{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R7XZ2OCYHRGRVMXPV6G6VXGLFW","short_pith_number":"pith:R7XZ2OCY","schema_version":"1.0","canonical_sha256":"8fef9d38583c4d1ab2efaf8deadccb2db04d6883d08f0e0cc9ba048a078c2949","source":{"kind":"arxiv","id":"2605.21272","version":1},"attestation_state":"computed","paper":{"title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Aubin, Cl\\'ement Chadebec, Damien Henry, Gonzalo I\\~naki Quintana, Onur Tasar, Sanjeev Sreetharan, Urszula Czerwinska","submitted_at":"2026-05-20T15:04:56Z","abstract_excerpt":"Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, deduplicating, and re-captioning such corpora at scale hinders open and reproducible research in the field. We introduce MONET, an open Apache 2.0 dataset of approx. 104.9M image--text pairs collected from 2.9B raw pairs across heterogeneous open sources through successive stages of safety filtering, domain-based filtering, exact and near-duplicate removal, and re-captioning with multiple vision-language models covering sh"},"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":"2605.21272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T15:04:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f0878e480361afaf1d5a35bccc3bec0b27dbdc2f53744e81502348f5c224325","abstract_canon_sha256":"6df51d32c6a628339c3aec7a6a3a131692e08bceb23c6fd4bde16eceb213171c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:26.103761Z","signature_b64":"PV7QyJN2iNzZKtPO9cmgEcnPa4qHA/8ogLilfe2yRFC5qVUlIkrVpLBC/IfAhNnLtn7QXFHdYK2o4RrqskP9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fef9d38583c4d1ab2efaf8deadccb2db04d6883d08f0e0cc9ba048a078c2949","last_reissued_at":"2026-05-21T02:05:26.102757Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:26.102757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benjamin Aubin, Cl\\'ement Chadebec, Damien Henry, Gonzalo I\\~naki Quintana, Onur Tasar, Sanjeev Sreetharan, Urszula Czerwinska","submitted_at":"2026-05-20T15:04:56Z","abstract_excerpt":"Training large text-to-image models requires high-quality, curated datasets with diverse content and detailed captions. Yet the cost and complexity of collecting, filtering, deduplicating, and re-captioning such corpora at scale hinders open and reproducible research in the field. We introduce MONET, an open Apache 2.0 dataset of approx. 104.9M image--text pairs collected from 2.9B raw pairs across heterogeneous open sources through successive stages of safety filtering, domain-based filtering, exact and near-duplicate removal, and re-captioning with multiple vision-language models covering sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21272","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/2605.21272/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.21272","created_at":"2026-05-21T02:05:26.102910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21272v1","created_at":"2026-05-21T02:05:26.102910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21272","created_at":"2026-05-21T02:05:26.102910+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7XZ2OCYHRGR","created_at":"2026-05-21T02:05:26.102910+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7XZ2OCYHRGRVMXP","created_at":"2026-05-21T02:05:26.102910+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7XZ2OCY","created_at":"2026-05-21T02:05:26.102910+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW","json":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW.json","graph_json":"https://pith.science/api/pith-number/R7XZ2OCYHRGRVMXPV6G6VXGLFW/graph.json","events_json":"https://pith.science/api/pith-number/R7XZ2OCYHRGRVMXPV6G6VXGLFW/events.json","paper":"https://pith.science/paper/R7XZ2OCY"},"agent_actions":{"view_html":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW","download_json":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW.json","view_paper":"https://pith.science/paper/R7XZ2OCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21272&json=true","fetch_graph":"https://pith.science/api/pith-number/R7XZ2OCYHRGRVMXPV6G6VXGLFW/graph.json","fetch_events":"https://pith.science/api/pith-number/R7XZ2OCYHRGRVMXPV6G6VXGLFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW/action/storage_attestation","attest_author":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW/action/author_attestation","sign_citation":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW/action/citation_signature","submit_replication":"https://pith.science/pith/R7XZ2OCYHRGRVMXPV6G6VXGLFW/action/replication_record"}},"created_at":"2026-05-21T02:05:26.102910+00:00","updated_at":"2026-05-21T02:05:26.102910+00:00"}