{"as_of":"2026-08-08T05:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:723c62b31fc57fff7e94e5c5ab402a45cc38292033a1555fed7d8775a878c83b","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:49:36.194123Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T06:13:01.236121Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.12728","snapshot_observed_at":"2026-08-03T06:13:01.236121Z","title":"Mcts-refined cot: High-quality fine-tuning data for llm-based repository issue resolution.arXiv preprint arXiv:2506.12728, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.23257","last_updated":"2026-05-27T23:46:30Z","snapshot_observed_at":"2026-08-05T01:50:54.147116Z","submitted_at":"2026-01-30T18:25:39Z","title":"From Historical Patches to Repair Plans: Outcome-Conditioned Reasoning for Repository-Level Program Repair","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T06:13:01.236121Z"},"links":{"cited_paper":"/paper/2506.12728","citing_paper":"/paper/2601.23257"},"observation_digest":"sha256:614b21bb23d8ccd74b2b9f4b043653fe9289503db6c874b606ea3e0fe3c62f6e","observation_id":"e9c529d4-39c3-40e0-88fe-4dfdd2219e79","resolution":{"observed_at":"2026-08-03T06:13:01.236121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.12728/citation-record","integrity":"/paper/2506.12728/integrity","json":"/paper/2506.12728/citation-record.json","paper":"/paper/2506.12728"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:39.289732Z","title":null,"venue":null,"work_id":"58dba2e5-1655-44e1-bc00-135f64fccad4","year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.074316Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:ffa2f6274973fa761e4d30f9d36c1af7259e558f49c3d73d710fa5784ff0d44e","observation_id":"a3f5e1f2-07c5-413f-b514-b58b3ffa8cfe","resolution":{"observed_at":"2026-08-07T00:49:39.362261Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:39.120951Z","title":"Large language models for software engineering: A systematic literature review[J]","venue":null,"work_id":"f40ec8e8-2c38-4e87-a988-777ec42fbb45","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.183137Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:6cea2f248181d2ff0ec98cf4c69e2863e786bda0496153a9200552af855c860d","observation_id":"b04d7347-8b3a-4f69-b149-a0198ae338cf","resolution":{"observed_at":"2026-08-07T00:49:39.214121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.976489Z","title":"Software testing with large language models: Survey, landscape, and vision[J]","venue":null,"work_id":"30838b39-9788-4011-b5b9-3293f26c8278","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.293255Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:cf592e9d5f48238553a06ec56f7fc31d4a2d9c9c70d4ce9428ed4fd833dc252c","observation_id":"727d9d79-577b-4f21-bc1e-c5a7dda46d82","resolution":{"observed_at":"2026-08-07T00:49:39.050603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-07T00:49:32.443911Z","title":"Deepseek-v3 technical report[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.443911Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:35c21f4214b98b5883b46726aa3cbfa6e9cbf512eada12ce8babd6787300e131","observation_id":"2e364cb1-de29-4d49-84f4-1b7c54b1b34f","resolution":{"observed_at":"2026-08-07T00:49:32.443911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14196","last_updated":"2024-01-26T09:23:11Z","snapshot_observed_at":"2026-08-06T22:40:28.707813Z","submitted_at":"2024-01-25T14:17:53Z","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14196","snapshot_observed_at":"2026-08-07T00:49:32.598281Z","title":"DeepSeek-Coder: When the Large Language Model Meets Programming–The Rise of Code Intelligence[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.598281Z"},"links":{"cited_paper":"/paper/2401.14196","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:56c57c8171606972a8b778181c40f6a2b64d61f23d737e131d2c896d7e80c902","observation_id":"084e6028-bf51-4543-bc4a-d2bacf6b507b","resolution":{"observed_at":"2026-08-07T00:49:32.598281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12950","last_updated":"2024-01-31T19:47:26Z","snapshot_observed_at":"2026-07-06T16:10:07.931347Z","submitted_at":"2023-08-24T17:39:13Z","title":"Code Llama: Open Foundation Models for Code","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12950","snapshot_observed_at":"2026-08-07T00:49:32.634419Z","title":"Code llama: Open foundation models for