{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PVWR3YO4CP3PQRDH2QAIG3VMFX","short_pith_number":"pith:PVWR3YO4","canonical_record":{"source":{"id":"2502.11466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T05:52:44Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"52f9a9ae497e30cc7130b923503e5a6f393da681e31da33c4267f93628be866b","abstract_canon_sha256":"7bf643d7052fcce69ba2e9b813d62fc144df492a7d81da8384f29f3c902ac012"},"schema_version":"1.0"},"canonical_sha256":"7d6d1de1dc13f6f84467d400836eac2dd01374328bd9d7fee3863e6c4c483627","source":{"kind":"arxiv","id":"2502.11466","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11466","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11466v2","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11466","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"PVWR3YO4CP3P","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"PVWR3YO4CP3PQRDH","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"PVWR3YO4","created_at":"2026-07-05T11:06:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PVWR3YO4CP3PQRDH2QAIG3VMFX","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T05:52:44Z","cross_cats_sorted":["cs.CL","cs.SE"],"title_canon_sha256":"52f9a9ae497e30cc7130b923503e5a6f393da681e31da33c4267f93628be866b","abstract_canon_sha256":"7bf643d7052fcce69ba2e9b813d62fc144df492a7d81da8384f29f3c902ac012"},"schema_version":"1.0"},"canonical_sha256":"7d6d1de1dc13f6f84467d400836eac2dd01374328bd9d7fee3863e6c4c483627","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:28.319665Z","signature_b64":"+1Y7x/Xlsoqm0VkmqtqlpBW3MJgdIDxvDy0SmqEAAhEJh0EsdGJ5Hz00L/RJLpV5IJBuzS/BxBoA7wkGiqeZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d6d1de1dc13f6f84467d400836eac2dd01374328bd9d7fee3863e6c4c483627","last_reissued_at":"2026-07-05T11:06:28.319092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:28.319092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11466","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSBtMtnOwuuvgCpDGsa//UgDByJ+UIVN6YPtslokDAbjFVVTwDbTVrKSJM6BjVywKEB+0e4nFVGw5SDm/LedCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:34:42.629878Z"},"content_sha256":"238dbbfd9e04f955cb90868dc56c46c2ab68e1d852830d23d5cf30414e518df8","schema_version":"1.0","event_id":"sha256:238dbbfd9e04f955cb90868dc56c46c2ab68e1d852830d23d5cf30414e518df8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PVWR3YO4CP3PQRDH2QAIG3VMFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GiFT: Gibbs Fine-Tuning for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SE"],"primary_cat":"cs.LG","authors_text":"Haochen Li, Wanjin Feng, Xin Zhou, Zhiqi Shen","submitted_at":"2025-02-17T05:52:44Z","abstract_excerpt":"Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation. A key approach is self-training, where LLMs are iteratively trained on self-generated correct code snippets. In this case, the self-generated codes are drawn from a conditional distribution, conditioned on a specific seed description. However, the seed description is not the only valid representation that aligns with its intended meaning. With all valid descriptions and codes forming a joint space, codes drawn from the conditional distribution would lead to an underrepresentation of the full d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11466","kind":"arxiv","version":2},"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/2502.11466/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":"2026-07-05T11:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KSmCVnlxwaYXfavw8om9QMR6XdYecDAj8RIwCyezzjPmSxaUevMPmTB8gWed1LEv8wZcR2sSK613gS6HfX2VAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:34:42.630196Z"},"content_sha256":"02cbced5e76bf4cd8dc5b250627a3354add69a89f17e429df5502f7e717b126d","schema_version":"1.0","event_id":"sha256:02cbced5e76bf4cd8dc5b250627a3354add69a89f17e429df5502f7e717b126d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX/bundle.json","state_url":"https://pith.science/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX/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":"2026-08-01T08:34:42Z","links":{"resolver":"https://pith.science/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX","bundle":"https://pith.science/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX/bundle.json","state":"https://pith.science/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PVWR3YO4CP3PQRDH2QAIG3VMFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PVWR3YO4CP3PQRDH2QAIG3VMFX","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":"7bf643d7052fcce69ba2e9b813d62fc144df492a7d81da8384f29f3c902ac012","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T05:52:44Z","title_canon_sha256":"52f9a9ae497e30cc7130b923503e5a6f393da681e31da33c4267f93628be866b"},"schema_version":"1.0","source":{"id":"2502.11466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11466","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11466v2","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11466","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"PVWR3YO4CP3P","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"PVWR3YO4CP3PQRDH","created_at":"2026-07-05T11:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"PVWR3YO4","created_at":"2026-07-05T11:06:28Z"}],"graph_snapshots":[{"event_id":"sha256:02cbced5e76bf4cd8dc5b250627a3354add69a89f17e429df5502f7e717b126d","target":"graph","created_at":"2026-07-05T11:06:28Z","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/2502.11466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation. A key approach is self-training, where LLMs are iteratively trained on self-generated correct code snippets. In this case, the self-generated codes are drawn from a conditional distribution, conditioned on a specific seed description. However, the seed description is not the only valid representation that aligns with its intended meaning. With all valid descriptions and codes forming a joint space, codes drawn from the conditional distribution would lead to an underrepresentation of the full d","authors_text":"Haochen Li, Wanjin Feng, Xin Zhou, Zhiqi Shen","cross_cats":["cs.CL","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T05:52:44Z","title":"GiFT: Gibbs Fine-Tuning for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11466","kind":"arxiv","version":2},"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":"sha256:238dbbfd9e04f955cb90868dc56c46c2ab68e1d852830d23d5cf30414e518df8","target":"record","created_at":"2026-07-05T11:06:28Z","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":"7bf643d7052fcce69ba2e9b813d62fc144df492a7d81da8384f29f3c902ac012","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-17T05:52:44Z","title_canon_sha256":"52f9a9ae497e30cc7130b923503e5a6f393da681e31da33c4267f93628be866b"},"schema_version":"1.0","source":{"id":"2502.11466","kind":"arxiv","version":2}},"canonical_sha256":"7d6d1de1dc13f6f84467d400836eac2dd01374328bd9d7fee3863e6c4c483627","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d6d1de1dc13f6f84467d400836eac2dd01374328bd9d7fee3863e6c4c483627","first_computed_at":"2026-07-05T11:06:28.319092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:28.319092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+1Y7x/Xlsoqm0VkmqtqlpBW3MJgdIDxvDy0SmqEAAhEJh0EsdGJ5Hz00L/RJLpV5IJBuzS/BxBoA7wkGiqeZAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:28.319665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:238dbbfd9e04f955cb90868dc56c46c2ab68e1d852830d23d5cf30414e518df8","sha256:02cbced5e76bf4cd8dc5b250627a3354add69a89f17e429df5502f7e717b126d"],"state_sha256":"9e3c2674546fdd88cff3d5a1b1b5a491cf42bd65404e19e6ae9c0b4eb17a3546"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKS+X7OOf9nsN5l/2cGnXe7/V8ZEM+DIimoPSzh9YTb8taOBcG34FyLSWMh0fRG0X7nWVGhbKh6kRk7eAfnUBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T08:34:42.638229Z","bundle_sha256":"9fd6175302a2964db0d1493771d446027a1d214c4d789a665c6e156b5c77177c"}}