{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RQ73J6PY6ZCXBZFPCAOPW5QKCF","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":"6a76f80000ffa898101722ec84ec50c6a6807748ff88106d43494df433435121","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T16:59:52Z","title_canon_sha256":"8ae6dd16a9b647aebf669b19d37530ff145b9063f4c0c230f9d3ca1302eab710"},"schema_version":"1.0","source":{"id":"2307.03132","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03132","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03132v2","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03132","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"pith_short_12","alias_value":"RQ73J6PY6ZCX","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"pith_short_16","alias_value":"RQ73J6PY6ZCXBZFP","created_at":"2026-07-05T07:57:41Z"},{"alias_kind":"pith_short_8","alias_value":"RQ73J6PY","created_at":"2026-07-05T07:57:41Z"}],"graph_snapshots":[{"event_id":"sha256:a2e5a80526fbde4bb2b079764c14e0b6ee6cf36ba680c65bf9c2f3f2f7b59c93","target":"graph","created_at":"2026-07-05T07:57:41Z","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/2307.03132/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large web-sourced multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial decision facing practitioners is how, if at all, to curate these ever-larger datasets. For example, the creators of the LAION-5B dataset chose to retain only image-caption pairs whose CLIP similarity score exceeded a designated threshold. In this paper, we propose a new state-of-the-art data filtering approach motivated by our observation that nearly 40% of ","authors_text":"Aditi Raghunathan, J. Zico Kolter, Pratyush Maini, Sachin Goyal, Zachary C. Lipton","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T16:59:52Z","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03132","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":"sha256:6c90841199234385c5013aa4666a91b2be35511675a65387478bc0e40b853c39","target":"record","created_at":"2026-07-05T07:57:41Z","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":"6a76f80000ffa898101722ec84ec50c6a6807748ff88106d43494df433435121","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-06T16:59:52Z","title_canon_sha256":"8ae6dd16a9b647aebf669b19d37530ff145b9063f4c0c230f9d3ca1302eab710"},"schema_version":"1.0","source":{"id":"2307.03132","kind":"arxiv","version":2}},"canonical_sha256":"8c3fb4f9f8f64570e4af101cfb760a1157dca8701e3d3097cbe06d8717bdab36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c3fb4f9f8f64570e4af101cfb760a1157dca8701e3d3097cbe06d8717bdab36","first_computed_at":"2026-07-05T07:57:41.669639Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:41.669639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wzvwQuZgb+nm0KlqfnyGFstXhktsbqSd76KJ8fF+o/2GnXL+snEsV6TQ7pWHpfKANG4YGn8GESG/NgC48MNGDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:41.670131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03132","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c90841199234385c5013aa4666a91b2be35511675a65387478bc0e40b853c39","sha256:a2e5a80526fbde4bb2b079764c14e0b6ee6cf36ba680c65bf9c2f3f2f7b59c93"],"state_sha256":"9e851e8c1ff644aa11dc4bc3cec7a2428c0f218617c8321a350159a5c364bf6f"}