{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ROTOHUFPYB2APP6SROBSWJI35N","short_pith_number":"pith:ROTOHUFP","canonical_record":{"source":{"id":"2406.10305","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-14T03:39:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"11d3c8d24dd2b65c8256125c6cf014bf9cb185d0b3ec51887c6eeb63f44b45e5","abstract_canon_sha256":"e29635f5d315749aa898f50c233c5fff0e49d0e7f3a4c0f128613f9c766908be"},"schema_version":"1.0"},"canonical_sha256":"8ba6e3d0afc07407bfd28b832b251beb68b52dba2f92175bc533e34445df9256","source":{"kind":"arxiv","id":"2406.10305","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10305","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10305v2","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10305","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"ROTOHUFPYB2A","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"pith_short_16","alias_value":"ROTOHUFPYB2APP6S","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"pith_short_8","alias_value":"ROTOHUFP","created_at":"2026-07-05T09:50:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ROTOHUFPYB2APP6SROBSWJI35N","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10305","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-14T03:39:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"11d3c8d24dd2b65c8256125c6cf014bf9cb185d0b3ec51887c6eeb63f44b45e5","abstract_canon_sha256":"e29635f5d315749aa898f50c233c5fff0e49d0e7f3a4c0f128613f9c766908be"},"schema_version":"1.0"},"canonical_sha256":"8ba6e3d0afc07407bfd28b832b251beb68b52dba2f92175bc533e34445df9256","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:02.984126Z","signature_b64":"BRoesjacI+A20nMpdVbqbJUaiRiH2XzzNFUreGdlbHIzAnPKuDMeH9Y/ORqqZ5xqsGFIv3tBka2ca8g0K9ZWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba6e3d0afc07407bfd28b832b251beb68b52dba2f92175bc533e34445df9256","last_reissued_at":"2026-07-05T09:50:02.983610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:02.983610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10305","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":"2026-07-05T09:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v9zOz1gt0Fd+QXzFrJWOXk0AZjML7s2BRlKuIpuILvO/lCssTuqqDB3BpdLwA/r2s6VvIG3vP+oyUT0iIHKAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:06:15.166217Z"},"content_sha256":"d8ac52451819e2e75efe4e2248137e9052e6b8195c300848e76d0aacbee97c3f","schema_version":"1.0","event_id":"sha256:d8ac52451819e2e75efe4e2248137e9052e6b8195c300848e76d0aacbee97c3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ROTOHUFPYB2APP6SROBSWJI35N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Jie Chen, Liang Xiang, Xintian Han, Xun Zhou, Yu Ma","submitted_at":"2024-06-14T03:39:01Z","abstract_excerpt":"Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a two-stage training paradigm is implemented to obtain a Code LLM, namely the pretraining and the fine-tuning. Within the fine-tuning, supervised fine-tuning (SFT), and reinforcement learning (RL) are often used to improve the model's zero-shot ability. A large number of work has been conducted to improve the model's performance on code-related benchmarks wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10305","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/2406.10305/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":"2026-07-05T09:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLMC7jQnczb9bEQKgfHQaFqZCM+yaDAKvU5xtX1pvdqXaqfnFZWhj7P+UZvHiLHNUAIZqqXj+qc/hTh6VqwuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T00:06:15.167132Z"},"content_sha256":"b5cacc86d7cb8fb16b0211a5eb1a99d16bb81eb7fc442acce52ffb4213c85e5d","schema_version":"1.0","event_id":"sha256:b5cacc86d7cb8fb16b0211a5eb1a99d16bb81eb7fc442acce52ffb4213c85e5d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROTOHUFPYB2APP6SROBSWJI35N/bundle.json","state_url":"https://pith.science/pith/ROTOHUFPYB2APP6SROBSWJI35N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROTOHUFPYB2APP6SROBSWJI35N/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":"2026-08-11T00:06:15Z","links":{"resolver":"https://pith.science/pith/ROTOHUFPYB2APP6SROBSWJI35N","bundle":"https://pith.science/pith/ROTOHUFPYB2APP6SROBSWJI35N/bundle.json","state":"https://pith.science/pith/ROTOHUFPYB2APP6SROBSWJI35N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROTOHUFPYB2APP6SROBSWJI35N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ROTOHUFPYB2APP6SROBSWJI35N","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":"e29635f5d315749aa898f50c233c5fff0e49d0e7f3a4c0f128613f9c766908be","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-14T03:39:01Z","title_canon_sha256":"11d3c8d24dd2b65c8256125c6cf014bf9cb185d0b3ec51887c6eeb63f44b45e5"},"schema_version":"1.0","source":{"id":"2406.10305","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10305","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10305v2","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10305","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"ROTOHUFPYB2A","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"pith_short_16","alias_value":"ROTOHUFPYB2APP6S","created_at":"2026-07-05T09:50:02Z"},{"alias_kind":"pith_short_8","alias_value":"ROTOHUFP","created_at":"2026-07-05T09:50:02Z"}],"graph_snapshots":[{"event_id":"sha256:b5cacc86d7cb8fb16b0211a5eb1a99d16bb81eb7fc442acce52ffb4213c85e5d","target":"graph","created_at":"2026-07-05T09:50:02Z","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/2406.10305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic code generation has been a longstanding research topic. With the advancement of general-purpose large language models (LLMs), the ability to code stands out as one important measure to the model's reasoning performance. Usually, a two-stage training paradigm is implemented to obtain a Code LLM, namely the pretraining and the fine-tuning. Within the fine-tuning, supervised fine-tuning (SFT), and reinforcement learning (RL) are often used to improve the model's zero-shot ability. A large number of work has been conducted to improve the model's performance on code-related benchmarks wit","authors_text":"Jie Chen, Liang Xiang, Xintian Han, Xun Zhou, Yu Ma","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-14T03:39:01Z","title":"Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10305","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:d8ac52451819e2e75efe4e2248137e9052e6b8195c300848e76d0aacbee97c3f","target":"record","created_at":"2026-07-05T09:50:02Z","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":"e29635f5d315749aa898f50c233c5fff0e49d0e7f3a4c0f128613f9c766908be","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-14T03:39:01Z","title_canon_sha256":"11d3c8d24dd2b65c8256125c6cf014bf9cb185d0b3ec51887c6eeb63f44b45e5"},"schema_version":"1.0","source":{"id":"2406.10305","kind":"arxiv","version":2}},"canonical_sha256":"8ba6e3d0afc07407bfd28b832b251beb68b52dba2f92175bc533e34445df9256","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ba6e3d0afc07407bfd28b832b251beb68b52dba2f92175bc533e34445df9256","first_computed_at":"2026-07-05T09:50:02.983610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:02.983610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRoesjacI+A20nMpdVbqbJUaiRiH2XzzNFUreGdlbHIzAnPKuDMeH9Y/ORqqZ5xqsGFIv3tBka2ca8g0K9ZWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:02.984126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10305","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8ac52451819e2e75efe4e2248137e9052e6b8195c300848e76d0aacbee97c3f","sha256:b5cacc86d7cb8fb16b0211a5eb1a99d16bb81eb7fc442acce52ffb4213c85e5d"],"state_sha256":"2d3def7c55c30d4fa377ad372863f217587e11aee6dda29b98c45eefdc2c6d0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZynMfSizoPnTnKUOcHPxJSCi+VG9M2KXNCKO9Mkv72GmOgCxT6KlGyFtqVbWqdOF1S5sfOdo1/CQBE6+5jOQAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T00:06:15.173749Z","bundle_sha256":"df67b49bf3e43963394d71a8ee1c9757237dfe462b16647eedd931c5176a99f7"}}