{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KHERICSVKBOTKDRDLHRFGB62PW","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":"b9a83539c34cb7376b03c669aafc6a0ff0d1015e09d2506ff159f7f9b175f04f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-30T11:27:58Z","title_canon_sha256":"b6e52f2b104f8719668ca4004b4936c31fc94c6cbd4a9201e7e22bf55dfcc4d5"},"schema_version":"1.0","source":{"id":"2412.00440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.00440","created_at":"2026-07-05T09:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.00440v1","created_at":"2026-07-05T09:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00440","created_at":"2026-07-05T09:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"KHERICSVKBOT","created_at":"2026-07-05T09:42:41Z"},{"alias_kind":"pith_short_16","alias_value":"KHERICSVKBOTKDRD","created_at":"2026-07-05T09:42:41Z"},{"alias_kind":"pith_short_8","alias_value":"KHERICSV","created_at":"2026-07-05T09:42:41Z"}],"graph_snapshots":[{"event_id":"sha256:bdb9b9db46fe476e6ffa70373ce24cd69708d9d69a397df4f32bf6584cf2d704","target":"graph","created_at":"2026-07-05T09:42:41Z","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/2412.00440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In rapidly evolving field of vision-language models (VLMs), contrastive language-image pre-training (CLIP) has made significant strides, becoming foundation for various downstream tasks. However, relying on one-to-one (image, text) contrastive paradigm to learn alignment from large-scale messy web data, CLIP faces a serious myopic dilemma, resulting in biases towards monotonous short texts and shallow visual expressivity. To overcome these issues, this paper advances CLIP into one novel holistic paradigm, by updating both diverse data and alignment optimization. To obtain colorful data with lo","authors_text":"Chang Liu, Chen Ju, Haicheng Wang, Jinsong Lan, Mengting Chen, Mingshuai Yao, Qingwen Liu, Shuai Xiao, Weixiong Lin, Yanfeng Wang, Ying Chen, Yixuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-30T11:27:58Z","title":"Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00440","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":"sha256:2b854d3136c261e6cd4c2f40b0cbeac5a18bf25c09f090854b8af0eca3b782f0","target":"record","created_at":"2026-07-05T09:42:41Z","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":"b9a83539c34cb7376b03c669aafc6a0ff0d1015e09d2506ff159f7f9b175f04f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-30T11:27:58Z","title_canon_sha256":"b6e52f2b104f8719668ca4004b4936c31fc94c6cbd4a9201e7e22bf55dfcc4d5"},"schema_version":"1.0","source":{"id":"2412.00440","kind":"arxiv","version":1}},"canonical_sha256":"51c9140a55505d350e2359e25307da7da3a527ca03dd4ebda4bb1745dab4043a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51c9140a55505d350e2359e25307da7da3a527ca03dd4ebda4bb1745dab4043a","first_computed_at":"2026-07-05T09:42:41.453778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:41.453778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Itf1i702z1NJ7/DGHDwGVFTT123Rex3WZwMSXyelRRizmcMTQelYrNDHasgNUlu3RhYhnaurJvpXV77RU0XOAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:41.454233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.00440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b854d3136c261e6cd4c2f40b0cbeac5a18bf25c09f090854b8af0eca3b782f0","sha256:bdb9b9db46fe476e6ffa70373ce24cd69708d9d69a397df4f32bf6584cf2d704"],"state_sha256":"dee3453dc01c147283c0175afa743585de234e39c40e7ac620f341ea78ebc15d"}