{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SSLAQALSLAMHUODWLK5JCXHQPR","short_pith_number":"pith:SSLAQALS","canonical_record":{"source":{"id":"2605.19407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T06:02:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a612820a38c4a1d66ad25ce3b44c1475ee019b5f7ada53d7eec06a2894638684","abstract_canon_sha256":"ac4ab5402dadd977f48daefa6fdd647a32b4bab2e5ca07db12f1e190a16f9eba"},"schema_version":"1.0"},"canonical_sha256":"949608017258187a38765aba915cf07c68d1ae4cfcd06593ed3ae12ee32573b6","source":{"kind":"arxiv","id":"2605.19407","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19407","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19407v1","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19407","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"SSLAQALSLAMH","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"SSLAQALSLAMHUODW","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"SSLAQALS","created_at":"2026-05-20T01:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SSLAQALSLAMHUODWLK5JCXHQPR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T06:02:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a612820a38c4a1d66ad25ce3b44c1475ee019b5f7ada53d7eec06a2894638684","abstract_canon_sha256":"ac4ab5402dadd977f48daefa6fdd647a32b4bab2e5ca07db12f1e190a16f9eba"},"schema_version":"1.0"},"canonical_sha256":"949608017258187a38765aba915cf07c68d1ae4cfcd06593ed3ae12ee32573b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:44.061061Z","signature_b64":"2OhuD6bKTtkC8aGu51C7goYjSkHh5EkEvvX36zYVUSpyxOxn7rwoyhXd7qpHn850EJNDXITMgy7aNCY/d3/fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"949608017258187a38765aba915cf07c68d1ae4cfcd06593ed3ae12ee32573b6","last_reissued_at":"2026-05-20T01:05:44.060487Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:44.060487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19407","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":"2026-05-20T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUzkQO1cLbFA0C4Fdb2yq0GftCItz2LwjiPMh2tEOEOj0zLSuyXXsLrEQ3RAFXzALuPUHEc9H63nOPxJMdvSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T17:44:08.360225Z"},"content_sha256":"57f0b10ab86788bbf6b63b01fcb0c564efeb832dba20d05e165900a3cb1ff0f8","schema_version":"1.0","event_id":"sha256:57f0b10ab86788bbf6b63b01fcb0c564efeb832dba20d05e165900a3cb1ff0f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SSLAQALSLAMHUODWLK5JCXHQPR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Bitter Lesson for Data Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christopher Mohri, John Duchi, Tatsunori Hashimoto","submitted_at":"2026-05-19T06:02:36Z","abstract_excerpt":"We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an apparently common belief that filtering data to include only high-quality information is essential, our experiments suggest that with enough compute, the best data filter is no data filter. We find that sufficiently trained large parameter models not only tolerate low-quality and distractor data, but in fact benefit from nominally ``poor'' data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19407","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/2605.19407/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":"2026-05-20T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2pHYOEiri/lFR797mYUaicTh+s7WsyoxN/WoMUp9UfgZdI9wA0vJsdFtQz7ZS6lMMeI+KTFmfsyCmTFIr2UiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T17:44:08.360736Z"},"content_sha256":"1b2d5d4a1f0869ddfb472598979de42be53038016dd6541a9dbad469993996b7","schema_version":"1.0","event_id":"sha256:1b2d5d4a1f0869ddfb472598979de42be53038016dd6541a9dbad469993996b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SSLAQALSLAMHUODWLK5JCXHQPR/bundle.json","state_url":"https://pith.science/pith/SSLAQALSLAMHUODWLK5JCXHQPR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SSLAQALSLAMHUODWLK5JCXHQPR/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":"2026-05-24T17:44:08Z","links":{"resolver":"https://pith.science/pith/SSLAQALSLAMHUODWLK5JCXHQPR","bundle":"https://pith.science/pith/SSLAQALSLAMHUODWLK5JCXHQPR/bundle.json","state":"https://pith.science/pith/SSLAQALSLAMHUODWLK5JCXHQPR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SSLAQALSLAMHUODWLK5JCXHQPR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SSLAQALSLAMHUODWLK5JCXHQPR","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":"ac4ab5402dadd977f48daefa6fdd647a32b4bab2e5ca07db12f1e190a16f9eba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T06:02:36Z","title_canon_sha256":"a612820a38c4a1d66ad25ce3b44c1475ee019b5f7ada53d7eec06a2894638684"},"schema_version":"1.0","source":{"id":"2605.19407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19407","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19407v1","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19407","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"SSLAQALSLAMH","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"SSLAQALSLAMHUODW","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"SSLAQALS","created_at":"2026-05-20T01:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:1b2d5d4a1f0869ddfb472598979de42be53038016dd6541a9dbad469993996b7","target":"graph","created_at":"2026-05-20T01:05:44Z","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/2605.19407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate data filtering for large model pretraining via new scaling studies that target the high compute, data-scarce regime. In spite of an apparently common belief that filtering data to include only high-quality information is essential, our experiments suggest that with enough compute, the best data filter is no data filter. We find that sufficiently trained large parameter models not only tolerate low-quality and distractor data, but in fact benefit from nominally ``poor'' data.","authors_text":"Christopher Mohri, John Duchi, Tatsunori Hashimoto","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T06:02:36Z","title":"A Bitter Lesson for Data Filtering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19407","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":"sha256:57f0b10ab86788bbf6b63b01fcb0c564efeb832dba20d05e165900a3cb1ff0f8","target":"record","created_at":"2026-05-20T01:05:44Z","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":"ac4ab5402dadd977f48daefa6fdd647a32b4bab2e5ca07db12f1e190a16f9eba","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T06:02:36Z","title_canon_sha256":"a612820a38c4a1d66ad25ce3b44c1475ee019b5f7ada53d7eec06a2894638684"},"schema_version":"1.0","source":{"id":"2605.19407","kind":"arxiv","version":1}},"canonical_sha256":"949608017258187a38765aba915cf07c68d1ae4cfcd06593ed3ae12ee32573b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"949608017258187a38765aba915cf07c68d1ae4cfcd06593ed3ae12ee32573b6","first_computed_at":"2026-05-20T01:05:44.060487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:44.060487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2OhuD6bKTtkC8aGu51C7goYjSkHh5EkEvvX36zYVUSpyxOxn7rwoyhXd7qpHn850EJNDXITMgy7aNCY/d3/fAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:44.061061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57f0b10ab86788bbf6b63b01fcb0c564efeb832dba20d05e165900a3cb1ff0f8","sha256:1b2d5d4a1f0869ddfb472598979de42be53038016dd6541a9dbad469993996b7"],"state_sha256":"343640daf0db2098227b196de3848714ea901ab33a05faf6268d60372be823e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S85/+x9Jc1ZTdiBY2K3L9y8AXQKwCV2qRU6RaQFOssd9jCcxh4pS2STJhdqYCnpcu0NKIPSrNsV4KydRhsZXAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T17:44:08.363273Z","bundle_sha256":"6645532f60eb19bd3886370a9cb6396f60f033cd5bcf09f7353650720fd9558b"}}