{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UTBEVWSQWLCALBLO2ZGY6HT5OJ","short_pith_number":"pith:UTBEVWSQ","canonical_record":{"source":{"id":"2404.07177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-10T17:27:54Z","cross_cats_sorted":[],"title_canon_sha256":"6e9ace4a06d7429f228282c589a69a532ee6fe3a9d56b4e6b377c6b7a8ebd870","abstract_canon_sha256":"bdc9e0a7f5fabef9ac55a1f255bab180979f94f1e09717f3f46b002cdade3176"},"schema_version":"1.0"},"canonical_sha256":"a4c24ada50b2c405856ed64d8f1e7d727e97ef8588303c12050f9b05511f575d","source":{"kind":"arxiv","id":"2404.07177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07177","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07177v1","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07177","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"UTBEVWSQWLCA","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"UTBEVWSQWLCALBLO","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"UTBEVWSQ","created_at":"2026-07-05T08:06:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UTBEVWSQWLCALBLO2ZGY6HT5OJ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07177","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-10T17:27:54Z","cross_cats_sorted":[],"title_canon_sha256":"6e9ace4a06d7429f228282c589a69a532ee6fe3a9d56b4e6b377c6b7a8ebd870","abstract_canon_sha256":"bdc9e0a7f5fabef9ac55a1f255bab180979f94f1e09717f3f46b002cdade3176"},"schema_version":"1.0"},"canonical_sha256":"a4c24ada50b2c405856ed64d8f1e7d727e97ef8588303c12050f9b05511f575d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:36.420384Z","signature_b64":"hVdwKFLddXOym1x9IWwPkEhquLp1MlHWCE6rD/LfrnlVJFRRCjS/V/KAGiW0mp2UTkYQQqMYJX0EZUSZ/bztCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4c24ada50b2c405856ed64d8f1e7d727e97ef8588303c12050f9b05511f575d","last_reissued_at":"2026-07-05T08:06:36.419996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:36.419996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07177","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":"2026-07-05T08:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ogl2p40392qXvq4PF3YpGFP/7qmDufObLyGUc0E/jzmLeaa7oc1MJMe3827no2jQ2beXcUyZLMZb55hR5P0EDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:10:49.656079Z"},"content_sha256":"10de397cb2badaa8c11e6f94ca0d8d41408ac08d0157998745717373c5f42323","schema_version":"1.0","event_id":"sha256:10de397cb2badaa8c11e6f94ca0d8d41408ac08d0157998745717373c5f42323"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UTBEVWSQWLCALBLO2ZGY6HT5OJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditi Raghunathan, J. Zico Kolter, Pratyush Maini, Sachin Goyal, Zachary C. Lipton","submitted_at":"2024-04-10T17:27:54Z","abstract_excerpt":"Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets. In recent times, data curation has gained prominence with several works developing strategies to retain 'high-quality' subsets of 'raw' scraped data. For instance, the LAION public dataset retained only 10% of the total crawled data. However, these strategies are typically developed agnostic of the available compute for training. In this paper, we first demonstrate that making filtering decisions independent of training compute is often suboptimal: the limited high-quality data rapidly loses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07177","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/2404.07177/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":"2026-07-05T08:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGu0vsORnuVf2lXnzux8sg0kmkPU/Cm/W5D6FO+B1iQZyCjWwioZY68D7LF33zUlbdZy85nQ2B5y0cHhjO2EBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T20:10:49.656614Z"},"content_sha256":"e8b60abafa3e7f7a5e3da622205e7badb6a1bce36c3b6be0d60accef2b48098b","schema_version":"1.0","event_id":"sha256:e8b60abafa3e7f7a5e3da622205e7badb6a1bce36c3b6be0d60accef2b48098b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ/bundle.json","state_url":"https://pith.science/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ/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":"2026-08-07T20:10:49Z","links":{"resolver":"https://pith.science/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ","bundle":"https://pith.science/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ/bundle.json","state":"https://pith.science/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UTBEVWSQWLCALBLO2ZGY6HT5OJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UTBEVWSQWLCALBLO2ZGY6HT5OJ","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":"bdc9e0a7f5fabef9ac55a1f255bab180979f94f1e09717f3f46b002cdade3176","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-10T17:27:54Z","title_canon_sha256":"6e9ace4a06d7429f228282c589a69a532ee6fe3a9d56b4e6b377c6b7a8ebd870"},"schema_version":"1.0","source":{"id":"2404.07177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07177","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07177v1","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07177","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"UTBEVWSQWLCA","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_16","alias_value":"UTBEVWSQWLCALBLO","created_at":"2026-07-05T08:06:36Z"},{"alias_kind":"pith_short_8","alias_value":"UTBEVWSQ","created_at":"2026-07-05T08:06:36Z"}],"graph_snapshots":[{"event_id":"sha256:e8b60abafa3e7f7a5e3da622205e7badb6a1bce36c3b6be0d60accef2b48098b","target":"graph","created_at":"2026-07-05T08:06:36Z","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/2404.07177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets. In recent times, data curation has gained prominence with several works developing strategies to retain 'high-quality' subsets of 'raw' scraped data. For instance, the LAION public dataset retained only 10% of the total crawled data. However, these strategies are typically developed agnostic of the available compute for training. In this paper, we first demonstrate that making filtering decisions independent of training compute is often suboptimal: the limited high-quality data rapidly loses","authors_text":"Aditi Raghunathan, J. Zico Kolter, Pratyush Maini, Sachin Goyal, Zachary C. Lipton","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-10T17:27:54Z","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07177","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":"sha256:10de397cb2badaa8c11e6f94ca0d8d41408ac08d0157998745717373c5f42323","target":"record","created_at":"2026-07-05T08:06:36Z","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":"bdc9e0a7f5fabef9ac55a1f255bab180979f94f1e09717f3f46b002cdade3176","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-10T17:27:54Z","title_canon_sha256":"6e9ace4a06d7429f228282c589a69a532ee6fe3a9d56b4e6b377c6b7a8ebd870"},"schema_version":"1.0","source":{"id":"2404.07177","kind":"arxiv","version":1}},"canonical_sha256":"a4c24ada50b2c405856ed64d8f1e7d727e97ef8588303c12050f9b05511f575d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4c24ada50b2c405856ed64d8f1e7d727e97ef8588303c12050f9b05511f575d","first_computed_at":"2026-07-05T08:06:36.419996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:36.419996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hVdwKFLddXOym1x9IWwPkEhquLp1MlHWCE6rD/LfrnlVJFRRCjS/V/KAGiW0mp2UTkYQQqMYJX0EZUSZ/bztCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:36.420384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:10de397cb2badaa8c11e6f94ca0d8d41408ac08d0157998745717373c5f42323","sha256:e8b60abafa3e7f7a5e3da622205e7badb6a1bce36c3b6be0d60accef2b48098b"],"state_sha256":"c954459d308db1c41fb3dc053eb9001168dd202211b29718ecf50fb6b02c9a81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"62+pXQjQTjgOsifNzSNf1l7BWysj/TNR4VLEfxlgnQ5AtUIgAVpqIzlR5dTmaCufna/Y2ZNwpBfQf4Z+5K0zBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T20:10:49.660933Z","bundle_sha256":"da411e2fbcb88e2ca60262c45b2c9519d8397edf1eb628ea37c2eef391c9120b"}}