{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T2CSTXLKJWNQJP7M3EAMOGCZZZ","short_pith_number":"pith:T2CSTXLK","schema_version":"1.0","canonical_sha256":"9e8529dd6a4d9b04bfecd900c71859ce4ac6e52b91b9a259550a4dd66481179e","source":{"kind":"arxiv","id":"2008.13533","version":1},"attestation_state":"computed","paper":{"title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Tomkins, Che Zheng, Cliff Brunk, Dara Bahri, Donald Metzler, Yi Tay","submitted_at":"2020-08-17T07:13:24Z","abstract_excerpt":"Large generative language models such as GPT-2 are well-known for their ability to generate text as well as their utility in supervised downstream tasks via fine-tuning. Our work is twofold: firstly we demonstrate via human evaluation that classifiers trained to discriminate between human and machine-generated text emerge as unsupervised predictors of \"page quality\", able to detect low quality content without any training. This enables fast bootstrapping of quality indicators in a low-resource setting. Secondly, curious to understand the prevalence and nature of low quality pages in the wild, "},"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":"2008.13533","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-17T07:13:24Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"cbbc5dc8201fe10e04d12172552ab5c8c8e74a39799ddfa2391fdbc9938e31b7","abstract_canon_sha256":"14b3f4395354232be459ee5834adc9fbbb88bd75a277ef0327d9aba70c90becf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:31:38.359229Z","signature_b64":"+P2Jge36cVzKMlhI64JRygQUFvYiunnjfTEbMbvvh3dk4hl2nCsBmV4aNPMEoH738lbfwOkavzyJkdIP97enDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e8529dd6a4d9b04bfecd900c71859ce4ac6e52b91b9a259550a4dd66481179e","last_reissued_at":"2026-07-05T01:31:38.358737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:31:38.358737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Tomkins, Che Zheng, Cliff Brunk, Dara Bahri, Donald Metzler, Yi Tay","submitted_at":"2020-08-17T07:13:24Z","abstract_excerpt":"Large generative language models such as GPT-2 are well-known for their ability to generate text as well as their utility in supervised downstream tasks via fine-tuning. Our work is twofold: firstly we demonstrate via human evaluation that classifiers trained to discriminate between human and machine-generated text emerge as unsupervised predictors of \"page quality\", able to detect low quality content without any training. This enables fast bootstrapping of quality indicators in a low-resource setting. Secondly, curious to understand the prevalence and nature of low quality pages in the wild, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.13533","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/2008.13533/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":"2008.13533","created_at":"2026-07-05T01:31:38.358801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.13533v1","created_at":"2026-07-05T01:31:38.358801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.13533","created_at":"2026-07-05T01:31:38.358801+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2CSTXLKJWNQ","created_at":"2026-07-05T01:31:38.358801+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2CSTXLKJWNQJP7M","created_at":"2026-07-05T01:31:38.358801+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2CSTXLK","created_at":"2026-07-05T01:31:38.358801+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/T2CSTXLKJWNQJP7M3EAMOGCZZZ","json":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ.json","graph_json":"https://pith.science/api/pith-number/T2CSTXLKJWNQJP7M3EAMOGCZZZ/graph.json","events_json":"https://pith.science/api/pith-number/T2CSTXLKJWNQJP7M3EAMOGCZZZ/events.json","paper":"https://pith.science/paper/T2CSTXLK"},"agent_actions":{"view_html":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ","download_json":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ.json","view_paper":"https://pith.science/paper/T2CSTXLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.13533&json=true","fetch_graph":"https://pith.science/api/pith-number/T2CSTXLKJWNQJP7M3EAMOGCZZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/T2CSTXLKJWNQJP7M3EAMOGCZZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/action/storage_attestation","attest_author":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/action/author_attestation","sign_citation":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/action/citation_signature","submit_replication":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/action/replication_record"}},"created_at":"2026-07-05T01:31:38.358801+00:00","updated_at":"2026-07-05T01:31:38.358801+00:00"}