{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CMXX5V7OEHTLOFPE5Z54JN5TSL","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":"eee7e5151eee0f7e9467f8b825a826140da8b6e8fdc85b55ddcffe54293d1116","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T00:40:21Z","title_canon_sha256":"1d3d8c46518355407869ab680b699240b9c0e9ae4dc866d41110643b2e5ed435"},"schema_version":"1.0","source":{"id":"2602.04909","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04909","created_at":"2026-05-20T00:00:33Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04909v3","created_at":"2026-05-20T00:00:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04909","created_at":"2026-05-20T00:00:33Z"},{"alias_kind":"pith_short_12","alias_value":"CMXX5V7OEHTL","created_at":"2026-05-20T00:00:33Z"},{"alias_kind":"pith_short_16","alias_value":"CMXX5V7OEHTLOFPE","created_at":"2026-05-20T00:00:33Z"},{"alias_kind":"pith_short_8","alias_value":"CMXX5V7O","created_at":"2026-05-20T00:00:33Z"}],"graph_snapshots":[{"event_id":"sha256:15769bcd4d637b054f953eae529f7fe00e8d897a393f3392e0a8471db388d4af","target":"graph","created_at":"2026-05-20T00:00:33Z","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/2602.04909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) and related methods align large language models from pairwise preferences by regularizing updates against a fixed reference policy. As the policy drifts, a static reference, however, can become increasingly miscalibrated, leading to distributional mismatch and amplifying spurious preference signals under noisy supervision. Conversely, reference-free variants avoid mismatch but often suffer from unconstrained reward drift. We propose Geometric Anchor Preference Optimization (GAPO), which replaces the fixed reference with a dynamic, geometry-aware anchor: an ","authors_text":"Ji-Hoon Kim, Jongsuk Kim, Youngjae Cho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T00:40:21Z","title":"Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04909","kind":"arxiv","version":3},"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:c134e6458309ccc1420e352e22cc3b4f9bdb040224131d5f81286350b25dbb8f","target":"record","created_at":"2026-05-20T00:00:33Z","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":"eee7e5151eee0f7e9467f8b825a826140da8b6e8fdc85b55ddcffe54293d1116","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T00:40:21Z","title_canon_sha256":"1d3d8c46518355407869ab680b699240b9c0e9ae4dc866d41110643b2e5ed435"},"schema_version":"1.0","source":{"id":"2602.04909","kind":"arxiv","version":3}},"canonical_sha256":"132f7ed7ee21e6b715e4ee7bc4b7b392fb81b8e4246142d798392668faa38136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"132f7ed7ee21e6b715e4ee7bc4b7b392fb81b8e4246142d798392668faa38136","first_computed_at":"2026-05-20T00:00:33.564166Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:33.564166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PYkrYZUPGHlBMJ3sJijAPbaX8cGio+dsWlB6fmHZIsKjKbhdkI9WiGP1AK1LH87YiNma9j5/Od8mWo7AeqNLCw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:33.564762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04909","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c134e6458309ccc1420e352e22cc3b4f9bdb040224131d5f81286350b25dbb8f","sha256:15769bcd4d637b054f953eae529f7fe00e8d897a393f3392e0a8471db388d4af"],"state_sha256":"02cad4a91ed2f096a3c3c92fd02f245d754eb5e5c541ba7b5fb7b3d638094cd8"}