{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ","short_pith_number":"pith:QO5OZPEO","canonical_record":{"source":{"id":"2507.06980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-09T16:07:20Z","cross_cats_sorted":[],"title_canon_sha256":"a1902e18ec33dcd5b95e30312720fb98a85224a36b92a857b00a4abfe1a134eb","abstract_canon_sha256":"c2e4f7c1b9a03276643116512783899cfe5596e2600f91c28a78d01003e10860"},"schema_version":"1.0"},"canonical_sha256":"83baecbc8ebee49f8632cfa1b51f2d84133b75cb1b3923e7567d9ebe39784a34","source":{"kind":"arxiv","id":"2507.06980","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06980","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06980v1","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06980","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"QO5OZPEOX3SJ","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"pith_short_16","alias_value":"QO5OZPEOX3SJ7BRS","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"pith_short_8","alias_value":"QO5OZPEO","created_at":"2026-07-05T11:34:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06980","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-09T16:07:20Z","cross_cats_sorted":[],"title_canon_sha256":"a1902e18ec33dcd5b95e30312720fb98a85224a36b92a857b00a4abfe1a134eb","abstract_canon_sha256":"c2e4f7c1b9a03276643116512783899cfe5596e2600f91c28a78d01003e10860"},"schema_version":"1.0"},"canonical_sha256":"83baecbc8ebee49f8632cfa1b51f2d84133b75cb1b3923e7567d9ebe39784a34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:26.291084Z","signature_b64":"QSOlPBoU51OTmnRWYQUhybZC7QZVOsbN5iyEhp1R3ITEx7SQsDyyU9zjI5o4ns5hWQDF6tsaVXTVjbCQOcvcCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83baecbc8ebee49f8632cfa1b51f2d84133b75cb1b3923e7567d9ebe39784a34","last_reissued_at":"2026-07-05T11:34:26.290521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:26.290521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06980","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7oryX+1ASnjV+urTjvBSf7pIHJcbbAH9JX6qnIJ0DFbIKAFz40jieQWDWeog4lOHQ9mGmGB9iLk155/l9QSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:36.782562Z"},"content_sha256":"304461b14f30e9bd5e2582372d70a0d365dc5578623c8c992247693bb4731ff3","schema_version":"1.0","event_id":"sha256:304461b14f30e9bd5e2582372d70a0d365dc5578623c8c992247693bb4731ff3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Binquan Zhang, Fang Liu, Lin Shi, Li Zhang, Song Wang, Yuxin Du, Zhiwen Luo","submitted_at":"2025-07-09T16:07:20Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive performance in code generation, particularly when augmented with chain-of-thought (CoT) prompting techniques. They break down requirements into intermediate reasoning steps, which act as design rationales to guide LLMs in writing code like human programmers. Thus, the quality of these steps is crucial for ensuring the correctness and reliability of the generated code. However, little is known about the quality of CoT generated by LLMs. To what extent can we trust the thoughts generated by LLMs? How good are they? This paper empirically "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06980","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.06980/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3KlfB1fjs2A9wsy06ht+yctVN4a2mItASj8Sz3AE9UtQVT3BYOlGWt7Uz4Kz4IGq6PqqjG2DlTzIKSjorrvnCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:36.783558Z"},"content_sha256":"3fd2e003aaed6cafcde88529dc57a7d731de462601b6dc62371006d907d21e0b","schema_version":"1.0","event_id":"sha256:3fd2e003aaed6cafcde88529dc57a7d731de462601b6dc62371006d907d21e0b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ/bundle.json","state_url":"https://pith.science/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T06:31:36Z","links":{"resolver":"https://pith.science/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ","bundle":"https://pith.science/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ/bundle.json","state":"https://pith.science/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QO5OZPEOX3SJ7BRSZ6Q3KHZNQQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c2e4f7c1b9a03276643116512783899cfe5596e2600f91c28a78d01003e10860","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-09T16:07:20Z","title_canon_sha256":"a1902e18ec33dcd5b95e30312720fb98a85224a36b92a857b00a4abfe1a134eb"},"schema_version":"1.0","source":{"id":"2507.06980","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06980","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06980v1","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06980","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"pith_short_12","alias_value":"QO5OZPEOX3SJ","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"pith_short_16","alias_value":"QO5OZPEOX3SJ7BRS","created_at":"2026-07-05T11:34:26Z"},{"alias_kind":"pith_short_8","alias_value":"QO5OZPEO","created_at":"2026-07-05T11:34:26Z"}],"graph_snapshots":[{"event_id":"sha256:3fd2e003aaed6cafcde88529dc57a7d731de462601b6dc62371006d907d21e0b","target":"graph","created_at":"2026-07-05T11:34:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.06980/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated impressive performance in code generation, particularly when augmented with chain-of-thought (CoT) prompting techniques. They break down requirements into intermediate reasoning steps, which act as design rationales to guide LLMs in writing code like human programmers. Thus, the quality of these steps is crucial for ensuring the correctness and reliability of the generated code. However, little is known about the quality of CoT generated by LLMs. To what extent can we trust the thoughts generated by LLMs? How good are they? This paper empirically ","authors_text":"Binquan Zhang, Fang Liu, Lin Shi, Li Zhang, Song Wang, Yuxin Du, Zhiwen Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-09T16:07:20Z","title":"Are They All Good? Evaluating the Quality of CoTs in LLM-based Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06980","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:304461b14f30e9bd5e2582372d70a0d365dc5578623c8c992247693bb4731ff3","target":"record","created_at":"2026-07-05T11:34:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c2e4f7c1b9a03276643116512783899cfe5596e2600f91c28a78d01003e10860","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-09T16:07:20Z","title_canon_sha256":"a1902e18ec33dcd5b95e30312720fb98a85224a36b92a857b00a4abfe1a134eb"},"schema_version":"1.0","source":{"id":"2507.06980","kind":"arxiv","version":1}},"canonical_sha256":"83baecbc8ebee49f8632cfa1b51f2d84133b75cb1b3923e7567d9ebe39784a34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83baecbc8ebee49f8632cfa1b51f2d84133b75cb1b3923e7567d9ebe39784a34","first_computed_at":"2026-07-05T11:34:26.290521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:26.290521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QSOlPBoU51OTmnRWYQUhybZC7QZVOsbN5iyEhp1R3ITEx7SQsDyyU9zjI5o4ns5hWQDF6tsaVXTVjbCQOcvcCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:26.291084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06980","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:304461b14f30e9bd5e2582372d70a0d365dc5578623c8c992247693bb4731ff3","sha256:3fd2e003aaed6cafcde88529dc57a7d731de462601b6dc62371006d907d21e0b"],"state_sha256":"bc256dfdce09844c0aae5757ce3884a139404ceaa2b5f63ed9eb73586ac094dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4gKtkdt9ZTlyEkakhtLBgxQ1DukpuM3Gw3GG6vsersKRwnOvYCpSHVt83i5vN6eAF24G/3tTltL8XWIqsgOIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:31:36.791063Z","bundle_sha256":"7374816d6a7d11a2fdd3360aa4bf933796f1c7f4b1522e672c626f25a513bfab"}}