{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UGG5VKD7FE4GPGUOIYALSVY4MP","short_pith_number":"pith:UGG5VKD7","canonical_record":{"source":{"id":"2401.12225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T08:40:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6616b1bb85479358af327587b5f649758ace96467038b8d3c36d102c784dcec5","abstract_canon_sha256":"97996a36e16b7198eba845979b1d1e1dc6826afb87afe0e4a643e9e121d8d7ca"},"schema_version":"1.0"},"canonical_sha256":"a18ddaa87f2938679a8e4600b9571c63feaf7ff2605745758ee5b384a97a5ad8","source":{"kind":"arxiv","id":"2401.12225","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12225","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12225v1","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12225","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_12","alias_value":"UGG5VKD7FE4G","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_16","alias_value":"UGG5VKD7FE4GPGUO","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_8","alias_value":"UGG5VKD7","created_at":"2026-07-05T07:36:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UGG5VKD7FE4GPGUOIYALSVY4MP","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T08:40:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6616b1bb85479358af327587b5f649758ace96467038b8d3c36d102c784dcec5","abstract_canon_sha256":"97996a36e16b7198eba845979b1d1e1dc6826afb87afe0e4a643e9e121d8d7ca"},"schema_version":"1.0"},"canonical_sha256":"a18ddaa87f2938679a8e4600b9571c63feaf7ff2605745758ee5b384a97a5ad8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:27.340793Z","signature_b64":"RUjDVz6QfyVP+d9xJemgMRDow0wQiun6uyjxiE0QvJu2rcXj6QZox/asJnF/SzeDH9OyseWkNvsAYPSivU5/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18ddaa87f2938679a8e4600b9571c63feaf7ff2605745758ee5b384a97a5ad8","last_reissued_at":"2026-07-05T07:36:27.340033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:27.340033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12225","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":"2026-07-05T07:36:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y7+smixVQ5ic57noNxpDS31R7GIqwhKqik3SG+wE5zG/uMfSXzMZtOv8aLzaJnLOoAZZa9CCl5zPX7eW60VTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:34:21.402374Z"},"content_sha256":"c12a32d8e93ff3d4ac82d937ac1ac23561fe6128bd88fff8f1353f49f0330edd","schema_version":"1.0","event_id":"sha256:c12a32d8e93ff3d4ac82d937ac1ac23561fe6128bd88fff8f1353f49f0330edd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UGG5VKD7FE4GPGUOIYALSVY4MP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Data Curation via Object Detection and Filter Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Changho Shin, Dyah Adila, Frederic Sala, Sui Jiet Tay, Tzu-Heng Huang","submitted_at":"2024-01-05T08:40:06Z","abstract_excerpt":"We propose an approach for curating multimodal data that we used for our entry in the 2023 DataComp competition filtering track. Our technique combines object detection and weak supervision-based ensembling. In the first of two steps in our approach, we employ an out-of-the-box zero-shot object detection model to extract granular information and produce a variety of filter designs. In the second step, we employ weak supervision to ensemble filtering rules. This approach results in a 4% performance improvement when compared to the best-performing baseline, producing the top-ranking position in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12225","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/2401.12225/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":"2026-07-05T07:36:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WTKlXv2Edee1riidjY9SwHwJ/zQW+DKrd+u/qsaxX62ea0WRohdzC7qPkfqDDjazmrUR0vi/DlxuhzjYX7zHCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T09:34:21.402875Z"},"content_sha256":"a9717950aeb459d404494e1a6398d4829eeea650fcb19a545fc58f443603d14e","schema_version":"1.0","event_id":"sha256:a9717950aeb459d404494e1a6398d4829eeea650fcb19a545fc58f443603d14e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UGG5VKD7FE4GPGUOIYALSVY4MP/bundle.json","state_url":"https://pith.science/