{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IFMWDFZY7XVF6CAKM4CQPH2ITI","short_pith_number":"pith:IFMWDFZY","canonical_record":{"source":{"id":"2412.17847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-19T01:30:19Z","cross_cats_sorted":["cs.CL","cs.CY","cs.LG","cs.MM"],"title_canon_sha256":"08ed9b76e09d10c9f59777eae41139105d1f6018a8c681674907ba07ace90662","abstract_canon_sha256":"44915a40775ef8bd0f010a31327784e0d48adce45a72597f847692ae633864b9"},"schema_version":"1.0"},"canonical_sha256":"4159619738fdea5f080a6705079f489a07d8e7e6b819e33bbc49604e8898dd97","source":{"kind":"arxiv","id":"2412.17847","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17847","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17847v2","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17847","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"IFMWDFZY7XVF","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"IFMWDFZY7XVF6CAK","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"IFMWDFZY","created_at":"2026-07-05T10:16:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IFMWDFZY7XVF6CAKM4CQPH2ITI","target":"record","payload":{"canonical_record":{"source":{"id":"2412.17847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-19T01:30:19Z","cross_cats_sorted":["cs.CL","cs.CY","cs.LG","cs.MM"],"title_canon_sha256":"08ed9b76e09d10c9f59777eae41139105d1f6018a8c681674907ba07ace90662","abstract_canon_sha256":"44915a40775ef8bd0f010a31327784e0d48adce45a72597f847692ae633864b9"},"schema_version":"1.0"},"canonical_sha256":"4159619738fdea5f080a6705079f489a07d8e7e6b819e33bbc49604e8898dd97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:40.559816Z","signature_b64":"NhnWkQrjPl36FIc1eCpZ0zfdNLI11maudsfICX/oBzqd547EWNJV8xqw/z9KK3W7+78U1mBRfGy/L3oOAb4ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4159619738fdea5f080a6705079f489a07d8e7e6b819e33bbc49604e8898dd97","last_reissued_at":"2026-07-05T10:16:40.559252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:40.559252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.17847","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":"2026-07-05T10:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fp572bxFDvEGSiD7vrnTLmTzRsjmXvOQznJUvFw61/Pr6Uv/PfdNNfHaJppcH2spG09q6U4spFDbSHWJeiqlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:07:53.671511Z"},"content_sha256":"c5e2d2f881483db8dbeb6665b8afb89380ade6af7754010cf5f88794d28059dd","schema_version":"1.0","event_id":"sha256:c5e2d2f881483db8dbeb6665b8afb89380ade6af7754010cf5f88794d28059dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IFMWDFZY7XVF6CAKM4CQPH2ITI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bridging the Data Provenance Gap Across Text, Speech and Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.LG","cs.MM"],"primary_cat":"cs.AI","authors_text":"Ahmad Mustafa Anis, Alex Pentland, An Dinh, Ariel N. Lee, Caiming Xiong, Campbell S. Lund, Christopher Klamm, Damien Sileo, Da Yin, Deividas Mataciunas, Diganta Misra, Emad A. Alghamdi, Enrico Shippole, Jad Kabbara, Jianguo Zhang, Joanna Materzynska, Kevin Klyman, Kun Qian, Kushagra Tiwary, Lester JV Miranda, Luis Villa, Manan Dey, Manuel Cherep, Minnie Liang, Mohammed Hamdy, Naana Obeng-Marnu, Nayan Saxena, Nikhil Singh, Niklas Muennighoff, Robert Mahari, Sara Hooker, Seonghyeon Ye, Seungone Kim, Shayne Longpre, Shrestha Mohanty, Stella Biderman, Tobin South, Vipul Gupta, Vivek Sharma, Vu Minh Chien, William Brannon, Xuhui Zhou, Yizhi Li","submitted_at":"2024-12-19T01:30:19Z","abstract_excerpt":"Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17847","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/2412.17847/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":"2026-07-05T10:16:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ZH8hzlGTsi87aXEqjplAu6FAG0GZI2q12OKckN8+P2u4i3NqprKGugRu2wMRrS8kkm73ctRc7CeKcIiDIXWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:07:53.672183Z"},"content_sha256":"a22375fcffe15e11fdd7718b78f08b46f321ac8dc65d6c8def47e5bd0a96a391","schema_version":"1.0","event_id":"sha256:a22375fcffe15e11fdd7718b78f08b46f321ac8dc65d6c8def47e5bd0a96a391"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI/bundle.json","state_url":"https://pith.science/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI/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":"2026-07-07T05:07:53Z","links":{"resolver":"https://pith.science/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI","bundle":"https://pith.science/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI/bundle.json","state":"https://pith.science/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFMWDFZY7XVF6CAKM4CQPH2ITI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IFMWDFZY7XVF6CAKM4CQPH2ITI","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":"44915a40775ef8bd0f010a31327784e0d48adce45a72597f847692ae633864b9","cross_cats_sorted":["cs.CL","cs.CY","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-19T01:30:19Z","title_canon_sha256":"08ed9b76e09d10c9f59777eae41139105d1f6018a8c681674907ba07ace90662"},"schema_version":"1.0","source":{"id":"2412.17847","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17847","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17847v2","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17847","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_12","alias_value":"IFMWDFZY7XVF","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_16","alias_value":"IFMWDFZY7XVF6CAK","created_at":"2026-07-05T10:16:40Z"},{"alias_kind":"pith_short_8","alias_value":"IFMWDFZY","created_at":"2026-07-05T10:16:40Z"}],"graph_snapshots":[{"event_id":"sha256:a22375fcffe15e11fdd7718b78f08b46f321ac8dc65d6c8def47e5bd0a96a391","target":"graph","created_at":"2026-07-05T10:16:40Z","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/2412.17847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established datasets beyond text. In this work we conduct the largest and first-of-its-kind longitudinal audit across modalities--popular text, speech, and video datasets--from their detailed sourcing trends and use restrictions to their geographical and linguistic representation. Our manual analysis covers nearly 4000 public datasets between 1990-2024, spanning 608 languages, 798 sources, 659 organizations, and 67 countries. We fin","authors_text":"Ahmad Mustafa Anis, Alex Pentland, An Dinh, Ariel N. Lee, Caiming Xiong, Campbell S. Lund, Christopher Klamm, Damien Sileo, Da Yin, Deividas Mataciunas, Diganta Misra, Emad A. Alghamdi, Enrico Shippole, Jad Kabbara, Jianguo Zhang, Joanna Materzynska, Kevin Klyman, Kun Qian, Kushagra Tiwary, Lester JV Miranda, Luis Villa, Manan Dey, Manuel Cherep, Minnie Liang, Mohammed Hamdy, Naana Obeng-Marnu, Nayan Saxena, Nikhil Singh, Niklas Muennighoff, Robert Mahari, Sara Hooker, Seonghyeon Ye, Seungone Kim, Shayne Longpre, Shrestha Mohanty, Stella Biderman, Tobin South, Vipul Gupta, Vivek Sharma, Vu Minh Chien, William Brannon, Xuhui Zhou, Yizhi Li","cross_cats":["cs.CL","cs.CY","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-19T01:30:19Z","title":"Bridging the Data Provenance Gap Across Text, Speech and Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17847","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:c5e2d2f881483db8dbeb6665b8afb89380ade6af7754010cf5f88794d28059dd","target":"record","created_at":"2026-07-05T10:16:40Z","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":"44915a40775ef8bd0f010a31327784e0d48adce45a72597f847692ae633864b9","cross_cats_sorted":["cs.CL","cs.CY","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-19T01:30:19Z","title_canon_sha256":"08ed9b76e09d10c9f59777eae41139105d1f6018a8c681674907ba07ace90662"},"schema_version":"1.0","source":{"id":"2412.17847","kind":"arxiv","version":2}},"canonical_sha256":"4159619738fdea5f080a6705079f489a07d8e7e6b819e33bbc49604e8898dd97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4159619738fdea5f080a6705079f489a07d8e7e6b819e33bbc49604e8898dd97","first_computed_at":"2026-07-05T10:16:40.559252Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:40.559252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NhnWkQrjPl36FIc1eCpZ0zfdNLI11maudsfICX/oBzqd547EWNJV8xqw/z9KK3W7+78U1mBRfGy/L3oOAb4ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:40.559816Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17847","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5e2d2f881483db8dbeb6665b8afb89380ade6af7754010cf5f88794d28059dd","sha256:a22375fcffe15e11fdd7718b78f08b46f321ac8dc65d6c8def47e5bd0a96a391"],"state_sha256":"18501d0c6708ded82674c01ca849bc72e434b3cf55bcc3ed76a8a39e59c45705"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e34+pNcqth2WoQhoAQQTigGO7hvcUYOCjuUShBQy89lR/G/FvTcqiZkXv+b3jE0bIZyl97iXl7SZMJ+vsSaLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:07:53.675940Z","bundle_sha256":"cbdb7932be2594ce18f9c196efc309d649b7ac1200297e74c4b5a4b393e43d2e"}}