{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FMWYV2BB27UBY6YISBHNUDYCN2","short_pith_number":"pith:FMWYV2BB","canonical_record":{"source":{"id":"2410.17621","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T07:22:33Z","cross_cats_sorted":[],"title_canon_sha256":"2e767d610b98c4f2bba171a7a2ac1dce359df7605a0ef35a4ecb80834bf11490","abstract_canon_sha256":"e35af8ffb2fcad754c394ffbe7f40e628cefc7002ef3d7df1a9e475c6adf3efd"},"schema_version":"1.0"},"canonical_sha256":"2b2d8ae821d7e81c7b08904eda0f026ebccbde5cf4388d471c22a1b51ceaef85","source":{"kind":"arxiv","id":"2410.17621","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17621","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17621v2","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17621","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"FMWYV2BB27UB","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"FMWYV2BB27UBY6YI","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"FMWYV2BB","created_at":"2026-07-05T10:09:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FMWYV2BB27UBY6YISBHNUDYCN2","target":"record","payload":{"canonical_record":{"source":{"id":"2410.17621","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T07:22:33Z","cross_cats_sorted":[],"title_canon_sha256":"2e767d610b98c4f2bba171a7a2ac1dce359df7605a0ef35a4ecb80834bf11490","abstract_canon_sha256":"e35af8ffb2fcad754c394ffbe7f40e628cefc7002ef3d7df1a9e475c6adf3efd"},"schema_version":"1.0"},"canonical_sha256":"2b2d8ae821d7e81c7b08904eda0f026ebccbde5cf4388d471c22a1b51ceaef85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:11.046856Z","signature_b64":"X6YdsxEpDYGsbmV9OcWbbWiTq6AbCAvwb0uesUVTRW/lQYETKxb2Qsa8ZyKKfu1ChitTlf1spgE0+CV83aymCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b2d8ae821d7e81c7b08904eda0f026ebccbde5cf4388d471c22a1b51ceaef85","last_reissued_at":"2026-07-05T10:09:11.046414Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:11.046414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.17621","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":"2026-07-05T10:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GKNxit1iak3EyN1vgAmCsdzXT7g6hr1albKzWAO9o/kfR4nHscBa30UuNZjAwg4+KHgfKQg+5C7zIdM1VDJwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:46:34.791700Z"},"content_sha256":"c4fa9516616114c7e94311e9364e6f60ae915e40ce9011112cd8eb56a8439666","schema_version":"1.0","event_id":"sha256:c4fa9516616114c7e94311e9364e6f60ae915e40ce9011112cd8eb56a8439666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FMWYV2BB27UBY6YISBHNUDYCN2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Process Supervision-Guided Policy Optimization for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chen Dun, Guanlin Liu, Liang Huang, Lin Yan, Ning Dai, Renjie Zheng, Wenlei Shi, Xing Jin, Zheng Wu, Ziyun Wei","submitted_at":"2024-10-23T07:22:33Z","abstract_excerpt":"Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental improvements. When generated code fails all unit tests, no learning signal is received, hindering progress on complex tasks. To address this, we propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement and providing immediate guidance. We explore various strategies for traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17621","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/2410.17621/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":"2026-07-05T10:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHlazo46yJrchuyVDOGwtb08+Au/0BDaLNtVgXD/3lGnKR8A76KtKIgXtg0ESL0hlSU/Am41K5jPvhR1Q5YXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:46:34.792607Z"},"content_sha256":"307f7cd4e8d824386c542d2c624ad532b221a369f274612bf0c9410cd9c67d74","schema_version":"1.0","event_id":"sha256:307f7cd4e8d824386c542d2c624ad532b221a369f274612bf0c9410cd9c67d74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMWYV2BB27UBY6YISBHNUDYCN2/bundle.json","state_url":"https://pith.science/pith/FMWYV2BB27UBY6YISBHNUDYCN2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMWYV2BB27UBY6YISBHNUDYCN2/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":"2026-08-09T00:46:34Z","links":{"resolver":"https://pith.science/pith/FMWYV2BB27UBY6YISBHNUDYCN2","bundle":"https://pith.science/pith/FMWYV2BB27UBY6YISBHNUDYCN2/bundle.json","state":"https://pith.science/pith/FMWYV2BB27UBY6YISBHNUDYCN2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMWYV2BB27UBY6YISBHNUDYCN2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FMWYV2BB27UBY6YISBHNUDYCN2","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":"e35af8ffb2fcad754c394ffbe7f40e628cefc7002ef3d7df1a9e475c6adf3efd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T07:22:33Z","title_canon_sha256":"2e767d610b98c4f2bba171a7a2ac1dce359df7605a0ef35a4ecb80834bf11490"},"schema_version":"1.0","source":{"id":"2410.17621","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17621","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17621v2","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17621","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"FMWYV2BB27UB","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"FMWYV2BB27UBY6YI","created_at":"2026-07-05T10:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"FMWYV2BB","created_at":"2026-07-05T10:09:11Z"}],"graph_snapshots":[{"event_id":"sha256:307f7cd4e8d824386c542d2c624ad532b221a369f274612bf0c9410cd9c67d74","target":"graph","created_at":"2026-07-05T10:09:11Z","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/2410.17621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental improvements. When generated code fails all unit tests, no learning signal is received, hindering progress on complex tasks. To address this, we propose a Process Reward Model (PRM) that delivers dense, line-level feedback on code correctness during generation, mimicking human code refinement and providing immediate guidance. We explore various strategies for traini","authors_text":"Chen Dun, Guanlin Liu, Liang Huang, Lin Yan, Ning Dai, Renjie Zheng, Wenlei Shi, Xing Jin, Zheng Wu, Ziyun Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T07:22:33Z","title":"Process Supervision-Guided Policy Optimization for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17621","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:c4fa9516616114c7e94311e9364e6f60ae915e40ce9011112cd8eb56a8439666","target":"record","created_at":"2026-07-05T10:09:11Z","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":"e35af8ffb2fcad754c394ffbe7f40e628cefc7002ef3d7df1a9e475c6adf3efd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T07:22:33Z","title_canon_sha256":"2e767d610b98c4f2bba171a7a2ac1dce359df7605a0ef35a4ecb80834bf11490"},"schema_version":"1.0","source":{"id":"2410.17621","kind":"arxiv","version":2}},"canonical_sha256":"2b2d8ae821d7e81c7b08904eda0f026ebccbde5cf4388d471c22a1b51ceaef85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b2d8ae821d7e81c7b08904eda0f026ebccbde5cf4388d471c22a1b51ceaef85","first_computed_at":"2026-07-05T10:09:11.046414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:11.046414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X6YdsxEpDYGsbmV9OcWbbWiTq6AbCAvwb0uesUVTRW/lQYETKxb2Qsa8ZyKKfu1ChitTlf1spgE0+CV83aymCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:11.046856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17621","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4fa9516616114c7e94311e9364e6f60ae915e40ce9011112cd8eb56a8439666","sha256:307f7cd4e8d824386c542d2c624ad532b221a369f274612bf0c9410cd9c67d74"],"state_sha256":"71749080edeffac0d9115b32833af9fef034e0b22bcb22ab609562ca07064faa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxq7CkOxJ6qlXXuH49dqvYbjfqAjg+GXsC7LlQLskGNOrfrFFOLhvb6E/2HsolfHWKnlV3x8G1D74NPapzPbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:46:34.798339Z","bundle_sha256":"fd6e35724fb9cc468190e736f9b748cdbea831ac3f21742e4e4014292b5aebac"}}