{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XXUTTKOKLH75TEY6GZQ7K2XNEL","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":"29c8b5ae52e430eeacdbb4efa7233d628d56e4a687a7aab80e2c8b9cf01a0fb6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T13:05:49Z","title_canon_sha256":"44c53748bb192232ee2ca7590086e392a5ee49a2c0aef57e5ef1f660cce87866"},"schema_version":"1.0","source":{"id":"2605.28440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28440","created_at":"2026-05-28T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28440v1","created_at":"2026-05-28T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28440","created_at":"2026-05-28T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"XXUTTKOKLH75","created_at":"2026-05-28T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"XXUTTKOKLH75TEY6","created_at":"2026-05-28T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"XXUTTKOK","created_at":"2026-05-28T01:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:6996146a47becc5da08440e9f3b66fad7bf94ae620539a63cde0f778448cb0f9","target":"graph","created_at":"2026-05-28T01:05:18Z","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/2605.28440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loop. Recent theoretical analysis uncovers an asymmetric gradient behavior in DPO: the loss suppresses dispreferred responses substantially faster than it promotes preferred ones, causing the model to learn to avoid bad answers rather than to generate good ones. We propose AdaDPO, a Self-Adaptive variant of the DPO algorithm that introduces per-preference-pair, stop-gradient-based coefficients derived directly from the policy model's generation pr","authors_text":"Madalina Ciobanu, Qingqing Mao, Ritankar Das, Shaolong Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T13:05:49Z","title":"AdaDPO: Self-Adaptive Direct Preference Optimization with Balanced Gradient Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28440","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:fd9f128b8606b618329c9d55440d13eb7e690f91e9bb3629d7f336402cb8d62d","target":"record","created_at":"2026-05-28T01:05:18Z","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":"29c8b5ae52e430eeacdbb4efa7233d628d56e4a687a7aab80e2c8b9cf01a0fb6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T13:05:49Z","title_canon_sha256":"44c53748bb192232ee2ca7590086e392a5ee49a2c0aef57e5ef1f660cce87866"},"schema_version":"1.0","source":{"id":"2605.28440","kind":"arxiv","version":1}},"canonical_sha256":"bde939a9ca59ffd9931e3661f56aed22facb3951fc63452a5eb4a16e9159e252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bde939a9ca59ffd9931e3661f56aed22facb3951fc63452a5eb4a16e9159e252","first_computed_at":"2026-05-28T01:05:18.194027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:18.194027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cb/084EQEweWBQ/rOC30j6yyZPqHmLBQlJQ/a65qDRGtZBwmnYE/VnaXJj4CEZ/d9xE0SvcXmCcm/dHvdwJgAQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:18.194447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd9f128b8606b618329c9d55440d13eb7e690f91e9bb3629d7f336402cb8d62d","sha256:6996146a47becc5da08440e9f3b66fad7bf94ae620539a63cde0f778448cb0f9"],"state_sha256":"c38cfd7cf62bd909776ecea78c016d7ec11ade098a65970332021fa60bbe00fb"}