pith/UGG5VKD7FE4GPGUOIYALSVY4MP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UGG5VKD7FE4GPGUOIYALSVY4MP/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":"2026-08-03T09:34:21Z","links":{"resolver":"https://pith.science/pith/UGG5VKD7FE4GPGUOIYALSVY4MP","bundle":"https://pith.science/pith/UGG5VKD7FE4GPGUOIYALSVY4MP/bundle.json","state":"https://pith.science/pith/UGG5VKD7FE4GPGUOIYALSVY4MP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UGG5VKD7FE4GPGUOIYALSVY4MP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UGG5VKD7FE4GPGUOIYALSVY4MP","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":"97996a36e16b7198eba845979b1d1e1dc6826afb87afe0e4a643e9e121d8d7ca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T08:40:06Z","title_canon_sha256":"6616b1bb85479358af327587b5f649758ace96467038b8d3c36d102c784dcec5"},"schema_version":"1.0","source":{"id":"2401.12225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12225","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12225v1","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12225","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_12","alias_value":"UGG5VKD7FE4G","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_16","alias_value":"UGG5VKD7FE4GPGUO","created_at":"2026-07-05T07:36:27Z"},{"alias_kind":"pith_short_8","alias_value":"UGG5VKD7","created_at":"2026-07-05T07:36:27Z"}],"graph_snapshots":[{"event_id":"sha256:a9717950aeb459d404494e1a6398d4829eeea650fcb19a545fc58f443603d14e","target":"graph","created_at":"2026-07-05T07:36:27Z","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/2401.12225/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an approach for curating multimodal data that we used for our entry in the 2023 DataComp competition filtering track. Our technique combines object detection and weak supervision-based ensembling. In the first of two steps in our approach, we employ an out-of-the-box zero-shot object detection model to extract granular information and produce a variety of filter designs. In the second step, we employ weak supervision to ensemble filtering rules. This approach results in a 4% performance improvement when compared to the best-performing baseline, producing the top-ranking position in ","authors_text":"Changho Shin, Dyah Adila, Frederic Sala, Sui Jiet Tay, Tzu-Heng Huang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T08:40:06Z","title":"Multimodal Data Curation via Object Detection and Filter Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12225","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:c12a32d8e93ff3d4ac82d937ac1ac23561fe6128bd88fff8f1353f49f0330edd","target":"record","created_at":"2026-07-05T07:36:27Z","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":"97996a36e16b7198eba845979b1d1e1dc6826afb87afe0e4a643e9e121d8d7ca","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-05T08:40:06Z","title_canon_sha256":"6616b1bb85479358af327587b5f649758ace96467038b8d3c36d102c784dcec5"},"schema_version":"1.0","source":{"id":"2401.12225","kind":"arxiv","version":1}},"canonical_sha256":"a18ddaa87f2938679a8e4600b9571c63feaf7ff2605745758ee5b384a97a5ad8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a18ddaa87f2938679a8e4600b9571c63feaf7ff2605745758ee5b384a97a5ad8","first_computed_at":"2026-07-05T07:36:27.340033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:27.340033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RUjDVz6QfyVP+d9xJemgMRDow0wQiun6uyjxiE0QvJu2rcXj6QZox/asJnF/SzeDH9OyseWkNvsAYPSivU5/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:27.340793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c12a32d8e93ff3d4ac82d937ac1ac23561fe6128bd88fff8f1353f49f0330edd","sha256:a9717950aeb459d404494e1a6398d4829eeea650fcb19a545fc58f443603d14e"],"state_sha256":"e77773bdc1d2cd5997bc5bc4fb61ae41e9b509d64b98f114c63ab37fb5a3a398"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JJZLgAMIDP3x6az0gNz7iqpkBPMt423IC6QiMUtvkk8H6Hv1wBOh8/tnhQ1r9vSgsu/O3LaWsd6pTMsY+BoxAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T09:34:21.407179Z","bundle_sha256":"c40b586aa7f116637d39b7678d6d35735d664dc6e4d5fe5e87e0de9b23f11909"}}