{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KE7CI7PR73KKGBXSPUO666OZ55","short_pith_number":"pith:KE7CI7PR","canonical_record":{"source":{"id":"2405.04623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-07T19:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"cef7e4f9baa2acc8796dc0b828e4c411b15d8c298145d9a5fd3e64215e7dd216","abstract_canon_sha256":"cb900fe9843847ac702322d97b3ad40088b185269675bf3a454d3a6494a1a991"},"schema_version":"1.0"},"canonical_sha256":"513e247df1fed4a306f27d1def79d9ef5a8df583101d4a6559a11e8e01aded5a","source":{"kind":"arxiv","id":"2405.04623","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04623","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04623v1","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04623","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"pith_short_12","alias_value":"KE7CI7PR73KK","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"pith_short_16","alias_value":"KE7CI7PR73KKGBXS","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"pith_short_8","alias_value":"KE7CI7PR","created_at":"2026-07-05T08:16:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KE7CI7PR73KKGBXSPUO666OZ55","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04623","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-07T19:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"cef7e4f9baa2acc8796dc0b828e4c411b15d8c298145d9a5fd3e64215e7dd216","abstract_canon_sha256":"cb900fe9843847ac702322d97b3ad40088b185269675bf3a454d3a6494a1a991"},"schema_version":"1.0"},"canonical_sha256":"513e247df1fed4a306f27d1def79d9ef5a8df583101d4a6559a11e8e01aded5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:51.601622Z","signature_b64":"vsEWtrPQY94/8nBy6gW6QtUTchUBCyIznDXqHKb3aEYYKHLNuToh9/8w+4g/Da7LIy0BYQ42q4/f1qX6O8mgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"513e247df1fed4a306f27d1def79d9ef5a8df583101d4a6559a11e8e01aded5a","last_reissued_at":"2026-07-05T08:16:51.601146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:51.601146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04623","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":"2026-07-05T08:16:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sgt/3S55wxraBDKdlqsLroNriELHpbQu0q50TbafMVS2vUq96qMyDcj2dRSP/cT7EcPq+OpQLtplHVGks7f5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:21:26.375785Z"},"content_sha256":"103afd3425dcfb1d7ee2699fc8115d66e67b067127181511b9eff5bc500ffaf8","schema_version":"1.0","event_id":"sha256:103afd3425dcfb1d7ee2699fc8115d66e67b067127181511b9eff5bc500ffaf8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KE7CI7PR73KKGBXSPUO666OZ55","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Abeba Birhane, Sepehr Dehdashtian, Vinay Uday Prabhu, Vishnu Boddeti","submitted_at":"2024-05-07T19:11:10Z","abstract_excerpt":"Scale the model, scale the data, scale the GPU farms is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling and its downstream impacts on model performance remain under-explored. This is particularly important in the context of multimodal datasets whose main source is the World Wide Web, condensed and packaged as the Common Crawl dump, which is known to exhibit numerous drawbacks. In this paper, we evaluate the downstream impact of dataset scaling on 14 visio-linguistic models (VLMs) trained on the LAION400-M and LAION-2B d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04623","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/2405.04623/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":"2026-07-05T08:16:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WmX1/eKvqFwMi8AbWgab1fsxHDmYpS+Iy0W50K91Iy/VkWWe4/lJb+4n/3l2jMvUwOSa/aYFkqlSalVoNJdoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:21:26.376351Z"},"content_sha256":"425f85b52f93f3d83540d87397ae3d77d2eaa4ee634917bd19f50c12cd154b02","schema_version":"1.0","event_id":"sha256:425f85b52f93f3d83540d87397ae3d77d2eaa4ee634917bd19f50c12cd154b02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KE7CI7PR73KKGBXSPUO666OZ55/bundle.json","state_url":"https://pith.science/pith/KE7CI7PR73KKGBXSPUO666OZ55/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