code[J]","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.634419Z"},"links":{"cited_paper":"/paper/2308.12950","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:7973667e730f730db40ae3b3e13c75096152b22aadf7d2f90e5ecccaddad948a","observation_id":"11bae016-b600-4909-8608-773efd5b1f5b","resolution":{"observed_at":"2026-08-07T00:49:32.634419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.02320","last_updated":"2024-11-04T17:46:20Z","snapshot_observed_at":"2026-08-04T11:37:37.551344Z","submitted_at":"2024-11-04T17:46:20Z","title":"An Empirical Study on the Code Refactoring Capability of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.02320","snapshot_observed_at":"2026-08-07T00:49:32.723197Z","title":"An Empirical Study on the Code Refactoring Capability of Large Language Models[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.723197Z"},"links":{"cited_paper":"/paper/2411.02320","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:0540cd6399fbdd9ebdb5d25cc0a83f1b57ad92c874d4b8d1b1b60f5530f77a0b","observation_id":"439e8265-1dc0-4352-8220-e8b6908b13c6","resolution":{"observed_at":"2026-08-07T00:49:32.723197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.852101Z","title":null,"venue":null,"work_id":"956acf7a-97fd-4769-8a23-a0ef95d6144d","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.848263Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:e12c6f9a60e360f788fd7746c19e24ab770a4adc5b441a024877023b690c4ccf","observation_id":"c2876b8f-598f-4e32-991b-2172931ebfb8","resolution":{"observed_at":"2026-08-07T00:49:38.905020Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.732609Z","title":null,"venue":null,"work_id":"5f2e8f2d-582a-4d51-9798-d8561a391da0","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:32.974363Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:e1a1ce4a5774d96addf0df44997966beefbb6409539d6e79d34bb0a90b4a92c3","observation_id":"4bd08387-6570-41de-ae70-0879edb369f2","resolution":{"observed_at":"2026-08-07T00:49:38.795769Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","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":"2026-08-07T00:49:33.035023Z","title":"The llama 3 herd of models[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.035023Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:6a409abe94b550cc9d38baa1560b2f9fb64cd290f2dc89ff5059e0c641e3bb7e","observation_id":"3b46656a-b300-4914-99ed-0374aa3172bf","resolution":{"observed_at":"2026-08-07T00:49:33.035023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06770","last_updated":"2024-11-11T23:05:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T16:47:29Z","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06770","snapshot_observed_at":"2026-08-07T00:49:33.128640Z","title":"Swe-bench: Can language models resolve real-world github issues?[J]","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.128640Z"},"links":{"cited_paper":"/paper/2310.06770","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:5367297a72632b6957e33973c6bb3b2eab3e859c87e9dea9cbfe00ff882c996c","observation_id":"ab4c1e4f-4cec-4e60-bf96-970011da2db6","resolution":{"observed_at":"2026-08-07T00:49:33.128640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.571050Z","title":"Chain-of-thought in neural code gener- ation: From and for lightweight language models[J]","venue":null,"work_id":"59891f6c-6ff5-45e0-8f52-953e26bb448b","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.228431Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:8bacf116b69fc5c04668af2932fb5002b0bbf29fd041783f8efa56249f82206e","observation_id":"7af1aebc-6709-4dd3-a8ed-bbfd388d3f02","resolution":{"observed_at":"2026-08-07T00:49:38.653880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.436028Z","title":"Structured chain-of-thought prompting for code generation[J]","venue":null,"work_id":"298b6d65-e313-417d-af26-32c565b47b78","year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.351378Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:2f4ae238623029427dbdbabe9ea3f863b0b894a72f39a4a9f23b1ccd0ba384a6","observation_id":"1b640a4b-4d54-4cf8-8ee1-ae2b14d108d5","resolution":{"observed_at":"2026-08-07T00:49:38.491408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.273735Z","title":"Recursive introspection: Teaching language model agents how to