{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BCMJWOEPQKZLT2NIFAX3XC2DFD","short_pith_number":"pith:BCMJWOEP","schema_version":"1.0","canonical_sha256":"08989b388f82b2b9e9a8282fbb8b4328cf5129b9adfb9a1f72fe3a3b31f6a168","source":{"kind":"arxiv","id":"1503.01817","version":2},"attestation_state":"computed","paper":{"title":"YFCC100M: The New Data in Multimedia Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.MM","authors_text":"Bart Thomee, Benjamin Elizalde, Damian Borth, David A. Shamma, Douglas Poland, Gerald Friedland, Karl Ni, Li-Jia Li","submitted_at":"2015-03-05T23:43:42Z","abstract_excerpt":"We present the Yahoo Flickr Creative Commons 100 Million Dataset (YFCC100M), the largest public multimedia collection that has ever been released. The dataset contains a total of 100 million media objects, of which approximately 99.2 million are photos and 0.8 million are videos, all of which carry a Creative Commons license. Each media object in the dataset is represented by several pieces of metadata, e.g. Flickr identifier, owner name, camera, title, tags, geo, media source. The collection provides a comprehensive snapshot of how photos and videos were taken, described, and shared over the "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1503.01817","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2015-03-05T23:43:42Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"889787f55dca018b32a411913389272186f91c2edb019b11152f9da66e153c5c","abstract_canon_sha256":"b8ea842882924707916a930c68d30c6af44e2ebf6e3642bf79d111e1a9a6b275"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:21.796018Z","signature_b64":"93KhVouhCVTBGOAbuWFLI0RwikePDKV9S7Ft5UD2Ms7m078KcUs2VTzTTBqLe8Dn8YFBDLzz4K4G+w8vs90uDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08989b388f82b2b9e9a8282fbb8b4328cf5129b9adfb9a1f72fe3a3b31f6a168","last_reissued_at":"2026-05-18T01:16:21.795494Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:21.795494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YFCC100M: The New Data in Multimedia Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.MM","authors_text":"Bart Thomee, Benjamin Elizalde, Damian Borth, David A. Shamma, Douglas Poland, Gerald Friedland, Karl Ni, Li-Jia Li","submitted_at":"2015-03-05T23:43:42Z","abstract_excerpt":"We present the Yahoo Flickr Creative Commons 100 Million Dataset (YFCC100M), the largest public multimedia collection that has ever been released. The dataset contains a total of 100 million media objects, of which approximately 99.2 million are photos and 0.8 million are videos, all of which carry a Creative Commons license. Each media object in the dataset is represented by several pieces of metadata, e.g. Flickr identifier, owner name, camera, title, tags, geo, media source. The collection provides a comprehensive snapshot of how photos and videos were taken, described, and shared over the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1503.01817","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1503.01817","created_at":"2026-05-18T01:16:21.795575+00:00"},{"alias_kind":"arxiv_version","alias_value":"1503.01817v2","created_at":"2026-05-18T01:16:21.795575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1503.01817","created_at":"2026-05-18T01:16:21.795575+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCMJWOEPQKZL","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCMJWOEPQKZLT2NI","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCMJWOEP","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.21523","citing_title":"Tackle CSM in JPEG Steganalysis with Data Adaptation","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2104.14294","citing_title":"Emerging Properties in Self-Supervised Vision Transformers","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2010.14701","citing_title":"Scaling Laws for Autoregressive Generative Modeling","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":120,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD","json":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD.json","graph_json":"https://pith.science/api/pith-number/BCMJWOEPQKZLT2NIFAX3XC2DFD/graph.json","events_json":"https://pith.science/api/pith-number/BCMJWOEPQKZLT2NIFAX3XC2DFD/events.json","paper":"https://pith.science/paper/BCMJWOEP"},"agent_actions":{"view_html":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD","download_json":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD.json","view_paper":"https://pith.science/paper/BCMJWOEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1503.01817&json=true","fetch_graph":"https://pith.science/api/pith-number/BCMJWOEPQKZLT2NIFAX3XC2DFD/graph.json","fetch_events":"https://pith.science/api/pith-number/BCMJWOEPQKZLT2NIFAX3XC2DFD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD/action/storage_attestation","attest_author":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD/action/author_attestation","sign_citation":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD/action/citation_signature","submit_replication":"https://pith.science/pith/BCMJWOEPQKZLT2NIFAX3XC2DFD/action/replication_record"}},"created_at":"2026-05-18T01:16:21.795575+00:00","updated_at":"2026-05-18T01:16:21.795575+00:00"}