{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3AK6WOGSP45MJJMSQD4PPMSRSP","short_pith_number":"pith:3AK6WOGS","schema_version":"1.0","canonical_sha256":"d815eb38d27f3ac4a59280f8f7b25193e72c15639c0b62396b27943d0a0a9bb3","source":{"kind":"arxiv","id":"2109.09707","version":1},"attestation_state":"computed","paper":{"title":"A Plug-and-Play Method for Controlled Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beni Egressy, Clara Meister, Damian Pascual, Roger Wattenhofer, Ryan Cotterell","submitted_at":"2021-09-20T17:27:03Z","abstract_excerpt":"Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling generation, e.g., to ensure specific words are included, either require additional models or fine-tuning, or work poorly when the task at hand is semantically unconstrained, e.g., story generation. In this work, we present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sente"},"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":"2109.09707","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:27:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5e58c2c479c8f59632d60d6ee6de0755fb08fcb479accc0639d81ebc0781dea0","abstract_canon_sha256":"210b746b843fae7cc0e12556ab2fc25af2a3603453c66114060bb004c85cf76a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:49.014460Z","signature_b64":"fWJSdbiR4PqWvps9SPKf/q1VDt7JLa0MYKXS6PewygYj8oVvwFu4ZbFIrxR+KFhwxA4k2ixQkPLE0VkLK9slCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d815eb38d27f3ac4a59280f8f7b25193e72c15639c0b62396b27943d0a0a9bb3","last_reissued_at":"2026-07-05T03:15:49.014022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:49.014022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Plug-and-Play Method for Controlled Text Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Beni Egressy, Clara Meister, Damian Pascual, Roger Wattenhofer, Ryan Cotterell","submitted_at":"2021-09-20T17:27:03Z","abstract_excerpt":"Large pre-trained language models have repeatedly shown their ability to produce fluent text. Yet even when starting from a prompt, generation can continue in many plausible directions. Current decoding methods with the goal of controlling generation, e.g., to ensure specific words are included, either require additional models or fine-tuning, or work poorly when the task at hand is semantically unconstrained, e.g., story generation. In this work, we present a plug-and-play decoding method for controlled language generation that is so simple and intuitive, it can be described in a single sente"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09707","kind":"arxiv","version":1},"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/2109.09707/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":"2109.09707","created_at":"2026-07-05T03:15:49.014083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09707v1","created_at":"2026-07-05T03:15:49.014083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09707","created_at":"2026-07-05T03:15:49.014083+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AK6WOGSP45M","created_at":"2026-07-05T03:15:49.014083+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AK6WOGSP45MJJMS","created_at":"2026-07-05T03:15:49.014083+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AK6WOGS","created_at":"2026-07-05T03:15:49.014083+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/3AK6WOGSP45MJJMSQD4PPMSRSP","json":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP.json","graph_json":"https://pith.science/api/pith-number/3AK6WOGSP45MJJMSQD4PPMSRSP/graph.json","events_json":"https://pith.science/api/pith-number/3AK6WOGSP45MJJMSQD4PPMSRSP/events.json","paper":"https://pith.science/paper/3AK6WOGS"},"agent_actions":{"view_html":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP","download_json":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP.json","view_paper":"https://pith.science/paper/3AK6WOGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09707&json=true","fetch_graph":"https://pith.science/api/pith-number/3AK6WOGSP45MJJMSQD4PPMSRSP/graph.json","fetch_events":"https://pith.science/api/pith-number/3AK6WOGSP45MJJMSQD4PPMSRSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP/action/storage_attestation","attest_author":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP/action/author_attestation","sign_citation":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP/action/citation_signature","submit_replication":"https://pith.science/pith/3AK6WOGSP45MJJMSQD4PPMSRSP/action/replication_record"}},"created_at":"2026-07-05T03:15:49.014083+00:00","updated_at":"2026-07-05T03:15:49.014083+00:00"}