{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZJVQNMWIGVSIK7QHYWYBLGFTRH","short_pith_number":"pith:ZJVQNMWI","canonical_record":{"source":{"id":"2505.02009","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T06:37:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c012dec8defd3beee36da72feca29d4b0ea421c5367bd838658fb7f5bbc679a","abstract_canon_sha256":"db5f32dedb7760a2a4da669eee6564c8809053b6a5a0d045ee80c7648fc62f35"},"schema_version":"1.0"},"canonical_sha256":"ca6b06b2c83564857e07c5b01598b389c4048341b146edcae1ee99d69976b199","source":{"kind":"arxiv","id":"2505.02009","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02009","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02009v3","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02009","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZJVQNMWIGVSI","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZJVQNMWIGVSIK7QH","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZJVQNMWI","created_at":"2026-07-05T11:53:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZJVQNMWIGVSIK7QHYWYBLGFTRH","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02009","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T06:37:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8c012dec8defd3beee36da72feca29d4b0ea421c5367bd838658fb7f5bbc679a","abstract_canon_sha256":"db5f32dedb7760a2a4da669eee6564c8809053b6a5a0d045ee80c7648fc62f35"},"schema_version":"1.0"},"canonical_sha256":"ca6b06b2c83564857e07c5b01598b389c4048341b146edcae1ee99d69976b199","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:02.653204Z","signature_b64":"/i1S1cw75+hw488k4i/+4yNykTv4SQbGUUU+LZVZULDh07+tEQZkxvZ4zQDW4ZNDHBZiW3DvuDGyrjItR3W0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca6b06b2c83564857e07c5b01598b389c4048341b146edcae1ee99d69976b199","last_reissued_at":"2026-07-05T11:53:02.652778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:02.652778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02009","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:53:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CnWdDJ206VEl+81556Hl4KR2kqlIQIg0cJdp4ndQhDitRq6zR6lfax/Vb2eTvL77seVb0RbdIYRA5qOErNVaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:14:34.854734Z"},"content_sha256":"656b725468bbbca01071a886a10d23576778f1fda8779989fe877cb0fc0a2302","schema_version":"1.0","event_id":"sha256:656b725468bbbca01071a886a10d23576778f1fda8779989fe877cb0fc0a2302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZJVQNMWIGVSIK7QHYWYBLGFTRH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditi Gulati, Harish Yenala, Parag Agrawal, Sai Krishna Mendu, Shanu Kumar","submitted_at":"2025-05-04T06:37:20Z","abstract_excerpt":"Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic data essential for high-quality natural language generation, they often contain harmful content, such as hate speech, misinformation, and biased narratives. Training LLMs on such unfiltered data risks perpetuating toxic behaviors, spreading misinformation, and amplifying societal biases which can undermine trust in LLM-driven applications and raise ethical concerns about their u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02009","kind":"arxiv","version":3},"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/2505.02009/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":"2026-07-05T11:53:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fVcdBVRamwwrZHwdEk7QQhRIiRhNYGOB7BOZQw0ZvRXm2+Qm7FlWtdVw2AKzGEuslBQyCzbNDy411e9mg8w3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:14:34.855097Z"},"content_sha256":"6cba50c0134de14ab13944116bc4adc9343a4476ee6b8cef848b5b1c21c8e47c","schema_version":"1.0","event_id":"sha256:6cba50c0134de14ab13944116bc4adc9343a4476ee6b8cef848b5b1c21c8e47c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH/bundle.json","state_url":"https://pith.science/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH/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":"2026-08-18T15:14:34Z","links":{"resolver":"https://pith.science/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH","bundle":"https://pith.science/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH/bundle.json","state":"https://pith.science/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJVQNMWIGVSIK7QHYWYBLGFTRH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZJVQNMWIGVSIK7QHYWYBLGFTRH","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":"db5f32dedb7760a2a4da669eee6564c8809053b6a5a0d045ee80c7648fc62f35","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T06:37:20Z","title_canon_sha256":"8c012dec8defd3beee36da72feca29d4b0ea421c5367bd838658fb7f5bbc679a"},"schema_version":"1.0","source":{"id":"2505.02009","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02009","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02009v3","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02009","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZJVQNMWIGVSI","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZJVQNMWIGVSIK7QH","created_at":"2026-07-05T11:53:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZJVQNMWI","created_at":"2026-07-05T11:53:02Z"}],"graph_snapshots":[{"event_id":"sha256:6cba50c0134de14ab13944116bc4adc9343a4476ee6b8cef848b5b1c21c8e47c","target":"graph","created_at":"2026-07-05T11:53:02Z","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/2505.02009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have become integral to various real-world applications, leveraging massive, web-sourced datasets like Common Crawl, C4, and FineWeb for pretraining. While these datasets provide linguistic data essential for high-quality natural language generation, they often contain harmful content, such as hate speech, misinformation, and biased narratives. Training LLMs on such unfiltered data risks perpetuating toxic behaviors, spreading misinformation, and amplifying societal biases which can undermine trust in LLM-driven applications and raise ethical concerns about their u","authors_text":"Aditi Gulati, Harish Yenala, Parag Agrawal, Sai Krishna Mendu, Shanu Kumar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T06:37:20Z","title":"Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale datasets for Responsible LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02009","kind":"arxiv","version":3},"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":"sha256:656b725468bbbca01071a886a10d23576778f1fda8779989fe877cb0fc0a2302","target":"record","created_at":"2026-07-05T11:53:02Z","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":"db5f32dedb7760a2a4da669eee6564c8809053b6a5a0d045ee80c7648fc62f35","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T06:37:20Z","title_canon_sha256":"8c012dec8defd3beee36da72feca29d4b0ea421c5367bd838658fb7f5bbc679a"},"schema_version":"1.0","source":{"id":"2505.02009","kind":"arxiv","version":3}},"canonical_sha256":"ca6b06b2c83564857e07c5b01598b389c4048341b146edcae1ee99d69976b199","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca6b06b2c83564857e07c5b01598b389c4048341b146edcae1ee99d69976b199","first_computed_at":"2026-07-05T11:53:02.652778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:02.652778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/i1S1cw75+hw488k4i/+4yNykTv4SQbGUUU+LZVZULDh07+tEQZkxvZ4zQDW4ZNDHBZiW3DvuDGyrjItR3W0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:02.653204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02009","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:656b725468bbbca01071a886a10d23576778f1fda8779989fe877cb0fc0a2302","sha256:6cba50c0134de14ab13944116bc4adc9343a4476ee6b8cef848b5b1c21c8e47c"],"state_sha256":"3f238fd8a2ac306097a9298245e3c9379196543a9a676d0e593d71960d07775d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"peIaNlokVpba2mZ3Za6kpVNQ94FKxzTeupewPzJMDoto3LbhVP25J0h1fFqC6YeLrRS0hT3mJ+U/IrJVFuZ3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:14:34.858618Z","bundle_sha256":"1eb5319ed1427a0272a389d4524048563dc31c80f6c7bfa4e4d289a4111438a5"}}