{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2LRKU3IPYUJ5JG4ZZBBK5LPOQO","short_pith_number":"pith:2LRKU3IP","schema_version":"1.0","canonical_sha256":"d2e2aa6d0fc513d49b99c842aeadee83a9dd2f6bd8726d2effdd7d7816ef2a59","source":{"kind":"arxiv","id":"2402.04160","version":1},"attestation_state":"computed","paper":{"title":"Harnessing the Plug-and-Play Controller by Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wang, Lei Sha","submitted_at":"2024-02-06T17:18:25Z","abstract_excerpt":"Controllable text generation is a growing field within natural language generation (NLG) that focuses on producing text that meets specific constraints in real-world applications. Previous approaches, such as plug-and-play controllers (PPCs), aimed to steer the properties of generated text in a flexible manner. However, these methods often compromised the integrity of the language model's decoding process, resulting in less smooth text generation. Alternatively, other techniques utilized multiple attribute prompts to align the generated text with desired attributes, but this approach required "},"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":"2402.04160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T17:18:25Z","cross_cats_sorted":[],"title_canon_sha256":"9ed5a214a121f14ed00b89393aed4ffa7b01b6f3a16ce4ba62794c19f6641732","abstract_canon_sha256":"dcd7ff2a6e6914894d6b1bc47167b889e1c3ad9dc5d1ebd3ba02a2e1709a5f08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:04.112542Z","signature_b64":"MXydt+SwrrmOK7VqwmS0BGo41o45Us43+nh7XGrzB3CDC/LqcDm3FKtqKim9/8c0/hRqNT/THkp47kOR4pJXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2e2aa6d0fc513d49b99c842aeadee83a9dd2f6bd8726d2effdd7d7816ef2a59","last_reissued_at":"2026-07-05T07:42:04.112214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:04.112214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing the Plug-and-Play Controller by Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Wang, Lei Sha","submitted_at":"2024-02-06T17:18:25Z","abstract_excerpt":"Controllable text generation is a growing field within natural language generation (NLG) that focuses on producing text that meets specific constraints in real-world applications. Previous approaches, such as plug-and-play controllers (PPCs), aimed to steer the properties of generated text in a flexible manner. However, these methods often compromised the integrity of the language model's decoding process, resulting in less smooth text generation. Alternatively, other techniques utilized multiple attribute prompts to align the generated text with desired attributes, but this approach required "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04160","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/2402.04160/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":"2402.04160","created_at":"2026-07-05T07:42:04.112264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04160v1","created_at":"2026-07-05T07:42:04.112264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04160","created_at":"2026-07-05T07:42:04.112264+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LRKU3IPYUJ5","created_at":"2026-07-05T07:42:04.112264+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LRKU3IPYUJ5JG4Z","created_at":"2026-07-05T07:42:04.112264+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LRKU3IP","created_at":"2026-07-05T07:42:04.112264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24319","citing_title":"HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modification","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO","json":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO.json","graph_json":"https://pith.science/api/pith-number/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/graph.json","events_json":"https://pith.science/api/pith-number/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/events.json","paper":"https://pith.science/paper/2LRKU3IP"},"agent_actions":{"view_html":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO","download_json":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO.json","view_paper":"https://pith.science/paper/2LRKU3IP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04160&json=true","fetch_graph":"https://pith.science/api/pith-number/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/graph.json","fetch_events":"https://pith.science/api/pith-number/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/action/storage_attestation","attest_author":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/action/author_attestation","sign_citation":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/action/citation_signature","submit_replication":"https://pith.science/pith/2LRKU3IPYUJ5JG4ZZBBK5LPOQO/action/replication_record"}},"created_at":"2026-07-05T07:42:04.112264+00:00","updated_at":"2026-07-05T07:42:04.112264+00:00"}