{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KJFVD6GSRTBF2V2J4JIIEH5L5W","short_pith_number":"pith:KJFVD6GS","schema_version":"1.0","canonical_sha256":"524b51f8d28cc25d5749e250821fabed990a9dc9569edb45b0cb942fda76cc6b","source":{"kind":"arxiv","id":"1702.01806","version":2},"attestation_state":"computed","paper":{"title":"Beam Search Strategies for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Markus Freitag, Yaser Al-Onaizan","submitted_at":"2017-02-06T22:08:46Z","abstract_excerpt":"The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new translations that approximately maximize the trained conditional probability. The current beam search strategy generates the target sentence word by word from left-to- right while keeping a fixed amount of active candidates at each time step. First, this simple search is less adaptive as it also expands candidates whose scores are much worse than the current be"},"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":"1702.01806","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-06T22:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"bf80c1486460e59b91f42a17e1ebe2b9007dadece2143244957f8d981b1b4523","abstract_canon_sha256":"bff6db2a95ba8bc8ab3b807ba9791181d05bbaf8fbc79b2b0fb2d51b75bc7eca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:05.602430Z","signature_b64":"awS89g8qOcFWydUKCvRvRz2PHhlJHtxbFRtjNae0u71b6glR0psbUAfPqUK31DcKic/oAd1zkA8dJ97CbVPpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"524b51f8d28cc25d5749e250821fabed990a9dc9569edb45b0cb942fda76cc6b","last_reissued_at":"2026-05-17T23:58:05.601941Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:05.601941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beam Search Strategies for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Markus Freitag, Yaser Al-Onaizan","submitted_at":"2017-02-06T22:08:46Z","abstract_excerpt":"The basic concept in Neural Machine Translation (NMT) is to train a large Neural Network that maximizes the translation performance on a given parallel corpus. NMT is then using a simple left-to-right beam-search decoder to generate new translations that approximately maximize the trained conditional probability. The current beam search strategy generates the target sentence word by word from left-to- right while keeping a fixed amount of active candidates at each time step. First, this simple search is less adaptive as it also expands candidates whose scores are much worse than the current be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.01806","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1702.01806","created_at":"2026-05-17T23:58:05.602015+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.01806v2","created_at":"2026-05-17T23:58:05.602015+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.01806","created_at":"2026-05-17T23:58:05.602015+00:00"},{"alias_kind":"pith_short_12","alias_value":"KJFVD6GSRTBF","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KJFVD6GSRTBF2V2J","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KJFVD6GS","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2505.11737","citing_title":"TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08980","citing_title":"AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2508.02455","citing_title":"TreeRanker: Fast and Model-agnostic Ranking System for Code Suggestions in IDEs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2310.00754","citing_title":"Analyzing and Mitigating Object Hallucination in Large Vision-Language Models","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2403.07815","citing_title":"Chronos: Learning the Language of Time Series","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09492","citing_title":"APCD: Adaptive Path-Contrastive Decoding for Reliable Large Language Model Generation","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W","json":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W.json","graph_json":"https://pith.science/api/pith-number/KJFVD6GSRTBF2V2J4JIIEH5L5W/graph.json","events_json":"https://pith.science/api/pith-number/KJFVD6GSRTBF2V2J4JIIEH5L5W/events.json","paper":"https://pith.science/paper/KJFVD6GS"},"agent_actions":{"view_html":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W","download_json":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W.json","view_paper":"https://pith.science/paper/KJFVD6GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.01806&json=true","fetch_graph":"https://pith.science/api/pith-number/KJFVD6GSRTBF2V2J4JIIEH5L5W/graph.json","fetch_events":"https://pith.science/api/pith-number/KJFVD6GSRTBF2V2J4JIIEH5L5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W/action/storage_attestation","attest_author":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W/action/author_attestation","sign_citation":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W/action/citation_signature","submit_replication":"https://pith.science/pith/KJFVD6GSRTBF2V2J4JIIEH5L5W/action/replication_record"}},"created_at":"2026-05-17T23:58:05.602015+00:00","updated_at":"2026-05-17T23:58:05.602015+00:00"}