{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PDEY2VD5US7EAM6BXQLEYZYP5S","short_pith_number":"pith:PDEY2VD5","canonical_record":{"source":{"id":"2405.08209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-13T21:53:06Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"58f74ad9e30d0d4a75c65ceb60182c8bbc1dbe75efac73ac770dee0146450e80","abstract_canon_sha256":"c1bde5cdc3f9bbc7e8ef0d599b94e7880a74f5f5433bb4bec246e8da38471c5c"},"schema_version":"1.0"},"canonical_sha256":"78c98d547da4be4033c1bc164c670fecb9bd5f28f46215292cc4a1125508d0d0","source":{"kind":"arxiv","id":"2405.08209","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08209","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08209v2","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08209","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"PDEY2VD5US7E","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"PDEY2VD5US7EAM6B","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"PDEY2VD5","created_at":"2026-07-05T09:18:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PDEY2VD5US7EAM6BXQLEYZYP5S","target":"record","payload":{"canonical_record":{"source":{"id":"2405.08209","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-13T21:53:06Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"58f74ad9e30d0d4a75c65ceb60182c8bbc1dbe75efac73ac770dee0146450e80","abstract_canon_sha256":"c1bde5cdc3f9bbc7e8ef0d599b94e7880a74f5f5433bb4bec246e8da38471c5c"},"schema_version":"1.0"},"canonical_sha256":"78c98d547da4be4033c1bc164c670fecb9bd5f28f46215292cc4a1125508d0d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:25.650248Z","signature_b64":"SBTzz191BuqNaE0ZBvvS6sjOU8suCFYUM2vbAdpK91DpLzBPIoaTa6J+GXrX9fN9WIEwuS1QDtIsxxE/Soi9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78c98d547da4be4033c1bc164c670fecb9bd5f28f46215292cc4a1125508d0d0","last_reissued_at":"2026-07-05T09:18:25.649780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:25.649780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.08209","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3gEVJehcRcJyn5S/Tl0/U6LjXAGx1GTji00jh+AGfMGw5TQMhtzeGIvv4l34WnBQUup7O7utxEI2QjLEIedCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:23:43.440338Z"},"content_sha256":"93e701c4aed295ae3667d522f60bda28636bcfcd9816157a38bffd08aa106c62","schema_version":"1.0","event_id":"sha256:93e701c4aed295ae3667d522f60bda28636bcfcd9816157a38bffd08aa106c62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PDEY2VD5US7EAM6BXQLEYZYP5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.CY","authors_text":"Jamie Morgenstern, Rachel Hong, Tadayoshi Kohno, William Agnew","submitted_at":"2024-05-13T21:53:06Z","abstract_excerpt":"As training datasets become increasingly drawn from unstructured, uncontrolled environments such as the web, researchers and industry practitioners have increasingly relied upon data filtering techniques to \"filter out the noise\" of web-scraped data. While datasets have been widely shown to reflect the biases and values of their creators, in this paper we contribute to an emerging body of research that assesses the filters used to create these datasets. We show that image-text data filtering also has biases and is value-laden, encoding specific notions of what is counted as \"high-quality\" data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08209","kind":"arxiv","version":2},"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/2405.08209/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":"2026-07-05T09:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EWGZTjNNXBce9yCLtOIe7nfWK0LQHr9NqwLn2MjHuYkaoVgOuelemwhrFN0vGr4eFeze/qSg2AoUYCiRKxlpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:23:43.441307Z"},"content_sha256":"ce22703b409cec127fc40e3c54f004f4e79da6e6f1590ff3a7b8c998bdf799b2","schema_version":"1.0","event_id":"sha256:ce22703b409cec127fc40e3c54f004f4e79da6e6f1590ff3a7b8c998bdf799b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PDEY2VD5US7EAM6BXQLEYZYP5S/bundle.json","state_url":"https://pith.science/pith/PDEY2VD5US7EAM6BXQLEYZYP5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