{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PUU6HP4LPZHRK2UGWMVKDOEUUU","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":"efd16cc3d7e37561b3d29ab94858ea6869f53e561612b63d0c88207da27b7eb9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T11:07:35Z","title_canon_sha256":"15955c16a6f7f80c795f7a856c19e3e98da42c24bd83f485757e438877ac2e7e"},"schema_version":"1.0","source":{"id":"2503.08295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08295","created_at":"2026-07-05T10:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08295v2","created_at":"2026-07-05T10:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08295","created_at":"2026-07-05T10:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"PUU6HP4LPZHR","created_at":"2026-07-05T10:46:41Z"},{"alias_kind":"pith_short_16","alias_value":"PUU6HP4LPZHRK2UG","created_at":"2026-07-05T10:46:41Z"},{"alias_kind":"pith_short_8","alias_value":"PUU6HP4L","created_at":"2026-07-05T10:46:41Z"}],"graph_snapshots":[{"event_id":"sha256:129297f60a107cf383874e9298f7915098d6915138444825af67e39259f51b5e","target":"graph","created_at":"2026-07-05T10:46:41Z","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/2503.08295/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have achieved state-of-the-art performance across multiple domains, with recent advancements extending their applicability to discrete data. However, aligning discrete diffusion models with task-specific preferences remains challenging, particularly in scenarios where explicit reward functions are unavailable. In this work, we introduce Discrete Diffusion DPO (D2-DPO), the first adaptation of Direct Preference Optimization (DPO) to discrete diffusion models formulated as continuous-time Markov chains. Our approach derives a novel loss function that directly fine-tunes the gene","authors_text":"Davide Paglieri, Jude Wells, Tim Rockt\\\"aschel, Umberto Borso","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T11:07:35Z","title":"Preference-Based Alignment of Discrete Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08295","kind":"arxiv","version":2},"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:dde6d629c8229c8c60def4c53b830d4ab5facb3413b0510cdb3cf82e65346c91","target":"record","created_at":"2026-07-05T10:46:41Z","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":"efd16cc3d7e37561b3d29ab94858ea6869f53e561612b63d0c88207da27b7eb9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T11:07:35Z","title_canon_sha256":"15955c16a6f7f80c795f7a856c19e3e98da42c24bd83f485757e438877ac2e7e"},"schema_version":"1.0","source":{"id":"2503.08295","kind":"arxiv","version":2}},"canonical_sha256":"7d29e3bf8b7e4f156a86b32aa1b894a5334c1435ee5261a0091f05f6a797f93f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d29e3bf8b7e4f156a86b32aa1b894a5334c1435ee5261a0091f05f6a797f93f","first_computed_at":"2026-07-05T10:46:41.518668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:41.518668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gsi1PoZ6Sd171vtkyjqTokpEixBKuq3e92+PpdJUjguRLFjHwsvuTWNwHK+YlE+F1eIhVJ/bFq3XIMC35EJRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:41.519145Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dde6d629c8229c8c60def4c53b830d4ab5facb3413b0510cdb3cf82e65346c91","sha256:129297f60a107cf383874e9298f7915098d6915138444825af67e39259f51b5e"],"state_sha256":"c39b7d5441d60a1e322937375cc8ad63453ebc99a98bc43a2568c2fc38d34d67"}