{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UFMEJKI7CTUSVU7A5ZVP65ZFR6","short_pith_number":"pith:UFMEJKI7","canonical_record":{"source":{"id":"2406.19271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:37:57Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"0439d23264775aeb4af480be4be84583ab13ca032074c4cafdb96e31a76a3512","abstract_canon_sha256":"4b4ba87c6792a0cab3ccae2d258e60a3758cfb795ef01b3c6f3f85a3bef15c65"},"schema_version":"1.0"},"canonical_sha256":"a15844a91f14e92ad3e0ee6aff77258fbfd10a692e8ede06d827f06bc0381a96","source":{"kind":"arxiv","id":"2406.19271","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19271","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19271v2","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19271","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"UFMEJKI7CTUS","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"UFMEJKI7CTUSVU7A","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"UFMEJKI7","created_at":"2026-07-05T10:20:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UFMEJKI7CTUSVU7A5ZVP65ZFR6","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:37:57Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"0439d23264775aeb4af480be4be84583ab13ca032074c4cafdb96e31a76a3512","abstract_canon_sha256":"4b4ba87c6792a0cab3ccae2d258e60a3758cfb795ef01b3c6f3f85a3bef15c65"},"schema_version":"1.0"},"canonical_sha256":"a15844a91f14e92ad3e0ee6aff77258fbfd10a692e8ede06d827f06bc0381a96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:37.973664Z","signature_b64":"q/JItF0QmPsx8OH1VbncBdLFfhERUDjcGgq2ZNpSFOT1wFGAifMBLrDKATOYZbnaMgxuWV0P09mO8Oy1u7neAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a15844a91f14e92ad3e0ee6aff77258fbfd10a692e8ede06d827f06bc0381a96","last_reissued_at":"2026-07-05T10:20:37.973080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:37.973080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19271","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P2sak9RD/rWK3zeBxQBFEP+X3TVXVwR7nAyFbwWCGhc9cI5SucXafT04JJqeYf+XJo+b/4sN0d8VWmUL3s/eDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:39:55.838677Z"},"content_sha256":"0c28fdf0d1d3ad9f1e63a04a00897e4f19565578a678aec87f96245f7d097318","schema_version":"1.0","event_id":"sha256:0c28fdf0d1d3ad9f1e63a04a00897e4f19565578a678aec87f96245f7d097318"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UFMEJKI7CTUSVU7A5ZVP65ZFR6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Praneeth Vadlapati","submitted_at":"2024-06-27T15:37:57Z","abstract_excerpt":"Up-to-date and reliable language models are consistently sought after and are essential in various applications. Typically, models are trained on a fixed dataset and then deployed globally. However, the knowledge of the models becomes outdated. Enabling automatic updation of AI knowledge using web data involves significant concerns regarding the model's safety and quality due to a threat from unsafe and undesirable text across the web. The purity of new data was essential for updating knowledge of language models to maintain their reliability. This paper proposes AutoPureData, a system that au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19271","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/2406.19271/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":"2026-07-05T10:20:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eV5B2XAd/paggCxXaBDij+SqH83tOxX1++uFpW8MWM2gxvamfN1834tu8aY1dbl8nxIoATburDwojUwUYCgeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T04:39:55.839182Z"},"content_sha256":"4e7542972959e768a6788f3927e7d28597adc30c3b1b22d7854c03121c3e7316","schema_version":"1.0","event_id":"sha256:4e7542972959e768a6788f3927e7d28597adc30c3b1b22d7854c03121c3e7316"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6/bundle.json","state_url":"https://pith.science/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6/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":"2026-08-15T04:39:55Z","links":{"resolver":"https://pith.science/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6","bundle":"https://pith.science/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6/bundle.json","state":"https://pith.science/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UFMEJKI7CTUSVU7A5ZVP65ZFR6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UFMEJKI7CTUSVU7A5ZVP65ZFR6","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":"4b4ba87c6792a0cab3ccae2d258e60a3758cfb795ef01b3c6f3f85a3bef15c65","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:37:57Z","title_canon_sha256":"0439d23264775aeb4af480be4be84583ab13ca032074c4cafdb96e31a76a3512"},"schema_version":"1.0","source":{"id":"2406.19271","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19271","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19271v2","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19271","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"pith_short_12","alias_value":"UFMEJKI7CTUS","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"pith_short_16","alias_value":"UFMEJKI7CTUSVU7A","created_at":"2026-07-05T10:20:37Z"},{"alias_kind":"pith_short_8","alias_value":"UFMEJKI7","created_at":"2026-07-05T10:20:37Z"}],"graph_snapshots":[{"event_id":"sha256:4e7542972959e768a6788f3927e7d28597adc30c3b1b22d7854c03121c3e7316","target":"graph","created_at":"2026-07-05T10:20:37Z","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/2406.19271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Up-to-date and reliable language models are consistently sought after and are essential in various applications. Typically, models are trained on a fixed dataset and then deployed globally. However, the knowledge of the models becomes outdated. Enabling automatic updation of AI knowledge using web data involves significant concerns regarding the model's safety and quality due to a threat from unsafe and undesirable text across the web. The purity of new data was essential for updating knowledge of language models to maintain their reliability. This paper proposes AutoPureData, a system that au","authors_text":"Praneeth Vadlapati","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:37:57Z","title":"AutoPureData: Automated Filtering of Undesirable Web Data to Update LLM Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19271","kind":"arxiv","version":2},"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":"sha256:0c28fdf0d1d3ad9f1e63a04a00897e4f19565578a678aec87f96245f7d097318","target":"record","created_at":"2026-07-05T10:20:37Z","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":"4b4ba87c6792a0cab3ccae2d258e60a3758cfb795ef01b3c6f3f85a3bef15c65","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T15:37:57Z","title_canon_sha256":"0439d23264775aeb4af480be4be84583ab13ca032074c4cafdb96e31a76a3512"},"schema_version":"1.0","source":{"id":"2406.19271","kind":"arxiv","version":2}},"canonical_sha256":"a15844a91f14e92ad3e0ee6aff77258fbfd10a692e8ede06d827f06bc0381a96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a15844a91f14e92ad3e0ee6aff77258fbfd10a692e8ede06d827f06bc0381a96","first_computed_at":"2026-07-05T10:20:37.973080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:20:37.973080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q/JItF0QmPsx8OH1VbncBdLFfhERUDjcGgq2ZNpSFOT1wFGAifMBLrDKATOYZbnaMgxuWV0P09mO8Oy1u7neAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:20:37.973664Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19271","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c28fdf0d1d3ad9f1e63a04a00897e4f19565578a678aec87f96245f7d097318","sha256:4e7542972959e768a6788f3927e7d28597adc30c3b1b22d7854c03121c3e7316"],"state_sha256":"bd1c9bc2f034153ee2d49f9286aeb73e0f122705e3a5a92dd9fae9a1c34ec8b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l00wtpy6dtmh+3VkAvgFgmnK9HHb6mOE5NkO02xKWQj0Vy2q5lVu5QRbxVY/s5AQNflqedlxtlC94SH5lsz4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T04:39:55.844067Z","bundle_sha256":"81defb5137f4a8db46e425cde326d31701e5ffc3bef20d1510f17786c573ddfb"}}