{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6U3ZQXKNDFSVWQUPU2TIPTPMNT","short_pith_number":"pith:6U3ZQXKN","canonical_record":{"source":{"id":"2605.20696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T04:49:13Z","cross_cats_sorted":[],"title_canon_sha256":"e30525dbd5448195b85e24a123220a721993728153fac6b2000caeb53c19bbe5","abstract_canon_sha256":"2d24c33cc2d3103da92976009350d66dc4e05244a524d1f2845e90291e4dcd64"},"schema_version":"1.0"},"canonical_sha256":"f537985d4d19655b428fa6a687cdec6cfe69bde77ee824f9d3b8838341ba92aa","source":{"kind":"arxiv","id":"2605.20696","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20696","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20696v1","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20696","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"6U3ZQXKNDFSV","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"6U3ZQXKNDFSVWQUP","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"6U3ZQXKN","created_at":"2026-05-21T01:04:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6U3ZQXKNDFSVWQUPU2TIPTPMNT","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T04:49:13Z","cross_cats_sorted":[],"title_canon_sha256":"e30525dbd5448195b85e24a123220a721993728153fac6b2000caeb53c19bbe5","abstract_canon_sha256":"2d24c33cc2d3103da92976009350d66dc4e05244a524d1f2845e90291e4dcd64"},"schema_version":"1.0"},"canonical_sha256":"f537985d4d19655b428fa6a687cdec6cfe69bde77ee824f9d3b8838341ba92aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:49.640171Z","signature_b64":"QJh9TdpCb589iuNj2KNQ3EkIauOjd6FAdoRFSdO/mP3xQJVG1iurGVcY2bxK/9yjLH0tOcNA+Uw/gjWKlwthCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f537985d4d19655b428fa6a687cdec6cfe69bde77ee824f9d3b8838341ba92aa","last_reissued_at":"2026-05-21T01:04:49.639276Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:49.639276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20696","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sh4j8TZbMgh/wnPpo7NJv9URzg+eTYLFpaSHlG+YNDwsPAvSmqRTp2Z92QGvFvtgarc2gkYqWLZeU7MyN/bXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T11:39:32.870197Z"},"content_sha256":"41e24f7c7af8ca5ad2f5a879172e90a49d890043bf4b84822d2bdd815b308cde","schema_version":"1.0","event_id":"sha256:41e24f7c7af8ca5ad2f5a879172e90a49d890043bf4b84822d2bdd815b308cde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6U3ZQXKNDFSVWQUPU2TIPTPMNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distributed Direct Preference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Zhanhong Jiang","submitted_at":"2026-05-20T04:49:13Z","abstract_excerpt":"Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly understood. Direct Preference Optimization (DPO) avoids explicit reward modeling but lacks convergence guarantees under federated and decentralized training, where communication constraints and non-IID preferences fundamentally alter optimization dynamics. We provide the first convergence and time-complexity analysis of DPO in distributed environments. Modeli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20696","kind":"arxiv","version":1},"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/2605.20696/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":"2026-05-21T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5JK7ILL2CCR/uOIM61X0cOET2Cynfhon2e7GiXQjH53jI4akN9syGnri2setg+elyeKnWNuFGU8qNRKrNo/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T11:39:32.870868Z"},"content_sha256":"1817841487764e1ba73561f6a3825d77c82694ea9ed87da9f72f942ad58d33b7","schema_version":"1.0","event_id":"sha256:1817841487764e1ba73561f6a3825d77c82694ea9ed87da9f72f942ad58d33b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT/bundle.json","state_url":"https://pith.science/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT/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":"2026-05-24T11:39:32Z","links":{"resolver":"https://pith.science/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT","bundle":"https://pith.science/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT/bundle.json","state":"https://pith.science/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U3ZQXKNDFSVWQUPU2TIPTPMNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6U3ZQXKNDFSVWQUPU2TIPTPMNT","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":"2d24c33cc2d3103da92976009350d66dc4e05244a524d1f2845e90291e4dcd64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T04:49:13Z","title_canon_sha256":"e30525dbd5448195b85e24a123220a721993728153fac6b2000caeb53c19bbe5"},"schema_version":"1.0","source":{"id":"2605.20696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20696","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20696v1","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20696","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"6U3ZQXKNDFSV","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"6U3ZQXKNDFSVWQUP","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"6U3ZQXKN","created_at":"2026-05-21T01:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:1817841487764e1ba73561f6a3825d77c82694ea9ed87da9f72f942ad58d33b7","target":"graph","created_at":"2026-05-21T01:04:49Z","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/2605.20696/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly understood. Direct Preference Optimization (DPO) avoids explicit reward modeling but lacks convergence guarantees under federated and decentralized training, where communication constraints and non-IID preferences fundamentally alter optimization dynamics. We provide the first convergence and time-complexity analysis of DPO in distributed environments. Modeli","authors_text":"Zhanhong Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T04:49:13Z","title":"Distributed Direct Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20696","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":"sha256:41e24f7c7af8ca5ad2f5a879172e90a49d890043bf4b84822d2bdd815b308cde","target":"record","created_at":"2026-05-21T01:04:49Z","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":"2d24c33cc2d3103da92976009350d66dc4e05244a524d1f2845e90291e4dcd64","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T04:49:13Z","title_canon_sha256":"e30525dbd5448195b85e24a123220a721993728153fac6b2000caeb53c19bbe5"},"schema_version":"1.0","source":{"id":"2605.20696","kind":"arxiv","version":1}},"canonical_sha256":"f537985d4d19655b428fa6a687cdec6cfe69bde77ee824f9d3b8838341ba92aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f537985d4d19655b428fa6a687cdec6cfe69bde77ee824f9d3b8838341ba92aa","first_computed_at":"2026-05-21T01:04:49.639276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:49.639276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QJh9TdpCb589iuNj2KNQ3EkIauOjd6FAdoRFSdO/mP3xQJVG1iurGVcY2bxK/9yjLH0tOcNA+Uw/gjWKlwthCw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:49.640171Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e24f7c7af8ca5ad2f5a879172e90a49d890043bf4b84822d2bdd815b308cde","sha256:1817841487764e1ba73561f6a3825d77c82694ea9ed87da9f72f942ad58d33b7"],"state_sha256":"dff1a8525700e694877baf2e3bed1947c9ca601b72a8ec5889ee4979a270eb48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mFlT2WfJPq8MFLkvit0jvZEx7kn+zFV7zW2czwAOSomm5qMZhNkt+rrgGnwSBnPKpgf4q1nvfVg/VkEw/4MDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T11:39:32.875367Z","bundle_sha256":"1e547709212a5d7f4fce6666860b4d333a99ec4c509ca0b3249f67aa8b01b70a"}}