{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:I5V6RE75GGXW3CXGOBTU3DU6IW","short_pith_number":"pith:I5V6RE75","canonical_record":{"source":{"id":"2304.02828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T02:33:51Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"1f92a65d0b0d8b6cd991b1cb143436c836979352759f0fe04043f21aba681a68","abstract_canon_sha256":"b6edf5dee6817643cdf6485fda448107db292ebc3dd9f1c60be28c1a03c91560"},"schema_version":"1.0"},"canonical_sha256":"476be893fd31af6d8ae670674d8e9e45820f6c96025985e4f461ba1ba73e3bf5","source":{"kind":"arxiv","id":"2304.02828","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02828","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02828v1","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02828","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"I5V6RE75GGXW","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"pith_short_16","alias_value":"I5V6RE75GGXW3CXG","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"pith_short_8","alias_value":"I5V6RE75","created_at":"2026-07-05T05:58:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:I5V6RE75GGXW3CXGOBTU3DU6IW","target":"record","payload":{"canonical_record":{"source":{"id":"2304.02828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T02:33:51Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"1f92a65d0b0d8b6cd991b1cb143436c836979352759f0fe04043f21aba681a68","abstract_canon_sha256":"b6edf5dee6817643cdf6485fda448107db292ebc3dd9f1c60be28c1a03c91560"},"schema_version":"1.0"},"canonical_sha256":"476be893fd31af6d8ae670674d8e9e45820f6c96025985e4f461ba1ba73e3bf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:32.128394Z","signature_b64":"x+8osTkDVw6XwLAjTccEUVq3HOzrAQwJEkwFPqd8EuRhFnxoH+z2zf+4RvfCWZh8QHBYIU2TyEhiQ3+P6N5yAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"476be893fd31af6d8ae670674d8e9e45820f6c96025985e4f461ba1ba73e3bf5","last_reissued_at":"2026-07-05T05:58:32.127645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:32.127645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.02828","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":"2026-07-05T05:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pl0Pu1EJodMPGcGxB0TE5kEg+MgYPLiLhkeMZSYduRcZn9cE4IXBKVK9we2j7XtLTbWeHtb+h0Ugu2L1MLZ8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:54:59.154590Z"},"content_sha256":"3d660e32b70d611cc1465c23111abc49855da8bc5396ac6b61e36203f0443560","schema_version":"1.0","event_id":"sha256:3d660e32b70d611cc1465c23111abc49855da8bc5396ac6b61e36203f0443560"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:I5V6RE75GGXW3CXGOBTU3DU6IW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CV","authors_text":"Noa Garcia, Yankun Wu, Yusuke Hirota, Yuta Nakashima","submitted_at":"2023-04-06T02:33:51Z","abstract_excerpt":"The increasing tendency to collect large and uncurated datasets to train vision-and-language models has raised concerns about fair representations. It is known that even small but manually annotated datasets, such as MSCOCO, are affected by societal bias. This problem, far from being solved, may be getting worse with data crawled from the Internet without much control. In addition, the lack of tools to analyze societal bias in big collections of images makes addressing the problem extremely challenging. Our first contribution is to annotate part of the Google Conceptual Captions dataset, widel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02828","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/2304.02828/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":"2026-07-05T05:58:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQI8712Yen8UQRPtY3h3nh2qU6TdbliE2deosaZ/XMXzpfXdvgYuPTvUxAK0xEJ8k4b2pu8SDJPmAAlJsAQLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:54:59.155149Z"},"content_sha256":"b862feef4f7bd1588966949c746c9b26951e3e97a042e2e500ad969a22e690c9","schema_version":"1.0","event_id":"sha256:b862feef4f7bd1588966949c746c9b26951e3e97a042e2e500ad969a22e690c9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5V6RE75GGXW3CXGOBTU3DU6IW/bundle.json","state_url":"https://pith.science/pith/I5V6RE75GGXW3CXGOBTU3DU6IW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