{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZWYRTGB2M3WVQQTYH4ZNWB4CSY","short_pith_number":"pith:ZWYRTGB2","schema_version":"1.0","canonical_sha256":"cdb119983a66ed5842783f32db07829638f57da58f53bf5b83ba7c726aa55ebd","source":{"kind":"arxiv","id":"2010.02164","version":3},"attestation_state":"computed","paper":{"title":"A Streaming Approach For Efficient Batched Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG","cs.PF"],"primary_cat":"cs.CL","authors_text":"Dan Klein, John DeNero, Kevin Yang, Violet Yao","submitted_at":"2020-10-05T17:13:34Z","abstract_excerpt":"We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically \"refills\" the batch before proceeding with a selected subset of candidates. We apply our method to variable-width beam search on a state-of-the-art machine translation model. Our method decreases runtime by up to 71% compared to a fixed-width beam search baseline and 17% compared to a variable-width baseline, while matching baselines' BLEU. Finally, experiments show that our method can "},"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":"2010.02164","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-05T17:13:34Z","cross_cats_sorted":["cs.AI","cs.DC","cs.LG","cs.PF"],"title_canon_sha256":"1c23b61b80d78e7d29bbd4dca34d758fadb929a7ff62ea46d378de3c03202cf5","abstract_canon_sha256":"28e7d74a1d0ccad6ac2b7b9f104d505969788391c9597f948ad9cb8cb4cafcfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:44.403549Z","signature_b64":"9XxQBfjttmjjZuqIm2eAoU3zVn3io64D/7dh8Xc5/RxJU4TmR/DL88xbpl6dPru3M0swcPvQ7uyHe03qvyAjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb119983a66ed5842783f32db07829638f57da58f53bf5b83ba7c726aa55ebd","last_reissued_at":"2026-07-05T03:05:44.403042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:44.403042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Streaming Approach For Efficient Batched Beam Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC","cs.LG","cs.PF"],"primary_cat":"cs.CL","authors_text":"Dan Klein, John DeNero, Kevin Yang, Violet Yao","submitted_at":"2020-10-05T17:13:34Z","abstract_excerpt":"We propose an efficient batching strategy for variable-length decoding on GPU architectures. During decoding, when candidates terminate or are pruned according to heuristics, our streaming approach periodically \"refills\" the batch before proceeding with a selected subset of candidates. We apply our method to variable-width beam search on a state-of-the-art machine translation model. Our method decreases runtime by up to 71% compared to a fixed-width beam search baseline and 17% compared to a variable-width baseline, while matching baselines' BLEU. Finally, experiments show that our method can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02164","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/2010.02164/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":"2010.02164","created_at":"2026-07-05T03:05:44.403113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.02164v3","created_at":"2026-07-05T03:05:44.403113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02164","created_at":"2026-07-05T03:05:44.403113+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWYRTGB2M3WV","created_at":"2026-07-05T03:05:44.403113+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWYRTGB2M3WVQQTY","created_at":"2026-07-05T03:05:44.403113+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWYRTGB2","created_at":"2026-07-05T03:05:44.403113+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/ZWYRTGB2M3WVQQTYH4ZNWB4CSY","json":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY.json","graph_json":"https://pith.science/api/pith-number/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/graph.json","events_json":"https://pith.science/api/pith-number/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/events.json","paper":"https://pith.science/paper/ZWYRTGB2"},"agent_actions":{"view_html":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY","download_json":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY.json","view_paper":"https://pith.science/paper/ZWYRTGB2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.02164&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/action/storage_attestation","attest_author":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/action/author_attestation","sign_citation":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/action/citation_signature","submit_replication":"https://pith.science/pith/ZWYRTGB2M3WVQQTYH4ZNWB4CSY/action/replication_record"}},"created_at":"2026-07-05T03:05:44.403113+00:00","updated_at":"2026-07-05T03:05:44.403113+00:00"}