{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H4PN3PI2WKOFRNZWXYNGL7IOCL","short_pith_number":"pith:H4PN3PI2","canonical_record":{"source":{"id":"2307.04349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-10T05:18:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9cad5cf687ca353362305f4bbe1a3609101087681415a9447702deabf30a26fa","abstract_canon_sha256":"a3022175f1f029fde4afb8460c1d737c9b0d12610ed66302c5de23d253ca203d"},"schema_version":"1.0"},"canonical_sha256":"3f1eddbd1ab29c58b736be1a65fd0e12d0b352a4f2174b2fd4193b0fc450b03f","source":{"kind":"arxiv","id":"2307.04349","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04349","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04349v2","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04349","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"H4PN3PI2WKOF","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"H4PN3PI2WKOFRNZW","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"H4PN3PI2","created_at":"2026-07-05T07:11:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H4PN3PI2WKOFRNZWXYNGL7IOCL","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04349","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-10T05:18:18Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9cad5cf687ca353362305f4bbe1a3609101087681415a9447702deabf30a26fa","abstract_canon_sha256":"a3022175f1f029fde4afb8460c1d737c9b0d12610ed66302c5de23d253ca203d"},"schema_version":"1.0"},"canonical_sha256":"3f1eddbd1ab29c58b736be1a65fd0e12d0b352a4f2174b2fd4193b0fc450b03f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:57.664192Z","signature_b64":"wc6jLBABSrFvNsuJKrdpRFnAmy97DXLobmo3goFk1j8vHwS2Wws8xQIav+HPD6ceZetJuBNq6YiJq970S17mCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f1eddbd1ab29c58b736be1a65fd0e12d0b352a4f2174b2fd4193b0fc450b03f","last_reissued_at":"2026-07-05T07:11:57.663692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:57.663692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04349","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":"2026-07-05T07:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OSy6ztGUjNd54dCFQLzNtWhkk6VvS/yJuxfkPF6VS6EaaEsipbSUWh4pF8SJRD4c3ga1lVG8dMlvOFxz7ttJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:14:59.746265Z"},"content_sha256":"bf4df8d232f9f95925d31d5d4b3a38188f2c5ca05397d574c0dda3f2c701186a","schema_version":"1.0","event_id":"sha256:bf4df8d232f9f95925d31d5d4b3a38188f2c5ca05397d574c0dda3f2c701186a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H4PN3PI2WKOFRNZWXYNGL7IOCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RLTF: Reinforcement Learning from Unit Test Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Deheng Ye, Jiate Liu, Kaiwen Xiao, Qiang Fu, Wei Yang, Xiao Han, Yiqin Zhu","submitted_at":"2023-07-10T05:18:18Z","abstract_excerpt":"The goal of program synthesis, or code generation, is to generate executable code based on given descriptions. Recently, there has been an increasing number of studies employing reinforcement learning (RL) to improve the performance of large language models (LLMs) for code. However, current representative works either rely solely on offline frameworks, limiting the exploration of new sample spaces, or fall short in the utilization of unit test signals, not accounting for specific error locations within the code. To address these issues, we propose RLTF, i.e., Reinforcement Learning from Unit T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04349","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/2307.04349/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":"2026-07-05T07:11:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNyivq0uFaLgVnw3lwasxIz8wZ4sfk1UK68Z+vCHUEzvUzJW8+Kj3bFsnB4Fqx2u9CWZW8DXGRlv3AQp9cn2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:14:59.746778Z"},"content_sha256":"cbb1bad338fe33befb639a5788656d9eb0ce938808242a6014fc5ddf554be8bf","schema_version":"1.0","event_id":"sha256:cbb1bad338fe33befb639a5788656d9eb0ce938808242a6014fc5ddf554be8bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL/bundle.json","state_url":"https://pith.science/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL/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":"2026-08-07T22:14:59Z","links":{"resolver":"https://pith.science/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL","bundle":"https://pith.science/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL/bundle.json","state":"https://pith.science/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H4PN3PI2WKOFRNZWXYNGL7IOCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H4PN3PI2WKOFRNZWXYNGL7IOCL","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":"a3022175f1f029fde4afb8460c1d737c9b0d12610ed66302c5de23d253ca203d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-10T05:18:18Z","title_canon_sha256":"9cad5cf687ca353362305f4bbe1a3609101087681415a9447702deabf30a26fa"},"schema_version":"1.0","source":{"id":"2307.04349","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04349","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04349v2","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04349","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_12","alias_value":"H4PN3PI2WKOF","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_16","alias_value":"H4PN3PI2WKOFRNZW","created_at":"2026-07-05T07:11:57Z"},{"alias_kind":"pith_short_8","alias_value":"H4PN3PI2","created_at":"2026-07-05T07:11:57Z"}],"graph_snapshots":[{"event_id":"sha256:cbb1bad338fe33befb639a5788656d9eb0ce938808242a6014fc5ddf554be8bf","target":"graph","created_at":"2026-07-05T07:11:57Z","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/2307.04349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of program synthesis, or code generation, is to generate executable code based on given descriptions. Recently, there has been an increasing number of studies employing reinforcement learning (RL) to improve the performance of large language models (LLMs) for code. However, current representative works either rely solely on offline frameworks, limiting the exploration of new sample spaces, or fall short in the utilization of unit test signals, not accounting for specific error locations within the code. To address these issues, we propose RLTF, i.e., Reinforcement Learning from Unit T","authors_text":"Deheng Ye, Jiate Liu, Kaiwen Xiao, Qiang Fu, Wei Yang, Xiao Han, Yiqin Zhu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-10T05:18:18Z","title":"RLTF: Reinforcement Learning from Unit Test Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.04349","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:bf4df8d232f9f95925d31d5d4b3a38188f2c5ca05397d574c0dda3f2c701186a","target":"record","created_at":"2026-07-05T07:11:57Z","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":"a3022175f1f029fde4afb8460c1d737c9b0d12610ed66302c5de23d253ca203d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-10T05:18:18Z","title_canon_sha256":"9cad5cf687ca353362305f4bbe1a3609101087681415a9447702deabf30a26fa"},"schema_version":"1.0","source":{"id":"2307.04349","kind":"arxiv","version":2}},"canonical_sha256":"3f1eddbd1ab29c58b736be1a65fd0e12d0b352a4f2174b2fd4193b0fc450b03f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f1eddbd1ab29c58b736be1a65fd0e12d0b352a4f2174b2fd4193b0fc450b03f","first_computed_at":"2026-07-05T07:11:57.663692Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:57.663692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wc6jLBABSrFvNsuJKrdpRFnAmy97DXLobmo3goFk1j8vHwS2Wws8xQIav+HPD6ceZetJuBNq6YiJq970S17mCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:57.664192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04349","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf4df8d232f9f95925d31d5d4b3a38188f2c5ca05397d574c0dda3f2c701186a","sha256:cbb1bad338fe33befb639a5788656d9eb0ce938808242a6014fc5ddf554be8bf"],"state_sha256":"acd9f2ce1d1409192cfd9a724df4184bbfc91449e8952baca26a12f6717335a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WZKNzfpL8cw+/6Vm8Y6tDDj637fFwkNcFX+KxD1TDLJ/BhSVJQImVP/pKaoV6RrWpGeQrXewC43mXt9+NOMABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:14:59.750747Z","bundle_sha256":"9ff22860d29ba1b82f9675a4b5d7b70d835a590b422d249668dc0671f299d780"}}