{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:C6ZED743RO4NN5DFEORDUZTHTA","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":"317f3cbd0653571722d7a5224101cd121f33a8fe0b61a63416a7497fab77f245","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T17:51:18Z","title_canon_sha256":"0450ca2f62d6c03572ab03e7ee617f1e3136bbd3be75a32ded18b92d8a16225b"},"schema_version":"1.0","source":{"id":"2306.07952","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07952","created_at":"2026-07-05T07:56:49Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07952v3","created_at":"2026-07-05T07:56:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07952","created_at":"2026-07-05T07:56:49Z"},{"alias_kind":"pith_short_12","alias_value":"C6ZED743RO4N","created_at":"2026-07-05T07:56:49Z"},{"alias_kind":"pith_short_16","alias_value":"C6ZED743RO4NN5DF","created_at":"2026-07-05T07:56:49Z"},{"alias_kind":"pith_short_8","alias_value":"C6ZED743","created_at":"2026-07-05T07:56:49Z"}],"graph_snapshots":[{"event_id":"sha256:3d48965d6133a75d9e1127050ea725ba15dde952ec85538cf8ca279a7dfc4088","target":"graph","created_at":"2026-07-05T07:56:49Z","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/2306.07952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MOFI, Manifold OF Images, a new vision foundation model designed to learn image representations from noisy entity annotated images. MOFI differs from previous work in two key aspects: (i) pre-training data, and (ii) training recipe. Regarding data, we introduce a new approach to automatically assign entity labels to images from noisy image-text pairs. Our approach involves employing a named entity recognition model to extract entities from the alt-text, and then using a CLIP model to select the correct entities as labels of the paired image. It's a simple, cost-effective method that","authors_text":"Aleksei Timofeev, Bowen Zhang, Chen Chen, Jonathon Shlens, Kun Duan, Shuangning Liu, Wentao Wu, Xianzhi Du, Yantao Zheng, Yinfei Yang, Zhe Gan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T17:51:18Z","title":"MOFI: Learning Image Representations from Noisy Entity Annotated Images"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07952","kind":"arxiv","version":3},"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:f90c8d15185b85a346c82bfae8ea977fa1c5ea7f27b0edb832d568dca7c953d1","target":"record","created_at":"2026-07-05T07:56:49Z","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":"317f3cbd0653571722d7a5224101cd121f33a8fe0b61a63416a7497fab77f245","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-13T17:51:18Z","title_canon_sha256":"0450ca2f62d6c03572ab03e7ee617f1e3136bbd3be75a32ded18b92d8a16225b"},"schema_version":"1.0","source":{"id":"2306.07952","kind":"arxiv","version":3}},"canonical_sha256":"17b241ff9b8bb8d6f46523a23a6667980cde84402b16fc63bc9a5c5e1e8eda53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17b241ff9b8bb8d6f46523a23a6667980cde84402b16fc63bc9a5c5e1e8eda53","first_computed_at":"2026-07-05T07:56:49.486105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:49.486105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QfJas0fmEceuWNVYsUrmD+TrDOJxkTiWvIpcirzTMG/D0vR24rXWeLHZ6HroHpqWNMfG9QqAyOkJHBTYjdExAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:49.486593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07952","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f90c8d15185b85a346c82bfae8ea977fa1c5ea7f27b0edb832d568dca7c953d1","sha256:3d48965d6133a75d9e1127050ea725ba15dde952ec85538cf8ca279a7dfc4088"],"state_sha256":"d0053772b57c8d00417fbd4c60fe472b97bcff664bef716f3c7fae677f46cc92"}