{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6ZGLWJKE5WC4I5UD6QRMC3WBFE","short_pith_number":"pith:6ZGLWJKE","schema_version":"1.0","canonical_sha256":"f64cbb2544ed85c47683f422c16ec1292ac27d78fb83fb4246fa0bed114fbee2","source":{"kind":"arxiv","id":"2005.00558","version":2},"attestation_state":"computed","paper":{"title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bill Dolan, Chris Brockett, Chunyuan Li, Guoyin Wang, Yizhe Zhang, Zhe Gan","submitted_at":"2020-05-01T18:11:54Z","abstract_excerpt":"Large-scale pre-trained language models, such as BERT and GPT-2, have achieved excellent performance in language representation learning and free-form text generation. However, these models cannot be directly employed to generate text under specified lexical constraints. To address this challenge, we present POINTER (PrOgressive INsertion-based TransformER), a simple yet novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. This procedure is recursively applied until "},"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":"2005.00558","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T18:11:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5b9bda395bb859d788335c60de9cfc33f48f76159a351c0613c90626b76e26b1","abstract_canon_sha256":"ecfd06be12267abe906e09cd4c12fa8dc4d93a83f8f5c2f33ff3ff454d2af6dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:18.268262Z","signature_b64":"wDJfUTWgEovg5qc/d7Se9J8eueMrv0wBhmd8xN9Aa/j+Kusx8A547I4DOk7OJ2dqSgaG5aQjR8ABo3UkS/nTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f64cbb2544ed85c47683f422c16ec1292ac27d78fb83fb4246fa0bed114fbee2","last_reissued_at":"2026-07-05T01:38:18.267865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:18.267865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bill Dolan, Chris Brockett, Chunyuan Li, Guoyin Wang, Yizhe Zhang, Zhe Gan","submitted_at":"2020-05-01T18:11:54Z","abstract_excerpt":"Large-scale pre-trained language models, such as BERT and GPT-2, have achieved excellent performance in language representation learning and free-form text generation. However, these models cannot be directly employed to generate text under specified lexical constraints. To address this challenge, we present POINTER (PrOgressive INsertion-based TransformER), a simple yet novel insertion-based approach for hard-constrained text generation. The proposed method operates by progressively inserting new tokens between existing tokens in a parallel manner. This procedure is recursively applied until "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00558","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/2005.00558/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":"2005.00558","created_at":"2026-07-05T01:38:18.267921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00558v2","created_at":"2026-07-05T01:38:18.267921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00558","created_at":"2026-07-05T01:38:18.267921+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZGLWJKE5WC4","created_at":"2026-07-05T01:38:18.267921+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZGLWJKE5WC4I5UD","created_at":"2026-07-05T01:38:18.267921+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZGLWJKE","created_at":"2026-07-05T01:38:18.267921+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/6ZGLWJKE5WC4I5UD6QRMC3WBFE","json":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE.json","graph_json":"https://pith.science/api/pith-number/6ZGLWJKE5WC4I5UD6QRMC3WBFE/graph.json","events_json":"https://pith.science/api/pith-number/6ZGLWJKE5WC4I5UD6QRMC3WBFE/events.json","paper":"https://pith.science/paper/6ZGLWJKE"},"agent_actions":{"view_html":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE","download_json":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE.json","view_paper":"https://pith.science/paper/6ZGLWJKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00558&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZGLWJKE5WC4I5UD6QRMC3WBFE/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZGLWJKE5WC4I5UD6QRMC3WBFE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE/action/storage_attestation","attest_author":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE/action/author_attestation","sign_citation":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE/action/citation_signature","submit_replication":"https://pith.science/pith/6ZGLWJKE5WC4I5UD6QRMC3WBFE/action/replication_record"}},"created_at":"2026-07-05T01:38:18.267921+00:00","updated_at":"2026-07-05T01:38:18.267921+00:00"}