{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C5U6V44JLOMSHFINQFOVESG6WY","short_pith_number":"pith:C5U6V44J","schema_version":"1.0","canonical_sha256":"1769eaf3895b9923950d815d5248deb633756bfe6045c5b1260996d4c3e4ed4e","source":{"kind":"arxiv","id":"2201.05337","version":5},"attestation_state":"computed","paper":{"title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dawei Song, Hanqing Zhang, Haolin Song, Ming Zhou, Shaoyu Li","submitted_at":"2022-01-14T08:32:20Z","abstract_excerpt":"Controllable Text Generation (CTG) is emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the limited level of interpretability of deep neural networks, the controllability of these methods need"},"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":"2201.05337","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-14T08:32:20Z","cross_cats_sorted":[],"title_canon_sha256":"bb0a2a36ede29e35477522bcbe61def12fc69e57df2bb2379344c89f9aa7d401","abstract_canon_sha256":"255b5aea60a6dfd1ae969cd2b49a6429e328163917dcad50866c1d0aed1588be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:04.031338Z","signature_b64":"w7JWKcrvy86NV+OAfp1pS2g4diIwvdM/JiBDlbx8I1iO+OfP0YpP5Wvp+kOGcKJ5nLjSvkenL7ed2A4xtPWFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1769eaf3895b9923950d815d5248deb633756bfe6045c5b1260996d4c3e4ed4e","last_reissued_at":"2026-07-05T06:44:04.030925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:04.030925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dawei Song, Hanqing Zhang, Haolin Song, Ming Zhou, Shaoyu Li","submitted_at":"2022-01-14T08:32:20Z","abstract_excerpt":"Controllable Text Generation (CTG) is emerging area in the field of natural language generation (NLG). It is regarded as crucial for the development of advanced text generation technologies that better meet the specific constraints in practical applications. In recent years, methods using large-scale pre-trained language models (PLMs), in particular the widely used transformer-based PLMs, have become a new paradigm of NLG, allowing generation of more diverse and fluent text. However, due to the limited level of interpretability of deep neural networks, the controllability of these methods need"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.05337","kind":"arxiv","version":5},"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/2201.05337/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":"2201.05337","created_at":"2026-07-05T06:44:04.030982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.05337v5","created_at":"2026-07-05T06:44:04.030982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.05337","created_at":"2026-07-05T06:44:04.030982+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5U6V44JLOMS","created_at":"2026-07-05T06:44:04.030982+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5U6V44JLOMSHFIN","created_at":"2026-07-05T06:44:04.030982+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5U6V44J","created_at":"2026-07-05T06:44:04.030982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12234","citing_title":"On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27969","citing_title":"Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2308.10248","citing_title":"Steering Language Models With Activation Engineering","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17078","citing_title":"Understanding and Enforcing Weight Disentanglement in Task Arithmetic","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY","json":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY.json","graph_json":"https://pith.science/api/pith-number/C5U6V44JLOMSHFINQFOVESG6WY/graph.json","events_json":"https://pith.science/api/pith-number/C5U6V44JLOMSHFINQFOVESG6WY/events.json","paper":"https://pith.science/paper/C5U6V44J"},"agent_actions":{"view_html":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY","download_json":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY.json","view_paper":"https://pith.science/paper/C5U6V44J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.05337&json=true","fetch_graph":"https://pith.science/api/pith-number/C5U6V44JLOMSHFINQFOVESG6WY/graph.json","fetch_events":"https://pith.science/api/pith-number/C5U6V44JLOMSHFINQFOVESG6WY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY/action/storage_attestation","attest_author":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY/action/author_attestation","sign_citation":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY/action/citation_signature","submit_replication":"https://pith.science/pith/C5U6V44JLOMSHFINQFOVESG6WY/action/replication_record"}},"created_at":"2026-07-05T06:44:04.030982+00:00","updated_at":"2026-07-05T06:44:04.030982+00:00"}