KE7CI7PR73KKGBXSPUO666OZ55/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":"2026-08-04T16:21:26Z","links":{"resolver":"https://pith.science/pith/KE7CI7PR73KKGBXSPUO666OZ55","bundle":"https://pith.science/pith/KE7CI7PR73KKGBXSPUO666OZ55/bundle.json","state":"https://pith.science/pith/KE7CI7PR73KKGBXSPUO666OZ55/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KE7CI7PR73KKGBXSPUO666OZ55/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KE7CI7PR73KKGBXSPUO666OZ55","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":"cb900fe9843847ac702322d97b3ad40088b185269675bf3a454d3a6494a1a991","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-07T19:11:10Z","title_canon_sha256":"cef7e4f9baa2acc8796dc0b828e4c411b15d8c298145d9a5fd3e64215e7dd216"},"schema_version":"1.0","source":{"id":"2405.04623","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04623","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04623v1","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04623","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"pith_short_12","alias_value":"KE7CI7PR73KK","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"pith_short_16","alias_value":"KE7CI7PR73KKGBXS","created_at":"2026-07-05T08:16:51Z"},{"alias_kind":"pith_short_8","alias_value":"KE7CI7PR","created_at":"2026-07-05T08:16:51Z"}],"graph_snapshots":[{"event_id":"sha256:425f85b52f93f3d83540d87397ae3d77d2eaa4ee634917bd19f50c12cd154b02","target":"graph","created_at":"2026-07-05T08:16:51Z","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/2405.04623/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scale the model, scale the data, scale the GPU farms is the reigning sentiment in the world of generative AI today. While model scaling has been extensively studied, data scaling and its downstream impacts on model performance remain under-explored. This is particularly important in the context of multimodal datasets whose main source is the World Wide Web, condensed and packaged as the Common Crawl dump, which is known to exhibit numerous drawbacks. In this paper, we evaluate the downstream impact of dataset scaling on 14 visio-linguistic models (VLMs) trained on the LAION400-M and LAION-2B d","authors_text":"Abeba Birhane, Sepehr Dehdashtian, Vinay Uday Prabhu, Vishnu Boddeti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-07T19:11:10Z","title":"The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04623","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":"sha256:103afd3425dcfb1d7ee2699fc8115d66e67b067127181511b9eff5bc500ffaf8","target":"record","created_at":"2026-07-05T08:16:51Z","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":"cb900fe9843847ac702322d97b3ad40088b185269675bf3a454d3a6494a1a991","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-07T19:11:10Z","title_canon_sha256":"cef7e4f9baa2acc8796dc0b828e4c411b15d8c298145d9a5fd3e64215e7dd216"},"schema_version":"1.0","source":{"id":"2405.04623","kind":"arxiv","version":1}},"canonical_sha256":"513e247df1fed4a306f27d1def79d9ef5a8df583101d4a6559a11e8e01aded5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"513e247df1fed4a306f27d1def79d9ef5a8df583101d4a6559a11e8e01aded5a","first_computed_at":"2026-07-05T08:16:51.601146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:51.601146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vsEWtrPQY94/8nBy6gW6QtUTchUBCyIznDXqHKb3aEYYKHLNuToh9/8w+4g/Da7LIy0BYQ42q4/f1qX6O8mgCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:51.601622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04623","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:103afd3425dcfb1d7ee2699fc8115d66e67b067127181511b9eff5bc500ffaf8","sha256:425f85b52f93f3d83540d87397ae3d77d2eaa4ee634917bd19f50c12cd154b02"],"state_sha256":"ba2a7ad6ccbdda82cb967b19b335fbd8e4136ffeae778d860160024951623631"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VW2T52TkZtpQGusJKUXIx+wD+Xwk37PWR3F3d+64OrzkF0KA7OcHxkqiXjepdYapJXitarWRdGJWtXPfpB5ZBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:21:26.381573Z","bundle_sha256":"7467f05e2e635941762a317d2d7d19cf4d7b557bd310dd2f190c29369cfd4d78"}}