{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:T2CSTXLKJWNQJP7M3EAMOGCZZZ","short_pith_number":"pith:T2CSTXLK","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"},"canonical_sha256":"9e8529dd6a4d9b04bfecd900c71859ce4ac6e52b91b9a259550a4dd66481179e","source":{"kind":"arxiv","id":"2008.13533","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.13533","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2008.13533v1","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.13533","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"T2CSTXLKJWNQ","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"T2CSTXLKJWNQJP7M","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"T2CSTXLK","created_at":"2026-07-05T01:31:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:T2CSTXLKJWNQJP7M3EAMOGCZZZ","target":"record","payload":{"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"},"canonical_sha256":"9e8529dd6a4d9b04bfecd900c71859ce4ac6e52b91b9a259550a4dd66481179e","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"},"source_kind":"arxiv","source_id":"2008.13533","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28JfUTL8PG4za/kCVIR5PlRczxu8SmE1DI/2UGZnRRK7iCZ6f5iJ1SqaTWC0qVNr9yuQFD37UIY9tlDcPgcMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:24:31.202266Z"},"content_sha256":"18d09e8aad0f8852abf86c3a1f275c67f357627b25caca4473ab513db05c0331","schema_version":"1.0","event_id":"sha256:18d09e8aad0f8852abf86c3a1f275c67f357627b25caca4473ab513db05c0331"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:T2CSTXLKJWNQJP7M3EAMOGCZZZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLqbz2mrnjQeYFguwhuxIqIlZAZOLsFrWdB8A7PcOO//SeK4234nTosvG8IS5DMVfDp/N7O0+Hq/seSCu303Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:24:31.203182Z"},"content_sha256":"a9fd1b16116d8f57a88ed4cdbe657be71876c76bb958cf7af640d1cca2250fa5","schema_version":"1.0","event_id":"sha256:a9fd1b16116d8f57a88ed4cdbe657be71876c76bb958cf7af640d1cca2250fa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/bundle.json","state_url":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T10:24:31Z","links":{"resolver":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ","bundle":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/bundle.json","state":"https://pith.science/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T2CSTXLKJWNQJP7M3EAMOGCZZZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:T2CSTXLKJWNQJP7M3EAMOGCZZZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"14b3f4395354232be459ee5834adc9fbbb88bd75a277ef0327d9aba70c90becf","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-17T07:13:24Z","title_canon_sha256":"cbbc5dc8201fe10e04d12172552ab5c8c8e74a39799ddfa2391fdbc9938e31b7"},"schema_version":"1.0","source":{"id":"2008.13533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.13533","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2008.13533v1","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.13533","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"T2CSTXLKJWNQ","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"T2CSTXLKJWNQJP7M","created_at":"2026-07-05T01:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"T2CSTXLK","created_at":"2026-07-05T01:31:38Z"}],"graph_snapshots":[{"event_id":"sha256:a9fd1b16116d8f57a88ed4cdbe657be71876c76bb958cf7af640d1cca2250fa5","target":"graph","created_at":"2026-07-05T01:31:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2008.13533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","authors_text":"Andrew Tomkins, Che Zheng, Cliff Brunk, Dara Bahri, Donald Metzler, Yi Tay","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-17T07:13:24Z","title":"Generative Models are Unsupervised Predictors of Page Quality: A Colossal-Scale Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.13533","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:18d09e8aad0f8852abf86c3a1f275c67f357627b25caca4473ab513db05c0331","target":"record","created_at":"2026-07-05T01:31:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"14b3f4395354232be459ee5834adc9fbbb88bd75a277ef0327d9aba70c90becf","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-17T07:13:24Z","title_canon_sha256":"cbbc5dc8201fe10e04d12172552ab5c8c8e74a39799ddfa2391fdbc9938e31b7"},"schema_version":"1.0","source":{"id":"2008.13533","kind":"arxiv","version":1}},"canonical_sha256":"9e8529dd6a4d9b04bfecd900c71859ce4ac6e52b91b9a259550a4dd66481179e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e8529dd6a4d9b04bfecd900c71859ce4ac6e52b91b9a259550a4dd66481179e","first_computed_at":"2026-07-05T01:31:38.358737Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:31:38.358737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+P2Jge36cVzKMlhI64JRygQUFvYiunnjfTEbMbvvh3dk4hl2nCsBmV4aNPMEoH738lbfwOkavzyJkdIP97enDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:31:38.359229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.13533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18d09e8aad0f8852abf86c3a1f275c67f357627b25caca4473ab513db05c0331","sha256:a9fd1b16116d8f57a88ed4cdbe657be71876c76bb958cf7af640d1cca2250fa5"],"state_sha256":"7aa5808e5ed6da3ec32b45137f1b64a72e7d45dd6e04a712387eea136354b9e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bWDnpU5SBAgeSXj/kgM/z0lisIM6Pm/7lns9AXquXY8ZdFCuqRQ8hk37kO5kBlLjPSIQ5R6PfjAG0aW8ev6LAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:24:31.210631Z","bundle_sha256":"61f34523a4a45d467511c01d2589a7ad6688d99eb529488a143fbbd7a91bbc13"}}