{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SB3HQIUMWF3DXYYETCC6DJCEGJ","short_pith_number":"pith:SB3HQIUM","canonical_record":{"source":{"id":"2502.01715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T16:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4bcd547b10a300a848d2791a5703ca9269af9065803c8660ddf673b5da304f1","abstract_canon_sha256":"96d97b176a2484445868f5da6895e5be11df915e971a0331bca07d87c6ac2020"},"schema_version":"1.0"},"canonical_sha256":"907678228cb1763be3049885e1a444327718160f923d90846d19a0e594766ad6","source":{"kind":"arxiv","id":"2502.01715","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01715","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01715v1","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01715","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"SB3HQIUMWF3D","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"SB3HQIUMWF3DXYYE","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"SB3HQIUM","created_at":"2026-07-05T10:09:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SB3HQIUMWF3DXYYETCC6DJCEGJ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01715","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T16:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b4bcd547b10a300a848d2791a5703ca9269af9065803c8660ddf673b5da304f1","abstract_canon_sha256":"96d97b176a2484445868f5da6895e5be11df915e971a0331bca07d87c6ac2020"},"schema_version":"1.0"},"canonical_sha256":"907678228cb1763be3049885e1a444327718160f923d90846d19a0e594766ad6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:18.166787Z","signature_b64":"7B+bu7D/2s0i21jYwBkqlygDQrqsiBepjAiTHOOaPcThm16PfgXx2umIWN9EQvPrZ35QoMjNemXr9zJJUh08Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"907678228cb1763be3049885e1a444327718160f923d90846d19a0e594766ad6","last_reissued_at":"2026-07-05T10:09:18.166336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:18.166336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01715","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":"2026-07-05T10:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"we/jNJhzSkkblUgB6A0Ai/6UeClIAlsAf7rSJidpncNMy4iEBn0DNY/nUmzdF+ZQVUT31wZeMf+exGJ95c1xBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:17:54.848685Z"},"content_sha256":"4bd36c1471afea6984a583e0f629d415530177b1eec26e7cb7014f67f43efb1f","schema_version":"1.0","event_id":"sha256:4bd36c1471afea6984a583e0f629d415530177b1eec26e7cb7014f67f43efb1f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SB3HQIUMWF3DXYYETCC6DJCEGJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Process-Supervised Reinforcement Learning for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hua Huang, Ting Zhang, Wenbin Jiang, Yufan Ye","submitted_at":"2025-02-03T16:22:06Z","abstract_excerpt":"Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has shown great promise in handling multi-step reasoning tasks, its effectiveness in code generation remains largely underexplored and underjustified. The primary obstacle stems from the resource-intensive nature of constructing high-quality process-supervised data, which demands substantial human expertise and computational resources. In response to this challenge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01715","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/2502.01715/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":"2026-07-05T10:09:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVbnDkIIEeWR9IGPynG7q6MnYEe2rJCARmpKeHgJtFBFSlLe2kc+d62iOeRXwAaJd6O9tiYCnSnrMtYuVv4iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:17:54.849191Z"},"content_sha256":"01fde266e12eaeb13858d8d1cec7c4869b30997af0bbfc0f95bcf061ada5f456","schema_version":"1.0","event_id":"sha256:01fde266e12eaeb13858d8d1cec7c4869b30997af0bbfc0f95bcf061ada5f456"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ/bundle.json","state_url":"https://pith.science/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ/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":"2026-08-06T06:17:54Z","links":{"resolver":"https://pith.science/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ","bundle":"https://pith.science/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ/bundle.json","state":"https://pith.science/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SB3HQIUMWF3DXYYETCC6DJCEGJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SB3HQIUMWF3DXYYETCC6DJCEGJ","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":"96d97b176a2484445868f5da6895e5be11df915e971a0331bca07d87c6ac2020","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T16:22:06Z","title_canon_sha256":"b4bcd547b10a300a848d2791a5703ca9269af9065803c8660ddf673b5da304f1"},"schema_version":"1.0","source":{"id":"2502.01715","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01715","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01715v1","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01715","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"SB3HQIUMWF3D","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"SB3HQIUMWF3DXYYE","created_at":"2026-07-05T10:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"SB3HQIUM","created_at":"2026-07-05T10:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:01fde266e12eaeb13858d8d1cec7c4869b30997af0bbfc0f95bcf061ada5f456","target":"graph","created_at":"2026-07-05T10:09:18Z","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/2502.01715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing reinforcement learning strategies based on outcome supervision have proven effective in enhancing the performance of large language models(LLMs) for code generation. While reinforcement learning based on process supervision has shown great promise in handling multi-step reasoning tasks, its effectiveness in code generation remains largely underexplored and underjustified. The primary obstacle stems from the resource-intensive nature of constructing high-quality process-supervised data, which demands substantial human expertise and computational resources. In response to this challenge","authors_text":"Hua Huang, Ting Zhang, Wenbin Jiang, Yufan Ye","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T16:22:06Z","title":"Process-Supervised Reinforcement Learning for Code Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01715","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":"sha256:4bd36c1471afea6984a583e0f629d415530177b1eec26e7cb7014f67f43efb1f","target":"record","created_at":"2026-07-05T10:09:18Z","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":"96d97b176a2484445868f5da6895e5be11df915e971a0331bca07d87c6ac2020","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-03T16:22:06Z","title_canon_sha256":"b4bcd547b10a300a848d2791a5703ca9269af9065803c8660ddf673b5da304f1"},"schema_version":"1.0","source":{"id":"2502.01715","kind":"arxiv","version":1}},"canonical_sha256":"907678228cb1763be3049885e1a444327718160f923d90846d19a0e594766ad6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"907678228cb1763be3049885e1a444327718160f923d90846d19a0e594766ad6","first_computed_at":"2026-07-05T10:09:18.166336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:18.166336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7B+bu7D/2s0i21jYwBkqlygDQrqsiBepjAiTHOOaPcThm16PfgXx2umIWN9EQvPrZ35QoMjNemXr9zJJUh08Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:18.166787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01715","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bd36c1471afea6984a583e0f629d415530177b1eec26e7cb7014f67f43efb1f","sha256:01fde266e12eaeb13858d8d1cec7c4869b30997af0bbfc0f95bcf061ada5f456"],"state_sha256":"77a24311bf6f39f8c63878c76186c5621a58224c03d024200dbea888857e5b6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kpmm2ODO++8B8ZEhuXoK8TAWsVdcrnTYgpPC0L7t5KFI34dHakbUMkhyLTpYnD71EObyOg6BC+GsK3FtGSFeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:17:54.853835Z","bundle_sha256":"5c97210212e67bd47491803f06f2c89487bbce1bf606fe4d7cc90c7cc68e2304"}}