{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YIPEZCXWYG3VKCH7XY3ISEXEGZ","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":"1d9d3653ea49eff9ededd5bad0943931257790b76c1bff72114a614429242de0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T01:37:48Z","title_canon_sha256":"22a573e46f964af3749229740c664a7ce0fd8d990d78a1771f74e4a6d87a4781"},"schema_version":"1.0","source":{"id":"2211.13854","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13854","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13854v5","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13854","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"pith_short_12","alias_value":"YIPEZCXWYG3V","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"pith_short_16","alias_value":"YIPEZCXWYG3VKCH7","created_at":"2026-07-05T08:07:26Z"},{"alias_kind":"pith_short_8","alias_value":"YIPEZCXW","created_at":"2026-07-05T08:07:26Z"}],"graph_snapshots":[{"event_id":"sha256:9cb597b198cc5b4fdec29a6b20b67395f64747a3271c0b36e4b832860d995316","target":"graph","created_at":"2026-07-05T08:07:26Z","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/2211.13854/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text matching -- a more challenging image and text matching task requiring the model understanding of compositional word concepts and visual components. Towards better compositional generalization in zero-shot image and text matching, in this paper, we study the problem from a causal perspective: the erroneous semantics of individual entities are essentially conf","authors_text":"Kenan Jiang, Ruize Xu, Xin Eric Wang, Xuehai He","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T01:37:48Z","title":"ComCLIP: Training-Free Compositional Image and Text Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13854","kind":"arxiv","version":5},"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":"sha256:3d631917546efa7a7248fd7b2b09e46f4a2357d89debdc256516b686cdb58abe","target":"record","created_at":"2026-07-05T08:07:26Z","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":"1d9d3653ea49eff9ededd5bad0943931257790b76c1bff72114a614429242de0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T01:37:48Z","title_canon_sha256":"22a573e46f964af3749229740c664a7ce0fd8d990d78a1771f74e4a6d87a4781"},"schema_version":"1.0","source":{"id":"2211.13854","kind":"arxiv","version":5}},"canonical_sha256":"c21e4c8af6c1b75508ffbe368912e4367175f6b2bbac4aa9cc3aa8c1811d5389","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c21e4c8af6c1b75508ffbe368912e4367175f6b2bbac4aa9cc3aa8c1811d5389","first_computed_at":"2026-07-05T08:07:26.410326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:26.410326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h7ymjgng8bTfX/SVyRLJtQ3OJKB5Atiij4+tMk1sNy5TutTxxfy6xP7QdErgFV9cJ5PhMAVpTMnp3+brPZm7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:26.410808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13854","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d631917546efa7a7248fd7b2b09e46f4a2357d89debdc256516b686cdb58abe","sha256:9cb597b198cc5b4fdec29a6b20b67395f64747a3271c0b36e4b832860d995316"],"state_sha256":"02ca9aecb415d00fc46b93dd62d3a45b8e39de0512d26c4e67a2232b4fc4384c"}