self-improve[J]","venue":null,"work_id":"02411f0e-f30a-4097-9519-6240c317463c","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.434439Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:7e73c6c848f44e749d9ecff20e0527ca85e097942dc5384ab4dfd08c842b7976","observation_id":"c3601886-f1bd-4533-bb5e-a39f3a68cfa0","resolution":{"observed_at":"2026-08-07T00:49:38.361017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.14492","last_updated":"2025-01-24T13:48:10Z","snapshot_observed_at":"2026-07-06T20:25:36.218904Z","submitted_at":"2025-01-24T13:48:10Z","title":"RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.14492","snapshot_observed_at":"2026-08-07T00:49:33.542633Z","title":"RealCritic: Towards Effectiveness- Driven Evaluation of Language Model Critiques[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.542633Z"},"links":{"cited_paper":"/paper/2501.14492","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:d29ad7707815476bb48a355e3dd7e3cb4d24d587f27dee7f1d6e15ecbf5afbda","observation_id":"42f418bb-9359-4ca8-a4dc-db0587dc668e","resolution":{"observed_at":"2026-08-07T00:49:33.542633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:33.594874Z","title":"Instruction tuning for large language models: A survey[J]","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.594874Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:d72047e2aef59ccf6d5ce26f27e030a53bc0a83b4eb5cd7429caa3872aa9bb88","observation_id":"a8dc5062-e58a-487f-b9fb-ed3066c4ee83","resolution":{"observed_at":"2026-08-07T00:49:33.594874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T00:49:33.689845Z","title":"Deepseek-r1: Incentivizing reason- ing capability in llms via reinforcement learning[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.689845Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:81cede15b9c87525bf6aa323649e2d6bbfdfd86a0be64a1b6f89d7f4b46e9c33","observation_id":"7010fb60-e203-4cb0-9de3-d2149442c714","resolution":{"observed_at":"2026-08-07T00:49:33.689845Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:38.141273Z","title":"Rest-mcts*: Llm self-training via process reward guided tree search[J]","venue":null,"work_id":"444c7d2a-68d5-40e6-9b1d-b34d822fbfcd","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:33.817122Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:74225a3d0ece3c6292d4b673e378d61651d9f2df7a54946a86ed187ca6a50e3b","observation_id":"68767acb-d613-48dc-8040-06c001592b38","resolution":{"observed_at":"2026-08-07T00:49:38.191705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-07T00:49:34.039982Z","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.039982Z"},"links":{"cited_paper":"/paper/2501.04519","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:52ee553116ec8ce5e55e596fbabf0729ae421316cdb619fb3194ace25c0cd800","observation_id":"59d93812-8bd4-4b1c-8421-7c8c5550685c","resolution":{"observed_at":"2026-08-07T00:49:34.039982Z","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":"2026-08-07T00:49:34.130943Z","title":"Towards reasoning era: A survey of long chain-of-thought for reasoning large language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.130943Z"},"links":{"cited_paper":"/paper/2503.09567","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:117842732b8ae3a4339321ddb7dd0251ee9080bc71a59566a2e7d7264102695f","observation_id":"ceb9ecb3-8dde-45d3-940b-67aae2af0558","resolution":{"observed_at":"2026-08-07T00:49:34.130943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12186","last_updated":"2024-11-12T13:24:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-18T17:57:57Z","title":"Qwen2.5-Coder Technical Report","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12186","snapshot_observed_at":"2026-08-07T00:49:34.246060Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.246060Z"},"links":{"cited_paper":"/paper/2409.12186","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:76e60ec6f0593ad3de98daa87f86229d425d5353dc9fea0a48bc621d854ba6cb","observation_id":"36a102e8-b41a-4e80-a14f-5d60920718b1","resolution":{"observed_at":"2026-08-07T00:49:34.246060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:37.975331Z","title":"Lingma SWE-GPT: An open development- process-centric language model for automated software improvement","venue":null,"work_id":"8f96c202-95e8-4609-80fc-acba0e33ab57","year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.356267Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:920ab9527415f274d49a97cd0220ee7d6ae6043a20ef673bc09edae08fedca52","observation_id":"446c9324-f0d0-4177-bda7-6bb2aeb93d18","resolution":{"observed_at":"2026-08-07T00:49:38.053833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:37.828081Z","title":"Swe-agent: