{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NRK4ZO5D7HG4UBBR2CPTGSRBUG","short_pith_number":"pith:NRK4ZO5D","canonical_record":{"source":{"id":"2402.01391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-02T13:14:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d7ac05414d54ea4dea5bb4888e488ffc74fcbd02848ec9a0beff37a69ea5150f","abstract_canon_sha256":"8dcd4482672a89e54c21b776991cdca14ee4c7a044e9c12b35949da38728c640"},"schema_version":"1.0"},"canonical_sha256":"6c55ccbba3f9cdca0431d09f334a21a1bf6882fbbcbb4175d94dd2485d34f8ac","source":{"kind":"arxiv","id":"2402.01391","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01391","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01391v2","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01391","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"pith_short_12","alias_value":"NRK4ZO5D7HG4","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"pith_short_16","alias_value":"NRK4ZO5D7HG4UBBR","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"pith_short_8","alias_value":"NRK4ZO5D","created_at":"2026-07-05T07:41:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NRK4ZO5D7HG4UBBR2CPTGSRBUG","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-02T13:14:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d7ac05414d54ea4dea5bb4888e488ffc74fcbd02848ec9a0beff37a69ea5150f","abstract_canon_sha256":"8dcd4482672a89e54c21b776991cdca14ee4c7a044e9c12b35949da38728c640"},"schema_version":"1.0"},"canonical_sha256":"6c55ccbba3f9cdca0431d09f334a21a1bf6882fbbcbb4175d94dd2485d34f8ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:04.179424Z","signature_b64":"3imAUqjNP2AZmI8ElaP885nW9RgdUp3x/YJEcEew70GGm9pfAk0KVZLqnV5W/FqRYA0v0XDvbFBkV/nmez3xCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c55ccbba3f9cdca0431d09f334a21a1bf6882fbbcbb4175d94dd2485d34f8ac","last_reissued_at":"2026-07-05T07:41:04.178919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:04.178919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01391","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":"2026-07-05T07:41:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNILkrSTJzcsD1y1ZR9AUHNOrf4sDL5gGE51CZxCnxHBt9A9EAWSjDqy/lPvqrNSiy1Bh2jgWaV6EIJNACIWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:56:13.693533Z"},"content_sha256":"e076c76da33ad57915fad8ae209186930c05b5823d3102f4fe78382e0b187ea5","schema_version":"1.0","event_id":"sha256:e076c76da33ad57915fad8ae209186930c05b5823d3102f4fe78382e0b187ea5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NRK4ZO5D7HG4UBBR2CPTGSRBUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Caishuang Huang, Enyu Zhou, Haoxiang Jia, Junjie Shan, Limao Xiong, Qi Zhang, Rui Zheng, Shihan Dou, Tao Gui, Tao Ji, Wei Shen, Xiaoran Fan, Xiao Wang, Xuanjing Huang, Yan Liu, Yuhao Zhou, Zhiheng Xi","submitted_at":"2024-02-02T13:14:31Z","abstract_excerpt":"The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code generation quality. However, the lengthy code generated by LLMs in response to complex human requirements makes RL exploration a challenge. Also, since the unit tests may not cover the complicated code, optimizing LLMs by using these unexecuted code snippets is ineffective. To tackle these challenges, we introduce StepCoder, a novel RL framework for code genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01391","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/2402.01391/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":"2026-07-05T07:41:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ws0vmTakRd5Eeon54GhMfXm9+wcTlLCkVFPX1fpoHrS6p3n7gvorSHbph9dhJRX9GOrJlePW5LQaUJRHg3cDDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:56:13.693943Z"},"content_sha256":"487f1b7123004e5b194a2d97c1a02b53cf2806a9974bd04daa6261b4fccd6fe0","schema_version":"1.0","event_id":"sha256:487f1b7123004e5b194a2d97c1a02b53cf2806a9974bd04daa6261b4fccd6fe0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG/bundle.json","state_url":"https://pith.science/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG/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