{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WXXIQPSFZ3SUHH25OHCEZAMIFQ","short_pith_number":"pith:WXXIQPSF","schema_version":"1.0","canonical_sha256":"b5ee883e45cee5439f5d71c44c81882c3dff6c9710bfae2ff6906e4a9cb503e6","source":{"kind":"arxiv","id":"2505.23078","version":1},"attestation_state":"computed","paper":{"title":"Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yuu Jinnai","submitted_at":"2025-05-29T04:34:04Z","abstract_excerpt":"Document-level text generation tasks are known to be more difficult than sentence-level text generation tasks as they require the understanding of longer context to generate high-quality texts. In this paper, we investigate the adaption of Minimum Bayes Risk (MBR) decoding for document-level text generation tasks. MBR decoding makes use of a utility function to estimate the output with the highest expected utility from a set of candidate outputs. Although MBR decoding is shown to be effective in a wide range of sentence-level text generation tasks, its performance on document-level text genera"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.23078","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T04:34:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d41e117a65d27df9873b1126371ce89167181da8fcfffd74a14fc322daf1950f","abstract_canon_sha256":"8930e6e9c561171922fde24d40a9128eae1adcb85b8c3b8b3aee299655c49e0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:55.075275Z","signature_b64":"6tNTubULTKG0ekIYvC39aGaJoDBvQdYpmtiQR9szv5a0yabKCMAWmnltkCHCSW58Z1u3MZXYzzPUzbTZNpk/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5ee883e45cee5439f5d71c44c81882c3dff6c9710bfae2ff6906e4a9cb503e6","last_reissued_at":"2026-07-05T11:11:55.074778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:55.074778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yuu Jinnai","submitted_at":"2025-05-29T04:34:04Z","abstract_excerpt":"Document-level text generation tasks are known to be more difficult than sentence-level text generation tasks as they require the understanding of longer context to generate high-quality texts. In this paper, we investigate the adaption of Minimum Bayes Risk (MBR) decoding for document-level text generation tasks. MBR decoding makes use of a utility function to estimate the output with the highest expected utility from a set of candidate outputs. Although MBR decoding is shown to be effective in a wide range of sentence-level text generation tasks, its performance on document-level text genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23078","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/2505.23078/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.23078","created_at":"2026-07-05T11:11:55.074838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23078v1","created_at":"2026-07-05T11:11:55.074838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23078","created_at":"2026-07-05T11:11:55.074838+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXXIQPSFZ3SU","created_at":"2026-07-05T11:11:55.074838+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXXIQPSFZ3SUHH25","created_at":"2026-07-05T11:11:55.074838+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXXIQPSF","created_at":"2026-07-05T11:11:55.074838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ","json":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ.json","graph_json":"https://pith.science/api/pith-number/WXXIQPSFZ3SUHH25OHCEZAMIFQ/graph.json","events_json":"https://pith.science/api/pith-number/WXXIQPSFZ3SUHH25OHCEZAMIFQ/events.json","paper":"https://pith.science/paper/WXXIQPSF"},"agent_actions":{"view_html":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ","download_json":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ.json","view_paper":"https://pith.science/paper/WXXIQPSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23078&json=true","fetch_graph":"https://pith.science/api/pith-number/WXXIQPSFZ3SUHH25OHCEZAMIFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WXXIQPSFZ3SUHH25OHCEZAMIFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ/action/storage_attestation","attest_author":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ/action/author_attestation","sign_citation":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ/action/citation_signature","submit_replication":"https://pith.science/pith/WXXIQPSFZ3SUHH25OHCEZAMIFQ/action/replication_record"}},"created_at":"2026-07-05T11:11:55.074838+00:00","updated_at":"2026-07-05T11:11:55.074838+00:00"}