{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CMXX5V7OEHTLOFPE5Z54JN5TSL","short_pith_number":"pith:CMXX5V7O","canonical_record":{"source":{"id":"2602.04909","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T00:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d3d8c46518355407869ab680b699240b9c0e9ae4dc866d41110643b2e5ed435","abstract_canon_sha256":"eee7e5151eee0f7e9467f8b825a826140da8b6e8fdc85b55ddcffe54293d1116"},"schema_version":"1.0"},"canonical_sha256":"132f7ed7ee21e6b715e4ee7bc4b7b392fb81b8e4246142d798392668faa38136","source":{"kind":"arxiv","id":"2602.04909","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CMXX5V7OEHTLOFPE5Z54JN5TSL","target":"record","payload":{"canonical_record":{"source":{"id":"2602.04909","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T00:40:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d3d8c46518355407869ab680b699240b9c0e9ae4dc866d41110643b2e5ed435","abstract_canon_sha256":"eee7e5151eee0f7e9467f8b825a826140da8b6e8fdc85b55ddcffe54293d1116"},"schema_version":"1.0"},"canonical_sha256":"132f7ed7ee21e6b715e4ee7bc4b7b392fb81b8e4246142d798392668faa38136","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:33.564762Z","signature_b64":"PYkrYZUPGHlBMJ3sJijAPbaX8cGio+dsWlB6fmHZIsKjKbhdkI9WiGP1AK1LH87YiNma9j5/Od8mWo7AeqNLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"132f7ed7ee21e6b715e4ee7bc4b7b392fb81b8e4246142d798392668faa38136","last_reissued_at":"2026-05-20T00:00:33.564166Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:33.564166Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.04909","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"msED6o4q/h/jvtpI4rsWNN2WnQFGYWrWbpdnvy2M19TRHjKwZj/Eko1O8ws5rQcNvOJ4YLZ1U4+vJ3KdJhpgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:13:11.281408Z"},"content_sha256":"c134e6458309ccc1420e352e22cc3b4f9bdb040224131d5f81286350b25dbb8f","schema_version":"1.0","event_id":"sha256:c134e6458309ccc1420e352e22cc3b4f9bdb040224131d5f81286350b25dbb8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CMXX5V7OEHTLOFPE5Z54JN5TSL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ji-Hoon Kim, Jongsuk Kim, Youngjae Cho","submitted_at":"2026-02-04T00:40:21Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04909","kind":"arxiv","version":3},"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/2602.04909/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":"2026-05-20T00:00:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"107+Cym46kvUxiazv9hFt9sVckryhQe1ZIAilZ6543VbJaDEEPGmqnbc6CgkeCmXSxshOwWXm0tMM8QJuz5mDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:13:11.281854Z"},"content_sha256":"15769bcd4d637b054f953eae529f7fe00e8d897a393f3392e0a8471db388d4af","schema_version":"1.0","event_id":"sha256:15769bcd4d637b054f953eae529f7fe00e8d897a393f3392e0a8471db388d4af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL/bundle.json","state_url":"https://pith.science/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL/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":"2026-05-27T22:13:11Z","links":{"resolver":"https://pith.science/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL","bundle":"https://pith.science/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL/bundle.json","state":"https://pith.science/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMXX5V7OEHTLOFPE5Z54JN5TSL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cX4IZFHQ1veuZtXUmzslZJfJp1jGt5Li6h3VT42kjDDGrwWIkB6a0PFXPqhLdky1MCBliD8lNcAyB6ZjC1c0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:13:11.284218Z","bundle_sha256":"ff39cb57bac2d0872e0d12acbdb3b9aadb47dc8a2f0fd398c00e7c5fce748d60"}}