{"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"}