{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YIPEZCXWYG3VKCH7XY3ISEXEGZ","short_pith_number":"pith:YIPEZCXW","schema_version":"1.0","canonical_sha256":"c21e4c8af6c1b75508ffbe368912e4367175f6b2bbac4aa9cc3aa8c1811d5389","source":{"kind":"arxiv","id":"2211.13854","version":5},"attestation_state":"computed","paper":{"title":"ComCLIP: Training-Free Compositional Image and Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Kenan Jiang, Ruize Xu, Xin Eric Wang, Xuehai He","submitted_at":"2022-11-25T01:37:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.13854","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-25T01:37:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"22a573e46f964af3749229740c664a7ce0fd8d990d78a1771f74e4a6d87a4781","abstract_canon_sha256":"1d9d3653ea49eff9ededd5bad0943931257790b76c1bff72114a614429242de0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:26.410808Z","signature_b64":"h7ymjgng8bTfX/SVyRLJtQ3OJKB5Atiij4+tMk1sNy5TutTxxfy6xP7QdErgFV9cJ5PhMAVpTMnp3+brPZm7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c21e4c8af6c1b75508ffbe368912e4367175f6b2bbac4aa9cc3aa8c1811d5389","last_reissued_at":"2026-07-05T08:07:26.410326Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:26.410326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComCLIP: Training-Free Compositional Image and Text Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Kenan Jiang, Ruize Xu, Xin Eric Wang, Xuehai He","submitted_at":"2022-11-25T01:37:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13854","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.13854/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.13854","created_at":"2026-07-05T08:07:26.410388+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.13854v5","created_at":"2026-07-05T08:07:26.410388+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13854","created_at":"2026-07-05T08:07:26.410388+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIPEZCXWYG3V","created_at":"2026-07-05T08:07:26.410388+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIPEZCXWYG3VKCH7","created_at":"2026-07-05T08:07:26.410388+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIPEZCXW","created_at":"2026-07-05T08:07:26.410388+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.23370","citing_title":"GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ","json":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ.json","graph_json":"https://pith.science/api/pith-number/YIPEZCXWYG3VKCH7XY3ISEXEGZ/graph.json","events_json":"https://pith.science/api/pith-number/YIPEZCXWYG3VKCH7XY3ISEXEGZ/events.json","paper":"https://pith.science/paper/YIPEZCXW"},"agent_actions":{"view_html":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ","download_json":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ.json","view_paper":"https://pith.science/paper/YIPEZCXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.13854&json=true","fetch_graph":"https://pith.science/api/pith-number/YIPEZCXWYG3VKCH7XY3ISEXEGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YIPEZCXWYG3VKCH7XY3ISEXEGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ/action/storage_attestation","attest_author":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ/action/author_attestation","sign_citation":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ/action/citation_signature","submit_replication":"https://pith.science/pith/YIPEZCXWYG3VKCH7XY3ISEXEGZ/action/replication_record"}},"created_at":"2026-07-05T08:07:26.410388+00:00","updated_at":"2026-07-05T08:07:26.410388+00:00"}