Agent-computer interfaces enable automated software engineering[J]","venue":null,"work_id":"91ee13f9-1edf-42fe-8de1-e8309e24d0f7","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.427920Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:b3821b76e0e68c2fb791d93bb207f31807d4ca64d3c16709c650b12e2c47f0f2","observation_id":"086b29ee-4ca9-48e9-8217-9e66e806fdc8","resolution":{"observed_at":"2026-08-07T00:49:37.888583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20127","last_updated":"2025-02-27T14:19:45Z","snapshot_observed_at":"2026-08-07T17:42:48.487164Z","submitted_at":"2025-02-27T14:19:45Z","title":"SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20127","snapshot_observed_at":"2026-08-07T00:49:34.508796Z","title":"Sorft: Issue resolving with subtask-oriented reinforced fine-tuning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.508796Z"},"links":{"cited_paper":"/paper/2502.20127","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:029569ad39e5ed0850a73ac42b747ee8b7469a1bb48f53bc8cff4f4352d39dbd","observation_id":"7dbd0a19-0c5f-46b6-b891-e4bb2b8f03e5","resolution":{"observed_at":"2026-08-07T00:49:34.508796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.18449","last_updated":"2025-12-01T00:16:59Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-02-25T18:45:04Z","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.18449","snapshot_observed_at":"2026-08-07T00:49:34.669625Z","title":"Swe-rl: Advancing llm reasoning via reinforcement learning on open software evolution","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.669625Z"},"links":{"cited_paper":"/paper/2502.18449","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:d7c596803c10dd4ee941f9e3321497dcf30239c478484d8fd5f01fd8ae4e4711","observation_id":"fd39c5a9-98ce-4c11-80fc-d0080fab6a6b","resolution":{"observed_at":"2026-08-07T00:49:34.669625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.21139","last_updated":"2025-06-06T07:53:20Z","snapshot_observed_at":"2026-07-06T20:14:49.976782Z","submitted_at":"2024-12-30T18:15:39Z","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.21139","snapshot_observed_at":"2026-08-07T00:49:34.793471Z","title":"Training Software Engineering Agents and Verifiers with SWE-Gym","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.793471Z"},"links":{"cited_paper":"/paper/2412.21139","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:5c55b719c74da9ec0ce3911a859f5a012609ede0aa3e7072b628c7249b5665b4","observation_id":"f8c7c5cd-7f9d-4b7d-93b6-5aefafe61eb3","resolution":{"observed_at":"2026-08-07T00:49:34.793471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.05040","last_updated":"2025-05-07T04:06:41Z","snapshot_observed_at":"2026-07-06T20:18:35.429115Z","submitted_at":"2025-01-09T07:54:24Z","title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.05040","snapshot_observed_at":"2026-08-07T00:49:34.867693Z","title":"SWE- Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.867693Z"},"links":{"cited_paper":"/paper/2501.05040","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:8734de277075f16f22faa4d861aa27baf5d6eb016c7718f08a78822fb6734691","observation_id":"304004a8-5abd-4589-9031-288696c97741","resolution":{"observed_at":"2026-08-07T00:49:34.867693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:34.988070Z","title":"RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:34.988070Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:3db3d4a88bc5d25bef981eadf04f2b275b169ce3086eb1981c5c63c1f908379d","observation_id":"c7396434-deae-47ec-a471-9e04d28fe1ee","resolution":{"observed_at":"2026-08-07T00:49:34.988070Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01489","last_updated":"2024-10-29T17:29:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-01T17:24:45Z","title":"Agentless: Demystifying LLM-based Software Engineering Agents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01489","snapshot_observed_at":"2026-08-07T00:49:35.090793Z","title":"S., Deng, Y ., Dunn, S., & Zhang, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.090793Z"},"links":{"cited_paper":"/paper/2407.01489","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:25c38dd179fee903e9fa906e9c7ed08fbf9582a5e4c9e80c2c64b00cc0c5a3ad","observation_id":"f60fe8d7-79ea-4af3-b293-db136d1d1a8c","resolution":{"observed_at":"2026-08-07T00:49:35.090793Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:37.616717Z","title":"Rest-mcts: