f34694045646200c14f52447dc0f4c21c15","observation_id":"14a74d48-cad2-48ae-91ac-6ee4de04d0cd","resolution":{"observed_at":"2026-08-10T22:26:46.663594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00724","last_updated":"2025-03-03T07:53:32Z","snapshot_observed_at":"2026-08-13T03:06:10.986532Z","submitted_at":"2024-08-01T17:16:04Z","title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00724","snapshot_observed_at":"2026-08-10T22:26:46.668322Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.668322Z"},"links":{"cited_paper":"/paper/2408.00724","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:3d4041447d6b0bc9b749890ed97d71ea33510e55bf68f17312a553ac73e22c2c","observation_id":"e985f17e-3cae-4c23-a020-d239daa608b1","resolution":{"observed_at":"2026-08-10T22:26:46.668322Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-08-10T22:26:46.673511Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.673511Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:b899b77e95151ba5ef40ce47cf5314286bfe5851399c6b2ab79b65633d903305","observation_id":"10b4e99c-b57f-46e2-a862-5efe46224815","resolution":{"observed_at":"2026-08-10T22:26:46.673511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.09724","last_updated":"2024-04-01T13:50:51Z","snapshot_observed_at":"2026-08-07T05:06:51.002209Z","submitted_at":"2023-11-16T09:56:28Z","title":"OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.09724","snapshot_observed_at":"2026-08-10T22:26:46.678285Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.678285Z"},"links":{"cited_paper":"/paper/2311.09724","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:591643a9b47e47ed460d67f16ef078329118b236742810e074519fef622a2f8e","observation_id":"e735caae-08c7-4dc0-a8e3-0fe3e14a5801","resolution":{"observed_at":"2026-08-10T22:26:46.678285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16646","last_updated":"2025-02-09T07:53:38Z","snapshot_observed_at":"2026-08-12T16:05:51.527047Z","submitted_at":"2024-11-25T18:28:26Z","title":"Self-Generated Critiques Boost Reward Modeling for Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16646","snapshot_observed_at":"2026-08-10T22:26:46.683078Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.683078Z"},"links":{"cited_paper":"/paper/2411.16646","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:af73fdcae9d995523de5b04f763aa26a19fd854fe2b0d80b8903f9d7bc90c9e1","observation_id":"860b6c67-1087-476e-b6cd-f5f4d8e47482","resolution":{"observed_at":"2026-08-10T22:26:46.683078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15240","last_updated":"2025-02-22T10:21:46Z","snapshot_observed_at":"2026-08-12T22:56:24.326978Z","submitted_at":"2024-08-27T17:57:45Z","title":"Generative Verifiers: Reward Modeling as Next-Token Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15240","snapshot_observed_at":"2026-08-10T22:26:46.689014Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.689014Z"},"links":{"cited_paper":"/paper/2408.15240","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:0985769b819f1b510dff7538f8e128b79a04cd7961f723e24effd1c26cfe4c63","observation_id":"0746fdff-5d34-437d-b35c-ae2fa98875e9","resolution":{"observed_at":"2026-08-10T22:26:46.689014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.19318","last_updated":"2025-02-17T13:45:00Z","snapshot_observed_at":"2026-08-13T00:43:07.860214Z","submitted_at":"2024-03-28T11:21:12Z","title":"TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarios","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.19318","snapshot_observed_at":"2026-08-10T22:26:46.693554Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.693554Z"},"links":{"cited_paper":"/paper/2403.19318","citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:b027db8a7cbf56909d500cb05e38c88ce511b0d2f2e43881abb45e8b575a7f86","observation_id":"e3af67ad-e41f-41f9-848c-da6d1110f42d","resolution":{"observed_at":"2026-08-10T22:26:46.693554Z","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":"2026-08-10T22:26:46.698345Z","title":"online\" 'onlinestring :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.698345Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:495c87cabc335a1efc005bc963eff70ce6a6331e95342eb1fb66bf915049faff","observation_id":"3891e8d2-1f36-4775-9da3-c1b50cfa2ebe","resolution":{"observed_at":"2026-08-10T22:26:46.698345Z","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":"2026-08-10T22:26:46.703436Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T22:26:46.703436Z"},"links":{"citing_paper":"/paper/2501.01668"},"observation_digest":"sha256:fa60440efc2a5cdbe6c886ca7d66f3b19a0b0b65e34a177cecd21e9486c3c33b","observation_id":"a6ce8876-2c6d-4102-ba10-d9bdf23c231f","resolution":{"observed_at":"2026-08-10T22:26:46.703436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.01668","last_updated":"2025-06-14T09:58:51Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-11T15:59:54.184603Z","submitted_at":"2025-01-03T06:50:06Z","title":"CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":44,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":46},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 2 inbound Pith citation observations for arXiv:2501.01668."}