{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LI5OT243TXLCFWX2TBEP3O7TFQ","short_pith_number":"pith:LI5OT243","canonical_record":{"source":{"id":"2502.11460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T05:37:02Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"0e6d3747f5fec3e3be37913137bb98322675904ce30e072636b3667061e37570","abstract_canon_sha256":"90a32a2f06ab35583a37f5a927d0d888b869c0b8fe610c010d17b151f576757d"},"schema_version":"1.0"},"canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","source":{"kind":"arxiv","id":"2502.11460","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11460","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11460v1","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11460","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"LI5OT243TXLC","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"LI5OT243TXLCFWX2","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"LI5OT243","created_at":"2026-07-05T10:15:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LI5OT243TXLCFWX2TBEP3O7TFQ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.11460","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T05:37:02Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"0e6d3747f5fec3e3be37913137bb98322675904ce30e072636b3667061e37570","abstract_canon_sha256":"90a32a2f06ab35583a37f5a927d0d888b869c0b8fe610c010d17b151f576757d"},"schema_version":"1.0"},"canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:29.141429Z","signature_b64":"9wa10BmftgqqM2P0jMnQMQynDSl8wwfoAryXcitraT8IC5BalEGP3mzPwmlC/rjGP31z7a1rSLjqECXNXGoJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","last_reissued_at":"2026-07-05T10:15:29.140941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:29.140941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.11460","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":"2026-07-05T10:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CjuS4jI2adHVUe7N1pgu4BwYqVm4KRmKVLtaQNmyYm/llaLw54SVb2y6XWSYLN4BbJggoLwKtCsYwa8lx2d0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:37:17.560181Z"},"content_sha256":"3aaa3fe9b17fbe7b3402b9ee86f3d435db6ac404c758e206d7503fed46c7ae81","schema_version":"1.0","event_id":"sha256:3aaa3fe9b17fbe7b3402b9ee86f3d435db6ac404c758e206d7503fed46c7ae81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LI5OT243TXLCFWX2TBEP3O7TFQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Demin Song, Kai Chen, Linyang Li, Peiji Li, Qipeng Guo, Xipeng Qiu, Yichuan Ma, Yunfan Shao","submitted_at":"2025-02-17T05:37:02Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale pre-training data and (ii) synthesizing instruction data through prompt engineering with powerful models. While pre-training data faces quality consistency issues, instruction-based synthesis suffers from limited instruction diversity and inherent biases of LLMs. To address this gap, we introduce UnitCoder, a systematic pipeline leveraging model-generated unit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11460","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/2502.11460/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":"2026-07-05T10:15:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S//mbY0+EAOrzbdVwl+gfslHxV5X0EP6qviKDlFrtW86fiXH0GcqitVaRJ+3FaAYlWWr1OX0b1qvQ2jvdsFCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T02:37:17.560847Z"},"content_sha256":"b03b5550fe806b51910cd37650b7a1265caeca48b9fd8d598eae1c5de48c9977","schema_version":"1.0","event_id":"sha256:b03b5550fe806b51910cd37650b7a1265caeca48b9fd8d598eae1c5de48c9977"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/bundle.json","state_url":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/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":"2026-07-07T02:37:17Z","links":{"resolver":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ","bundle":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/bundle.json","state":"https://pith.science/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LI5OT243TXLCFWX2TBEP3O7TFQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LI5OT243TXLCFWX2TBEP3O7TFQ","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":"90a32a2f06ab35583a37f5a927d0d888b869c0b8fe610c010d17b151f576757d","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T05:37:02Z","title_canon_sha256":"0e6d3747f5fec3e3be37913137bb98322675904ce30e072636b3667061e37570"},"schema_version":"1.0","source":{"id":"2502.11460","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11460","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11460v1","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11460","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"pith_short_12","alias_value":"LI5OT243TXLC","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"pith_short_16","alias_value":"LI5OT243TXLCFWX2","created_at":"2026-07-05T10:15:29Z"},{"alias_kind":"pith_short_8","alias_value":"LI5OT243","created_at":"2026-07-05T10:15:29Z"}],"graph_snapshots":[{"event_id":"sha256:b03b5550fe806b51910cd37650b7a1265caeca48b9fd8d598eae1c5de48c9977","target":"graph","created_at":"2026-07-05T10:15:29Z","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/2502.11460/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet code generation remains a major challenge. Current approaches for obtaining high-quality code data primarily focus on (i) collecting large-scale pre-training data and (ii) synthesizing instruction data through prompt engineering with powerful models. While pre-training data faces quality consistency issues, instruction-based synthesis suffers from limited instruction diversity and inherent biases of LLMs. To address this gap, we introduce UnitCoder, a systematic pipeline leveraging model-generated unit","authors_text":"Demin Song, Kai Chen, Linyang Li, Peiji Li, Qipeng Guo, Xipeng Qiu, Yichuan Ma, Yunfan Shao","cross_cats":["cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T05:37:02Z","title":"UnitCoder: Scalable Iterative Code Synthesis with Unit Test Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11460","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":"sha256:3aaa3fe9b17fbe7b3402b9ee86f3d435db6ac404c758e206d7503fed46c7ae81","target":"record","created_at":"2026-07-05T10:15:29Z","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":"90a32a2f06ab35583a37f5a927d0d888b869c0b8fe610c010d17b151f576757d","cross_cats_sorted":["cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T05:37:02Z","title_canon_sha256":"0e6d3747f5fec3e3be37913137bb98322675904ce30e072636b3667061e37570"},"schema_version":"1.0","source":{"id":"2502.11460","kind":"arxiv","version":1}},"canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a3ae9eb9b9dd622dafa9848fdbbf32c20fceb8c6c0873451a9441b8f4d4d594","first_computed_at":"2026-07-05T10:15:29.140941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:29.140941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9wa10BmftgqqM2P0jMnQMQynDSl8wwfoAryXcitraT8IC5BalEGP3mzPwmlC/rjGP31z7a1rSLjqECXNXGoJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:29.141429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11460","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aaa3fe9b17fbe7b3402b9ee86f3d435db6ac404c758e206d7503fed46c7ae81","sha256:b03b5550fe806b51910cd37650b7a1265caeca48b9fd8d598eae1c5de48c9977"],"state_sha256":"b4f4ab50050a802586316aba8ff505b2f35eae31ae151bbe504235d6848f16af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8WBU0LEB3sTyDihTtAEpGCTli/+7zkHwDPVE+hawOF/lw9T5brCIEbagpE7kH8B+eY9BfnmeymvNLcfIvwXqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T02:37:17.565116Z","bundle_sha256":"87adcdc233c2bd204c5ad9e10e67066acae1736d1e0cf2ea832be4a1293a7fd0"}}