Llm self-training via process reward guided tree search[J]","venue":null,"work_id":"c73192d9-eb56-4a25-9784-36e976b1a927","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.200240Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:d1ecca1b1d17d31557b104f10dd5c980f3ca660b13cd588fd6b50ff75acdf6c5","observation_id":"6e07fb15-f3f7-45e2-b4e6-a840ac9ab688","resolution":{"observed_at":"2026-08-07T00:49:37.702231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:37.432523Z","title":"Swe-agent: Agent-computer interfaces enable automated software engineering","venue":null,"work_id":"1fe14a79-4ec0-4038-a54c-f2c788422651","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.273464Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:57217ac54faf05bc43c201de449e57ba38609fb005a26e6aad709dbe8dd9708e","observation_id":"31f1aaaa-86d0-4b54-ab5f-612c82a80906","resolution":{"observed_at":"2026-08-07T00:49:37.501435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:37.300174Z","title":"Openhands: An open platform for ai software developers as generalist agents.//The Thirteenth International Conference on Learning Representations","venue":null,"work_id":"0a1644a8-d7e4-48c5-a68b-e3292eeaf1d3","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.386546Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:b8f6ee8901936a179fa7e29d00d3b06dd090a0aeefb966f48ef904a146c93905","observation_id":"17f7435c-e95b-405b-970e-ee60d809295d","resolution":{"observed_at":"2026-08-07T00:49:37.347064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19031","last_updated":"2024-12-26T03:01:32Z","snapshot_observed_at":"2026-08-07T06:27:40.158722Z","submitted_at":"2024-12-26T03:01:32Z","title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","version":1},"cited_work":{"arxiv_id":"2412.19031","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.19031","snapshot_observed_at":"2026-08-07T00:49:36.385627Z","title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","venue":"cs.SE","work_id":"80cd8f8c-9beb-4b58-a8f0-8bebec190e41","year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.472160Z"},"links":{"cited_paper":"/paper/2412.19031","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:7d4303d4fb448756c46113a321c266d26e5a915f805865f0b9a103683be0cddc","observation_id":"cb77cc7e-f70f-44cb-92d3-20305b43d89f","resolution":{"observed_at":"2026-08-07T00:49:36.476965Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.15292","last_updated":"2025-02-21T08:37:02Z","snapshot_observed_at":"2026-08-07T17:59:22.222963Z","submitted_at":"2025-02-21T08:37:02Z","title":"Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.15292","snapshot_observed_at":"2026-08-07T00:49:35.536554Z","title":"Bridging Bug Localization and Issue Fixing: A Hierarchical Localization Framework Leveraging Large Language Models[J]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.536554Z"},"links":{"cited_paper":"/paper/2502.15292","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:3cfdc76dc0cf7c65415bfeac34e5ad7e370193f09f68fcf38e5eb76fd42cc0f8","observation_id":"43e97a3c-ab94-43da-959b-312333852b63","resolution":{"observed_at":"2026-08-07T00:49:35.536554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01560","last_updated":"2024-10-05T03:54:22Z","snapshot_observed_at":"2026-07-06T19:26:02.193680Z","submitted_at":"2024-10-02T14:00:09Z","title":"OpenMathInstruct-2: Accelerating AI for Math with Massive Open-Source Instruction Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01560","snapshot_observed_at":"2026-08-07T00:49:35.646586Z","title":"Openmathinstruct-2: Accelerating ai for math with massive open-source instruction data[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.646586Z"},"links":{"cited_paper":"/paper/2410.01560","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:16f4f1e76a6690749d0ca7175f5ae4c7c4b650ec6eeab9d45a27b984b20281df","observation_id":"0b40f663-46a7-429a-ae41-d907f88edb21","resolution":{"observed_at":"2026-08-07T00:49:35.646586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16380","last_updated":"2024-01-29T18:19:08Z","snapshot_observed_at":"2026-07-06T17:21:58.983048Z","submitted_at":"2024-01-29T18:19:08Z","title":"Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16380","snapshot_observed_at":"2026-08-07T00:49:35.734975Z","title":"Rephrasing the web: A recipe for compute and data-efficient language