{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V67NSWBDXGIYCGTNUF4ITXQ7PE","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":"6bb0254893bb6ed8f45b6653d451359086a4c167b8ae3649b73951c5843fbda6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T18:53:45Z","title_canon_sha256":"99dd149ffb05d8038055edd5e89a53346171b4182a61d3d877b6c4e0d6f74fc7"},"schema_version":"1.0","source":{"id":"2606.10078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10078","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10078v1","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10078","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"pith_short_12","alias_value":"V67NSWBDXGIY","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"pith_short_16","alias_value":"V67NSWBDXGIYCGTN","created_at":"2026-06-10T00:08:48Z"},{"alias_kind":"pith_short_8","alias_value":"V67NSWBD","created_at":"2026-06-10T00:08:48Z"}],"graph_snapshots":[{"event_id":"sha256:d29ab0ca86debecfc3bc78261870224a83ac35703c94b573573e9cb5ee49b3df","target":"graph","created_at":"2026-06-10T00:08:48Z","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/2606.10078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences. In recommender systems, however, user feedback is rarely pairwise. For a given context, e.g., a user, a session, or a conversation, we typically observe set-wise preferences with multiple positive items, where every positive item should outrank every unobserved or explicitly negative item, with no prescribed order among the positives or the negatives themselves. A natural generalization is to use the Plackett-Luce (PL) reward model, which extends the","authors_text":"Aditya Sinha, Harald Steck, James McInerney, Jundong Li, Nathan Kallus, Yaochen Zhu, Yinhan He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T18:53:45Z","title":"Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10078","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":"sha256:43fcac6058ddcb43c1466f76eeebe6219026342749e6f9daf1eb4bd5dc845941","target":"record","created_at":"2026-06-10T00:08:48Z","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":"6bb0254893bb6ed8f45b6653d451359086a4c167b8ae3649b73951c5843fbda6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-08T18:53:45Z","title_canon_sha256":"99dd149ffb05d8038055edd5e89a53346171b4182a61d3d877b6c4e0d6f74fc7"},"schema_version":"1.0","source":{"id":"2606.10078","kind":"arxiv","version":1}},"canonical_sha256":"afbed95823b991811a6da17889de1f792a5b315f33516f996c8d3267482e54d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afbed95823b991811a6da17889de1f792a5b315f33516f996c8d3267482e54d9","first_computed_at":"2026-06-10T00:08:48.227327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:48.227327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0GNiPHgzC6KD81AllvlKS6ufntT6mf5uBelo84Nja4RO5rWZXR8IueiEyoq+6lTHTmFWbFRchVuzUnvPspyjDw==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:48.228222Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43fcac6058ddcb43c1466f76eeebe6219026342749e6f9daf1eb4bd5dc845941","sha256:d29ab0ca86debecfc3bc78261870224a83ac35703c94b573573e9cb5ee49b3df"],"state_sha256":"40430066a2e0dfc946e5e7227adc327eb74a7d015797564c66b0c9e3d53ab3e6"}