":"2026-08-03T15:56:13Z","links":{"resolver":"https://pith.science/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG","bundle":"https://pith.science/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG/bundle.json","state":"https://pith.science/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NRK4ZO5D7HG4UBBR2CPTGSRBUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NRK4ZO5D7HG4UBBR2CPTGSRBUG","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":"8dcd4482672a89e54c21b776991cdca14ee4c7a044e9c12b35949da38728c640","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-02T13:14:31Z","title_canon_sha256":"d7ac05414d54ea4dea5bb4888e488ffc74fcbd02848ec9a0beff37a69ea5150f"},"schema_version":"1.0","source":{"id":"2402.01391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01391","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01391v2","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01391","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"pith_short_12","alias_value":"NRK4ZO5D7HG4","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"pith_short_16","alias_value":"NRK4ZO5D7HG4UBBR","created_at":"2026-07-05T07:41:04Z"},{"alias_kind":"pith_short_8","alias_value":"NRK4ZO5D","created_at":"2026-07-05T07:41:04Z"}],"graph_snapshots":[{"event_id":"sha256:487f1b7123004e5b194a2d97c1a02b53cf2806a9974bd04daa6261b4fccd6fe0","target":"graph","created_at":"2026-07-05T07:41:04Z","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/2402.01391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of large language models (LLMs) has significantly propelled the field of code generation. Previous work integrated reinforcement learning (RL) with compiler feedback for exploring the output space of LLMs to enhance code generation quality. However, the lengthy code generated by LLMs in response to complex human requirements makes RL exploration a challenge. Also, since the unit tests may not cover the complicated code, optimizing LLMs by using these unexecuted code snippets is ineffective. To tackle these challenges, we introduce StepCoder, a novel RL framework for code genera","authors_text":"Caishuang Huang, Enyu Zhou, Haoxiang Jia, Junjie Shan, Limao Xiong, Qi Zhang, Rui Zheng, Shihan Dou, Tao Gui, Tao Ji, Wei Shen, Xiaoran Fan, Xiao Wang, Xuanjing Huang, Yan Liu, Yuhao Zhou, Zhiheng Xi","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-02T13:14:31Z","title":"StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01391","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:e076c76da33ad57915fad8ae209186930c05b5823d3102f4fe78382e0b187ea5","target":"record","created_at":"2026-07-05T07:41:04Z","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":"8dcd4482672a89e54c21b776991cdca14ee4c7a044e9c12b35949da38728c640","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-02T13:14:31Z","title_canon_sha256":"d7ac05414d54ea4dea5bb4888e488ffc74fcbd02848ec9a0beff37a69ea5150f"},"schema_version":"1.0","source":{"id":"2402.01391","kind":"arxiv","version":2}},"canonical_sha256":"6c55ccbba3f9cdca0431d09f334a21a1bf6882fbbcbb4175d94dd2485d34f8ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c55ccbba3f9cdca0431d09f334a21a1bf6882fbbcbb4175d94dd2485d34f8ac","first_computed_at":"2026-07-05T07:41:04.178919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:04.178919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3imAUqjNP2AZmI8ElaP885nW9RgdUp3x/YJEcEew70GGm9pfAk0KVZLqnV5W/FqRYA0v0XDvbFBkV/nmez3xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:04.179424Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e076c76da33ad57915fad8ae209186930c05b5823d3102f4fe78382e0b187ea5","sha256:487f1b7123004e5b194a2d97c1a02b53cf2806a9974bd04daa6261b4fccd6fe0"],"state_sha256":"d4d167b1e4d3b755191651092402dfd5ca5bb88ed920dd23a69e6ab5a37f1225"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJODKzwMWhqcKouh+b/iPoozm5Nh5kvW3TOqKx3ZqzEf5GfAunuRPa6vWeCGILIGQDQwJnqc8xpvDIqXQ4dnAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:56:13.696580Z","bundle_sha256":"47aff9e102534327cdff9adfeaa13b7223844403cdf15ce6a67fcbde115b1e0e"}}