modeling[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.734975Z"},"links":{"cited_paper":"/paper/2401.16380","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:d8de2d4ae7a4c4197c2dcd8af424c255e93f8fff77cfead0ef5e974713a1a6fb","observation_id":"02e4352e-6e95-453e-bf01-72a906a47bcc","resolution":{"observed_at":"2026-08-07T00:49:35.734975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.12896","last_updated":"2024-10-16T16:12:39Z","snapshot_observed_at":"2026-07-06T19:34:51.296918Z","submitted_at":"2024-10-16T16:12:39Z","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.12896","snapshot_observed_at":"2026-08-07T00:49:35.791398Z","title":"A survey on data synthesis and augmen- tation for large language models[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.791398Z"},"links":{"cited_paper":"/paper/2410.12896","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:535f62323651b299ef2edc3d23004dad3b86bb864f2ab8da37ba1889b2df9dc2","observation_id":"59767ec8-0ea4-49d7-934b-629c4656807e","resolution":{"observed_at":"2026-08-07T00:49:35.791398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:35.857930Z","title":"Impact of code language models on automated program repair[C]//2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.857930Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:ef023c9f194adb2be4c57e666ed2eca70cc97356d82f2376cbd6a96be0d425c1","observation_id":"788d0b7e-50ec-4b3d-abd9-57c5b5f5784c","resolution":{"observed_at":"2026-08-07T00:49:35.857930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:37.160901Z","title":"An empirical evaluation of using large language models for automated unit test generation[J]","venue":null,"work_id":"4986dab1-7cef-4ea2-af36-91c98be1f17c","year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:35.962619Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:0c9895dd8a3bf239abd9c68bf0a3e3fc3eca96afe7f511764f300fb3cc0cb53a","observation_id":"2180bd36-4cf5-4b4a-9bdb-32ba3fe129a3","resolution":{"observed_at":"2026-08-07T00:49:37.210981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13372","last_updated":"2024-06-27T22:44:48Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-03-20T08:08:54Z","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13372","snapshot_observed_at":"2026-08-07T00:49:36.040614Z","title":"Llamafactory: Unified efficient fine- tuning of 100+ language models[J]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:36.040614Z"},"links":{"cited_paper":"/paper/2403.13372","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:12fb4171d8d5ed62b09e0e55f11829b435ebce8bf560e549d9995ec6194204b6","observation_id":"c38d15e0-97a0-419d-9bf3-8c5af6c82729","resolution":{"observed_at":"2026-08-07T00:49:36.040614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:49:36.992163Z","title":"Lora: Low-rank adaptation of large language models[J]","venue":null,"work_id":"76b2a208-7e5e-48e9-bce0-32d54a644da3","year":2022},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:36.115764Z"},"links":{"citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:8ce1bb4c0a8bcb38ab39d6331fca34b848426dd08c52e071a3182b8c7f0e227a","observation_id":"a14f16df-bf3d-4550-b9f9-0bb4a12efbb7","resolution":{"observed_at":"2026-08-07T00:49:37.083461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08109","last_updated":"2023-04-18T03:08:18Z","snapshot_observed_at":"2026-08-05T17:52:48.117684Z","submitted_at":"2023-04-17T09:36:36Z","title":"A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08109","snapshot_observed_at":"2026-08-07T00:49:36.194123Z","title":"A comparative study between full-parameter and lora-based fine-tuning on chinese instruction data for instruction following large language model[J]","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:36.194123Z"},"links":{"cited_paper":"/paper/2304.08109","citing_paper":"/paper/2506.12728"},"observation_digest":"sha256:76ab734489d09b3ecb5472b9610a688406c3c44e04cb52cb58158d2c138ecb0e","observation_id":"79f16ac7-51a7-491b-a681-9f29f3eba136","resolution":{"observed_at":"2026-08-07T00:49:36.194123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.12728","last_updated":"2025-06-15T05:42:01Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-07T00:41:18.488297Z","submitted_at":"2025-06-15T05:42:01Z","title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":1,"verified_fuzzy":13},"total_outbound_references":42},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2506.12728."}