{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:52UM4YYUGBKIWIZCWU6EPF7E5W","short_pith_number":"pith:52UM4YYU","schema_version":"1.0","canonical_sha256":"eea8ce631430548b2322b53c4797e4edb5498cc5ec189105e67aa3ee0ee557e5","source":{"kind":"arxiv","id":"1610.02424","version":2},"attestation_state":"computed","paper":{"title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ashwin K Vijayakumar, David Crandall, Dhruv Batra, Michael Cogswell, Qing Sun, Ramprasath R. Selvaraju, Stefan Lee","submitted_at":"2016-10-07T20:56:47Z","abstract_excerpt":"Neural sequence models are widely used to model time-series data. Equally ubiquitous is the usage of beam search (BS) as an approximate inference algorithm to decode output sequences from these models. BS explores the search space in a greedy left-right fashion retaining only the top-B candidates - resulting in sequences that differ only slightly from each other. Producing lists of nearly identical sequences is not only computationally wasteful but also typically fails to capture the inherent ambiguity of complex AI tasks. To overcome this problem, we propose Diverse Beam Search (DBS), an alte"},"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":"1610.02424","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-10-07T20:56:47Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"1dedb54d95df8a2ad98d96310892ccc3460aef26aef91a8e4d736c529425c19a","abstract_canon_sha256":"434448efa4aff710e9ffadec62142b38271656144687e750b6e103e316a741d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:45.918297Z","signature_b64":"JVqY7hO4Mm7DDAXCvnEVV+zEUZgKRL0O0ZiDWHxtpZ2R7EywLw/ntVC3wckeQPCLmBY+JkHIbnjiWbVox+gpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eea8ce631430548b2322b53c4797e4edb5498cc5ec189105e67aa3ee0ee557e5","last_reissued_at":"2026-05-18T00:02:45.917695Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:45.917695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Ashwin K Vijayakumar, David Crandall, Dhruv Batra, Michael Cogswell, Qing Sun, Ramprasath R. Selvaraju, Stefan Lee","submitted_at":"2016-10-07T20:56:47Z","abstract_excerpt":"Neural sequence models are widely used to model time-series data. Equally ubiquitous is the usage of beam search (BS) as an approximate inference algorithm to decode output sequences from these models. BS explores the search space in a greedy left-right fashion retaining only the top-B candidates - resulting in sequences that differ only slightly from each other. Producing lists of nearly identical sequences is not only computationally wasteful but also typically fails to capture the inherent ambiguity of complex AI tasks. To overcome this problem, we propose Diverse Beam Search (DBS), an alte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.02424","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":"1610.02424","created_at":"2026-05-18T00:02:45.917770+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.02424v2","created_at":"2026-05-18T00:02:45.917770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.02424","created_at":"2026-05-18T00:02:45.917770+00:00"},{"alias_kind":"pith_short_12","alias_value":"52UM4YYUGBKI","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"52UM4YYUGBKIWIZC","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"52UM4YYU","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2503.02574","citing_title":"LLM-Safety Evaluations Lack Robustness","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15635","citing_title":"Evaluating Chinese Ambiguity Understanding in Large Language Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2210.08933","citing_title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2602.10346","citing_title":"Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13050","citing_title":"Context Training with Active Information Seeking","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13050","citing_title":"Context Training with Active Information Seeking","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11258","citing_title":"Unlocking LLM Creativity in Science through Analogical Reasoning","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09781","citing_title":"Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09995","citing_title":"Annotations Mitigate Post-Training Mode Collapse","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":77,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22269","citing_title":"Semantic Error Correction and Decoding for Short Block Codes","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16453","citing_title":"Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20500","citing_title":"Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W","json":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W.json","graph_json":"https://pith.science/api/pith-number/52UM4YYUGBKIWIZCWU6EPF7E5W/graph.json","events_json":"https://pith.science/api/pith-number/52UM4YYUGBKIWIZCWU6EPF7E5W/events.json","paper":"https://pith.science/paper/52UM4YYU"},"agent_actions":{"view_html":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W","download_json":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W.json","view_paper":"https://pith.science/paper/52UM4YYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.02424&json=true","fetch_graph":"https://pith.science/api/pith-number/52UM4YYUGBKIWIZCWU6EPF7E5W/graph.json","fetch_events":"https://pith.science/api/pith-number/52UM4YYUGBKIWIZCWU6EPF7E5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W/action/storage_attestation","attest_author":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W/action/author_attestation","sign_citation":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W/action/citation_signature","submit_replication":"https://pith.science/pith/52UM4YYUGBKIWIZCWU6EPF7E5W/action/replication_record"}},"created_at":"2026-05-18T00:02:45.917770+00:00","updated_at":"2026-05-18T00:02:45.917770+00:00"}