{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:H3F7BPVBH4SZ2S4EH4J6PTSCOF","short_pith_number":"pith:H3F7BPVB","schema_version":"1.0","canonical_sha256":"3ecbf0bea13f259d4b843f13e7ce42716b2a263a992cd321a34b01a192862026","source":{"kind":"arxiv","id":"2006.15720","version":2},"attestation_state":"computed","paper":{"title":"Progressive Generation of Long Text with Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Tan, Eric P. Xing, Maruan AI-Shedivat, Zhiting Hu, Zichao Yang","submitted_at":"2020-06-28T21:23:05Z","abstract_excerpt":"Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passages of text (e.g., 1000 tokens), especially when the models are fine-tuned to the target domain on a small corpus. Previous planning-then-generation methods also fall short of producing such long text in various domains. To overcome the limitations, we propose a simple but effective method of generating text in a progressive manner, inspired by gene"},"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":"2006.15720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-28T21:23:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9bc2d7cb44aad65207440a01c39641234fa4fc3bda67a0ccf78d24541d4cd242","abstract_canon_sha256":"99c2c9407aed1f701a76605467ae33e275e708002c62105b9416e19210584f6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:59.560485Z","signature_b64":"i7KqOU7AyNiAo1FK5/hsBhSaUwT+6XbhcUNrdxhUqlQU+QTLWRZgpj0piHN93qwdesuH3XyPyvWoFKQM+HcvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ecbf0bea13f259d4b843f13e7ce42716b2a263a992cd321a34b01a192862026","last_reissued_at":"2026-07-05T02:31:59.559986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:59.559986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressive Generation of Long Text with Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Tan, Eric P. Xing, Maruan AI-Shedivat, Zhiting Hu, Zichao Yang","submitted_at":"2020-06-28T21:23:05Z","abstract_excerpt":"Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent long passages of text (e.g., 1000 tokens), especially when the models are fine-tuned to the target domain on a small corpus. Previous planning-then-generation methods also fall short of producing such long text in various domains. To overcome the limitations, we propose a simple but effective method of generating text in a progressive manner, inspired by gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15720","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/2006.15720/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":"2006.15720","created_at":"2026-07-05T02:31:59.560047+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.15720v2","created_at":"2026-07-05T02:31:59.560047+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15720","created_at":"2026-07-05T02:31:59.560047+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3F7BPVBH4SZ","created_at":"2026-07-05T02:31:59.560047+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3F7BPVBH4SZ2S4E","created_at":"2026-07-05T02:31:59.560047+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3F7BPVB","created_at":"2026-07-05T02:31:59.560047+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.09659","citing_title":"Intent Factored Generation: Unleashing the Diversity in Your Language Model","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF","json":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF.json","graph_json":"https://pith.science/api/pith-number/H3F7BPVBH4SZ2S4EH4J6PTSCOF/graph.json","events_json":"https://pith.science/api/pith-number/H3F7BPVBH4SZ2S4EH4J6PTSCOF/events.json","paper":"https://pith.science/paper/H3F7BPVB"},"agent_actions":{"view_html":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF","download_json":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF.json","view_paper":"https://pith.science/paper/H3F7BPVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.15720&json=true","fetch_graph":"https://pith.science/api/pith-number/H3F7BPVBH4SZ2S4EH4J6PTSCOF/graph.json","fetch_events":"https://pith.science/api/pith-number/H3F7BPVBH4SZ2S4EH4J6PTSCOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF/action/storage_attestation","attest_author":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF/action/author_attestation","sign_citation":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF/action/citation_signature","submit_replication":"https://pith.science/pith/H3F7BPVBH4SZ2S4EH4J6PTSCOF/action/replication_record"}},"created_at":"2026-07-05T02:31:59.560047+00:00","updated_at":"2026-07-05T02:31:59.560047+00:00"}