PDEY2VD5US7EAM6BXQLEYZYP5S/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":"2026-08-10T00:23:43Z","links":{"resolver":"https://pith.science/pith/PDEY2VD5US7EAM6BXQLEYZYP5S","bundle":"https://pith.science/pith/PDEY2VD5US7EAM6BXQLEYZYP5S/bundle.json","state":"https://pith.science/pith/PDEY2VD5US7EAM6BXQLEYZYP5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PDEY2VD5US7EAM6BXQLEYZYP5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PDEY2VD5US7EAM6BXQLEYZYP5S","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":"c1bde5cdc3f9bbc7e8ef0d599b94e7880a74f5f5433bb4bec246e8da38471c5c","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-13T21:53:06Z","title_canon_sha256":"58f74ad9e30d0d4a75c65ceb60182c8bbc1dbe75efac73ac770dee0146450e80"},"schema_version":"1.0","source":{"id":"2405.08209","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.08209","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2405.08209v2","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08209","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"PDEY2VD5US7E","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"PDEY2VD5US7EAM6B","created_at":"2026-07-05T09:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"PDEY2VD5","created_at":"2026-07-05T09:18:25Z"}],"graph_snapshots":[{"event_id":"sha256:ce22703b409cec127fc40e3c54f004f4e79da6e6f1590ff3a7b8c998bdf799b2","target":"graph","created_at":"2026-07-05T09:18:25Z","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/2405.08209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As training datasets become increasingly drawn from unstructured, uncontrolled environments such as the web, researchers and industry practitioners have increasingly relied upon data filtering techniques to \"filter out the noise\" of web-scraped data. While datasets have been widely shown to reflect the biases and values of their creators, in this paper we contribute to an emerging body of research that assesses the filters used to create these datasets. We show that image-text data filtering also has biases and is value-laden, encoding specific notions of what is counted as \"high-quality\" data","authors_text":"Jamie Morgenstern, Rachel Hong, Tadayoshi Kohno, William Agnew","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-13T21:53:06Z","title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08209","kind":"arxiv","version":2},"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":"sha256:93e701c4aed295ae3667d522f60bda28636bcfcd9816157a38bffd08aa106c62","target":"record","created_at":"2026-07-05T09:18:25Z","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":"c1bde5cdc3f9bbc7e8ef0d599b94e7880a74f5f5433bb4bec246e8da38471c5c","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-13T21:53:06Z","title_canon_sha256":"58f74ad9e30d0d4a75c65ceb60182c8bbc1dbe75efac73ac770dee0146450e80"},"schema_version":"1.0","source":{"id":"2405.08209","kind":"arxiv","version":2}},"canonical_sha256":"78c98d547da4be4033c1bc164c670fecb9bd5f28f46215292cc4a1125508d0d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78c98d547da4be4033c1bc164c670fecb9bd5f28f46215292cc4a1125508d0d0","first_computed_at":"2026-07-05T09:18:25.649780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:25.649780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SBTzz191BuqNaE0ZBvvS6sjOU8suCFYUM2vbAdpK91DpLzBPIoaTa6J+GXrX9fN9WIEwuS1QDtIsxxE/Soi9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:25.650248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.08209","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93e701c4aed295ae3667d522f60bda28636bcfcd9816157a38bffd08aa106c62","sha256:ce22703b409cec127fc40e3c54f004f4e79da6e6f1590ff3a7b8c998bdf799b2"],"state_sha256":"449b7acf8eb02553261f84ae3415ee5e1d5f95bf908a9d3b6f6a117d7dff7786"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTg+uoPfKL40akkKYknuXwH3ogGVn+cZjNf+bM6/rIpe4BQngsS6FhjQIBcy+1u+dFtuSflbMoIPWvPjRI7/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:23:43.448143Z","bundle_sha256":"7495cadb65aa6766bd2bc36941f63967f3f23e2f6a251474c70940b53bf7f39a"}}