{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R7XZ2OCYHRGRVMXPV6G6VXGLFW","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":"6df51d32c6a628339c3aec7a6a3a131692e08bceb23c6fd4bde16eceb213171c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T15:04:56Z","title_canon_sha256":"1f0878e480361afaf1d5a35bccc3bec0b27dbdc2f53744e81502348f5c224325"},"schema_version":"1.0","source":{"id":"2605.21272","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21272","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21272v1","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21272","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"R7XZ2OCYHRGR","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"R7XZ2OCYHRGRVMXP","created_at":"2026-05-21T02:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"R7XZ2OCY","created_at":"2026-05-21T02:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:87c560a3eadd50dfea0efc6c5664cd7e8bf1f6f5ac9a0b8ae20bf68a206f5141","target":"graph","created_at":"2026-05-21T02:05:26Z","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/2605.21272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin Aubin, Cl\\'ement Chadebec, Damien Henry, Gonzalo I\\~naki Quintana, Onur Tasar, Sanjeev Sreetharan, Urszula Czerwinska","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T15:04:56Z","title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21272","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":"sha256:3dfc5532b332e0dc331f3411646512e4af7da3e8a96da7d7cb7794b39c509888","target":"record","created_at":"2026-05-21T02:05:26Z","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":"6df51d32c6a628339c3aec7a6a3a131692e08bceb23c6fd4bde16eceb213171c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T15:04:56Z","title_canon_sha256":"1f0878e480361afaf1d5a35bccc3bec0b27dbdc2f53744e81502348f5c224325"},"schema_version":"1.0","source":{"id":"2605.21272","kind":"arxiv","version":1}},"canonical_sha256":"8fef9d38583c4d1ab2efaf8deadccb2db04d6883d08f0e0cc9ba048a078c2949","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fef9d38583c4d1ab2efaf8deadccb2db04d6883d08f0e0cc9ba048a078c2949","first_computed_at":"2026-05-21T02:05:26.102757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:26.102757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PV7QyJN2iNzZKtPO9cmgEcnPa4qHA/8ogLilfe2yRFC5qVUlIkrVpLBC/IfAhNnLtn7QXFHdYK2o4RrqskP9Dg==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:26.103761Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21272","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dfc5532b332e0dc331f3411646512e4af7da3e8a96da7d7cb7794b39c509888","sha256:87c560a3eadd50dfea0efc6c5664cd7e8bf1f6f5ac9a0b8ae20bf68a206f5141"],"state_sha256":"d3d91c147aeb116f32d4570c46edde542161e168702a0ac4392861bb5c0e85e2"}