{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4LVVOH5LIDI5F7JNF53VBONVI6","short_pith_number":"pith:4LVVOH5L","schema_version":"1.0","canonical_sha256":"e2eb571fab40d1d2fd2d2f7750b9b547ab9b7144a29f284824be0116f97a274b","source":{"kind":"arxiv","id":"2407.18698","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME","stat.ML"],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Esteban Garces Arias, Julian Rodemann, Matthias A{\\ss}enmacher, Meimingwei Li","submitted_at":"2024-07-26T12:23:54Z","abstract_excerpt":"Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus $p-$sampling, typical decoding, contrastive decoding, and contrastive search, have been proposed to address this problem, aiming to improve coherence, diversity, as well as resemblance to human-generated text. In this study, we introduce adaptive contrastive search, a novel decoding strategy extending contrastive search by incorporating an adaptive degeneration penalty,"},"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":"2407.18698","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T12:23:54Z","cross_cats_sorted":["cs.LG","stat.ME","stat.ML"],"title_canon_sha256":"a0be5aef75d82284593eb9ed3237249d992fca4dde72aefc166bf594f99188db","abstract_canon_sha256":"b96213d8a66eeb1dc94c11156dda9e7c22681ae83aaeba66bd45d0cea221f9cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:09.543755Z","signature_b64":"CVGDgjjfCIIUxAL7o6ZFYIGbh2x0vE7OfIsPywqNZQxN24nfYmteZ+FCpl3WZY+26cvT0ftr4J9VNdMVOKVmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2eb571fab40d1d2fd2d2f7750b9b547ab9b7144a29f284824be0116f97a274b","last_reissued_at":"2026-07-05T09:23:09.543264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:09.543264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Contrastive Search: Uncertainty-Guided Decoding for Open-Ended Text Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME","stat.ML"],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Esteban Garces Arias, Julian Rodemann, Matthias A{\\ss}enmacher, Meimingwei Li","submitted_at":"2024-07-26T12:23:54Z","abstract_excerpt":"Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus $p-$sampling, typical decoding, contrastive decoding, and contrastive search, have been proposed to address this problem, aiming to improve coherence, diversity, as well as resemblance to human-generated text. In this study, we introduce adaptive contrastive search, a novel decoding strategy extending contrastive search by incorporating an adaptive degeneration penalty,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18698","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.18698/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":"2407.18698","created_at":"2026-07-05T09:23:09.543334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.18698v2","created_at":"2026-07-05T09:23:09.543334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18698","created_at":"2026-07-05T09:23:09.543334+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LVVOH5LIDI5","created_at":"2026-07-05T09:23:09.543334+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LVVOH5LIDI5F7JN","created_at":"2026-07-05T09:23:09.543334+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LVVOH5L","created_at":"2026-07-05T09:23:09.543334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.02170","citing_title":"Avoidance Decoding for Diverse Multi-Branch Story Generation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6","json":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6.json","graph_json":"https://pith.science/api/pith-number/4LVVOH5LIDI5F7JNF53VBONVI6/graph.json","events_json":"https://pith.science/api/pith-number/4LVVOH5LIDI5F7JNF53VBONVI6/events.json","paper":"https://pith.science/paper/4LVVOH5L"},"agent_actions":{"view_html":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6","download_json":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6.json","view_paper":"https://pith.science/paper/4LVVOH5L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.18698&json=true","fetch_graph":"https://pith.science/api/pith-number/4LVVOH5LIDI5F7JNF53VBONVI6/graph.json","fetch_events":"https://pith.science/api/pith-number/4LVVOH5LIDI5F7JNF53VBONVI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6/action/storage_attestation","attest_author":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6/action/author_attestation","sign_citation":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6/action/citation_signature","submit_replication":"https://pith.science/pith/4LVVOH5LIDI5F7JNF53VBONVI6/action/replication_record"}},"created_at":"2026-07-05T09:23:09.543334+00:00","updated_at":"2026-07-05T09:23:09.543334+00:00"}