5V6RE75GGXW3CXGOBTU3DU6IW/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":"2026-08-09T06:54:59Z","links":{"resolver":"https://pith.science/pith/I5V6RE75GGXW3CXGOBTU3DU6IW","bundle":"https://pith.science/pith/I5V6RE75GGXW3CXGOBTU3DU6IW/bundle.json","state":"https://pith.science/pith/I5V6RE75GGXW3CXGOBTU3DU6IW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5V6RE75GGXW3CXGOBTU3DU6IW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:I5V6RE75GGXW3CXGOBTU3DU6IW","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":"b6edf5dee6817643cdf6485fda448107db292ebc3dd9f1c60be28c1a03c91560","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T02:33:51Z","title_canon_sha256":"1f92a65d0b0d8b6cd991b1cb143436c836979352759f0fe04043f21aba681a68"},"schema_version":"1.0","source":{"id":"2304.02828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.02828","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"arxiv_version","alias_value":"2304.02828v1","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02828","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"pith_short_12","alias_value":"I5V6RE75GGXW","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"pith_short_16","alias_value":"I5V6RE75GGXW3CXG","created_at":"2026-07-05T05:58:32Z"},{"alias_kind":"pith_short_8","alias_value":"I5V6RE75","created_at":"2026-07-05T05:58:32Z"}],"graph_snapshots":[{"event_id":"sha256:b862feef4f7bd1588966949c746c9b26951e3e97a042e2e500ad969a22e690c9","target":"graph","created_at":"2026-07-05T05:58:32Z","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/2304.02828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing tendency to collect large and uncurated datasets to train vision-and-language models has raised concerns about fair representations. It is known that even small but manually annotated datasets, such as MSCOCO, are affected by societal bias. This problem, far from being solved, may be getting worse with data crawled from the Internet without much control. In addition, the lack of tools to analyze societal bias in big collections of images makes addressing the problem extremely challenging. Our first contribution is to annotate part of the Google Conceptual Captions dataset, widel","authors_text":"Noa Garcia, Yankun Wu, Yusuke Hirota, Yuta Nakashima","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T02:33:51Z","title":"Uncurated Image-Text Datasets: Shedding Light on Demographic Bias"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02828","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":"sha256:3d660e32b70d611cc1465c23111abc49855da8bc5396ac6b61e36203f0443560","target":"record","created_at":"2026-07-05T05:58:32Z","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":"b6edf5dee6817643cdf6485fda448107db292ebc3dd9f1c60be28c1a03c91560","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T02:33:51Z","title_canon_sha256":"1f92a65d0b0d8b6cd991b1cb143436c836979352759f0fe04043f21aba681a68"},"schema_version":"1.0","source":{"id":"2304.02828","kind":"arxiv","version":1}},"canonical_sha256":"476be893fd31af6d8ae670674d8e9e45820f6c96025985e4f461ba1ba73e3bf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"476be893fd31af6d8ae670674d8e9e45820f6c96025985e4f461ba1ba73e3bf5","first_computed_at":"2026-07-05T05:58:32.127645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:32.127645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x+8osTkDVw6XwLAjTccEUVq3HOzrAQwJEkwFPqd8EuRhFnxoH+z2zf+4RvfCWZh8QHBYIU2TyEhiQ3+P6N5yAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:32.128394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.02828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d660e32b70d611cc1465c23111abc49855da8bc5396ac6b61e36203f0443560","sha256:b862feef4f7bd1588966949c746c9b26951e3e97a042e2e500ad969a22e690c9"],"state_sha256":"6a876b97bed46fd923a774f6578f67581c9ba811bc522cd1bada24171253031c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ARizHUrdjExWpcDY5fVcfeaMy3yNWCnjHajeigJLwL2+/RSOCQJ91XnFmn1wGdzPSW9DDSdPOoILcPRVkv8zDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:54:59.159407Z","bundle_sha256":"ca1b4bcaae461857887ca94889190b80a0638967db49f64478e01902cae30a52"}}