{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OZVBJXF33S7M3PJQCKZXHVR4BJ","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":"5a5a504d9de9c0748b4f379baabf7f0a61f6cef5119b53923daf45226a1ceadc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T09:36:13Z","title_canon_sha256":"6d79848fb7260f311774215e771db31f43185b6a1ba47ddb35413d326faf3c85"},"schema_version":"1.0","source":{"id":"2410.18585","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18585","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18585v1","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18585","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"OZVBJXF33S7M","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"OZVBJXF33S7M3PJQ","created_at":"2026-07-05T09:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"OZVBJXF3","created_at":"2026-07-05T09:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:20d750d13e8340e29d176840ff45cf1dad9fdb7dcc60c42f55ca4c0fdb7b872d","target":"graph","created_at":"2026-07-05T09:25:10Z","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/2410.18585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also represent the decision-making and logical reasoning capabilities of LLMs. However, current CodeLLMs mainly focus on pre-training and supervised fine-tuning scenarios, leaving the alignment stage, which is important for post-training LLMs, under-explored. This work first identifies that the commonly used PPO algorithm may be suboptimal for the alignment of C","authors_text":"Bofei Gao, Daoguang Zan, Jiaheng Liu, Jian Yang, Junyang Lin, Shanghaoran Quan, Tianyu Liu, Yibo Miao, Zhijie Deng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T09:36:13Z","title":"Aligning CodeLLMs with Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18585","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":"sha256:47abd6024425b8bebcdc73bb87bc3f67e3979bbba17cf3dd5fb3f65d74163513","target":"record","created_at":"2026-07-05T09:25:10Z","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":"5a5a504d9de9c0748b4f379baabf7f0a61f6cef5119b53923daf45226a1ceadc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-24T09:36:13Z","title_canon_sha256":"6d79848fb7260f311774215e771db31f43185b6a1ba47ddb35413d326faf3c85"},"schema_version":"1.0","source":{"id":"2410.18585","kind":"arxiv","version":1}},"canonical_sha256":"766a14dcbbdcbecdbd3012b373d63c0a642689c2f873bc54644cf84530c946a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"766a14dcbbdcbecdbd3012b373d63c0a642689c2f873bc54644cf84530c946a7","first_computed_at":"2026-07-05T09:25:10.754712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:25:10.754712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hpZldTNbJFgAOsKPqrdI/oMJzuLe+3dycgytUTzgdqIOwVgA2csS9ufo52EWOWVWvlmUEVvyL+/fZdZU4a1jAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:25:10.755222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18585","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47abd6024425b8bebcdc73bb87bc3f67e3979bbba17cf3dd5fb3f65d74163513","sha256:20d750d13e8340e29d176840ff45cf1dad9fdb7dcc60c42f55ca4c0fdb7b872d"],"state_sha256":"aecae79f500affe75e42cacd14dd7ba3445a6d6e8cc76965530d07f9865168d9"}