{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S5LGJ7L3CXDFWGV4PKCFR5WAIK","short_pith_number":"pith:S5LGJ7L3","schema_version":"1.0","canonical_sha256":"975664fd7b15c65b1abc7a8458f6c0428934660026c7dc47e40221ce6a23b8fb","source":{"kind":"arxiv","id":"2109.11034","version":3},"attestation_state":"computed","paper":{"title":"Conditional Poisson Stochastic Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Amini, Clara Meister, Ryan Cotterell, Tim Vieira","submitted_at":"2021-09-22T20:49:16Z","abstract_excerpt":"Beam search is the default decoding strategy for many sequence generation tasks in NLP. The set of approximate K-best items returned by the algorithm is a useful summary of the distribution for many applications; however, the candidates typically exhibit high overlap and may give a highly biased estimate for expectations under our model. These problems can be addressed by instead using stochastic decoding strategies. In this work, we propose a new method for turning beam search into a stochastic process: Conditional Poisson stochastic beam search. Rather than taking the maximizing set at each "},"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":"2109.11034","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-22T20:49:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8be4634cc9640f2b8e454c6693387751b2b105d2eed0b5e8c29db10a86914f15","abstract_canon_sha256":"6914e1c2b1311dfc7872bb92b3181e56b06a020dd1917a228a1cd5f83bc1bdac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:14.175476Z","signature_b64":"hQnT0sasUTJa2+QEJiRcrZ23KztpwKlNPaohK/y9yxDGdaN8yDaB8KW0ztDwtbXa+EbolUqy+DXtdENAwjWCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"975664fd7b15c65b1abc7a8458f6c0428934660026c7dc47e40221ce6a23b8fb","last_reissued_at":"2026-07-05T05:47:14.175007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:14.175007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional Poisson Stochastic Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Afra Amini, Clara Meister, Ryan Cotterell, Tim Vieira","submitted_at":"2021-09-22T20:49:16Z","abstract_excerpt":"Beam search is the default decoding strategy for many sequence generation tasks in NLP. The set of approximate K-best items returned by the algorithm is a useful summary of the distribution for many applications; however, the candidates typically exhibit high overlap and may give a highly biased estimate for expectations under our model. These problems can be addressed by instead using stochastic decoding strategies. In this work, we propose a new method for turning beam search into a stochastic process: Conditional Poisson stochastic beam search. Rather than taking the maximizing set at each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.11034","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/2109.11034/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":"2109.11034","created_at":"2026-07-05T05:47:14.175060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.11034v3","created_at":"2026-07-05T05:47:14.175060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.11034","created_at":"2026-07-05T05:47:14.175060+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5LGJ7L3CXDF","created_at":"2026-07-05T05:47:14.175060+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5LGJ7L3CXDFWGV4","created_at":"2026-07-05T05:47:14.175060+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5LGJ7L3","created_at":"2026-07-05T05:47:14.175060+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/S5LGJ7L3CXDFWGV4PKCFR5WAIK","json":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK.json","graph_json":"https://pith.science/api/pith-number/S5LGJ7L3CXDFWGV4PKCFR5WAIK/graph.json","events_json":"https://pith.science/api/pith-number/S5LGJ7L3CXDFWGV4PKCFR5WAIK/events.json","paper":"https://pith.science/paper/S5LGJ7L3"},"agent_actions":{"view_html":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK","download_json":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK.json","view_paper":"https://pith.science/paper/S5LGJ7L3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.11034&json=true","fetch_graph":"https://pith.science/api/pith-number/S5LGJ7L3CXDFWGV4PKCFR5WAIK/graph.json","fetch_events":"https://pith.science/api/pith-number/S5LGJ7L3CXDFWGV4PKCFR5WAIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK/action/storage_attestation","attest_author":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK/action/author_attestation","sign_citation":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK/action/citation_signature","submit_replication":"https://pith.science/pith/S5LGJ7L3CXDFWGV4PKCFR5WAIK/action/replication_record"}},"created_at":"2026-07-05T05:47:14.175060+00:00","updated_at":"2026-07-05T05:47:14.175060+00:00"}