{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JEHVI72WZO4UR5YZW3LTWUYG53","short_pith_number":"pith:JEHVI72W","canonical_record":{"source":{"id":"2310.03173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T21:40:36Z","cross_cats_sorted":[],"title_canon_sha256":"e5545daaf478ec9d22c8fe3abf300b68440069b4c68304a08e3ecbf56d1c7d2d","abstract_canon_sha256":"93cc2db8704400c3b4ce737931999a16a44221d4262cc7d35194113139ef2cd6"},"schema_version":"1.0"},"canonical_sha256":"490f547f56cbb948f719b6d73b5306eefa17f0eccbde3bb9bb254c656055ddd3","source":{"kind":"arxiv","id":"2310.03173","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03173","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03173v2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03173","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"JEHVI72WZO4U","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"JEHVI72WZO4UR5YZ","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"JEHVI72W","created_at":"2026-07-05T07:57:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JEHVI72WZO4UR5YZW3LTWUYG53","target":"record","payload":{"canonical_record":{"source":{"id":"2310.03173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T21:40:36Z","cross_cats_sorted":[],"title_canon_sha256":"e5545daaf478ec9d22c8fe3abf300b68440069b4c68304a08e3ecbf56d1c7d2d","abstract_canon_sha256":"93cc2db8704400c3b4ce737931999a16a44221d4262cc7d35194113139ef2cd6"},"schema_version":"1.0"},"canonical_sha256":"490f547f56cbb948f719b6d73b5306eefa17f0eccbde3bb9bb254c656055ddd3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:44.329010Z","signature_b64":"eTPoz0HOMmgyR3SWzCF4akSJwhWNN3bIKhe/P6m54nVA25Jx4uBYhLOwy8JiKfaJF7F1r/ty4WBb0Nu+aOfSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"490f547f56cbb948f719b6d73b5306eefa17f0eccbde3bb9bb254c656055ddd3","last_reissued_at":"2026-07-05T07:57:44.328483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:44.328483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.03173","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":"2026-07-05T07:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81+FZXi/JMSd+4RYfBrbpJMp/pShGZKcHT1FbCGmnxKMk2q/z99qfuBVlu9zZ8godco6PT/1OwXAjHckbiMiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:31:12.847176Z"},"content_sha256":"ee8f54e0492e6610488a81ceec904fd9f37317c45f32bd5712600f52ff5ad28a","schema_version":"1.0","event_id":"sha256:ee8f54e0492e6610488a81ceec904fd9f37317c45f32bd5712600f52ff5ad28a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JEHVI72WZO4UR5YZW3LTWUYG53","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongxia Yang, Liyu Chen, Tao Sun, Yunzhe Tao, Zishun Yu","submitted_at":"2023-10-04T21:40:36Z","abstract_excerpt":"Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leveraged the power of reinforcement learning (RL) in conjunction with large language models (LLMs), significantly enhancing code generation capabilities. The application of RL focuses on directly optimizing for functional correctness, offering an advantage over conventional supervised methods. Despite policy-based RL methods dominating the literature on RL for program synthesis, the nature of program synthesis tasks hin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03173","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/2310.03173/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":"2026-07-05T07:57:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVD5Dt+7ho+m0dKnmz0077NeMZaXE+5iZgJZvN2cKzuN2oAQxjt2P8XMyPkbvXVBJQKFb5Tq7IjV60ZpUuS0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T18:31:12.847725Z"},"content_sha256":"302840302bd04d4a23ded176cfcceaf454d4e15d6a38e71db7f3d44c4158ca5f","schema_version":"1.0","event_id":"sha256:302840302bd04d4a23ded176cfcceaf454d4e15d6a38e71db7f3d44c4158ca5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEHVI72WZO4UR5YZW3LTWUYG53/bundle.json","state_url":"https://pith.science/pith/JEHVI72WZO4UR5YZW3LTWUYG53/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEHVI72WZO4UR5YZW3LTWUYG53/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":"2026-08-23T18:31:12Z","links":{"resolver":"https://pith.science/pith/JEHVI72WZO4UR5YZW3LTWUYG53","bundle":"https://pith.science/pith/JEHVI72WZO4UR5YZW3LTWUYG53/bundle.json","state":"https://pith.science/pith/JEHVI72WZO4UR5YZW3LTWUYG53/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEHVI72WZO4UR5YZW3LTWUYG53/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JEHVI72WZO4UR5YZW3LTWUYG53","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":"93cc2db8704400c3b4ce737931999a16a44221d4262cc7d35194113139ef2cd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T21:40:36Z","title_canon_sha256":"e5545daaf478ec9d22c8fe3abf300b68440069b4c68304a08e3ecbf56d1c7d2d"},"schema_version":"1.0","source":{"id":"2310.03173","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03173","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03173v2","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03173","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_12","alias_value":"JEHVI72WZO4U","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_16","alias_value":"JEHVI72WZO4UR5YZ","created_at":"2026-07-05T07:57:44Z"},{"alias_kind":"pith_short_8","alias_value":"JEHVI72W","created_at":"2026-07-05T07:57:44Z"}],"graph_snapshots":[{"event_id":"sha256:302840302bd04d4a23ded176cfcceaf454d4e15d6a38e71db7f3d44c4158ca5f","target":"graph","created_at":"2026-07-05T07:57:44Z","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/2310.03173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leveraged the power of reinforcement learning (RL) in conjunction with large language models (LLMs), significantly enhancing code generation capabilities. The application of RL focuses on directly optimizing for functional correctness, offering an advantage over conventional supervised methods. Despite policy-based RL methods dominating the literature on RL for program synthesis, the nature of program synthesis tasks hin","authors_text":"Hongxia Yang, Liyu Chen, Tao Sun, Yunzhe Tao, Zishun Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T21:40:36Z","title":"$\\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03173","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:ee8f54e0492e6610488a81ceec904fd9f37317c45f32bd5712600f52ff5ad28a","target":"record","created_at":"2026-07-05T07:57:44Z","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":"93cc2db8704400c3b4ce737931999a16a44221d4262cc7d35194113139ef2cd6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T21:40:36Z","title_canon_sha256":"e5545daaf478ec9d22c8fe3abf300b68440069b4c68304a08e3ecbf56d1c7d2d"},"schema_version":"1.0","source":{"id":"2310.03173","kind":"arxiv","version":2}},"canonical_sha256":"490f547f56cbb948f719b6d73b5306eefa17f0eccbde3bb9bb254c656055ddd3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"490f547f56cbb948f719b6d73b5306eefa17f0eccbde3bb9bb254c656055ddd3","first_computed_at":"2026-07-05T07:57:44.328483Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:44.328483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTPoz0HOMmgyR3SWzCF4akSJwhWNN3bIKhe/P6m54nVA25Jx4uBYhLOwy8JiKfaJF7F1r/ty4WBb0Nu+aOfSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:44.329010Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03173","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee8f54e0492e6610488a81ceec904fd9f37317c45f32bd5712600f52ff5ad28a","sha256:302840302bd04d4a23ded176cfcceaf454d4e15d6a38e71db7f3d44c4158ca5f"],"state_sha256":"ee0af84e2c24d562dd42db8d4df101e44c229e510bd505c0c0dc2faf7cc2501c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RbPzFZeb7/53n9KorkL8IpeCwmJw+JrMrLQDxgwrxC6ax5oDV92AOKnxtm3FUNmDoR6ao535IJ6wLWBohrP2AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T18:31:12.852887Z","bundle_sha256":"de1a156dd47aec74b4f7fc4efbeea0c631eb857e980672572d6a029a0d700419"}}