{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VPP52XC25AJ7VMJ3NW6KFRHFJY","short_pith_number":"pith:VPP52XC2","schema_version":"1.0","canonical_sha256":"abdfdd5c5ae813fab13b6dbca2c4e54e11f6f45743a4f4f22575c4ca5d399125","source":{"kind":"arxiv","id":"2606.26891","version":1},"attestation_state":"computed","paper":{"title":"Bridging Vision and Language Concepts through Optimal Transport Semantic Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anqi Dong, Chenyang Zhang, Guangming Zhu, Liang Zhang, Lin Mei, Nuoye Xiong, Siyuan Wang","submitted_at":"2026-06-25T11:24:44Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept alignment as a dynamic cross-modal transport process instead of static projection and propose the Optimal Transport Flow Concept Bottleneck Model ("},"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":"2606.26891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-25T11:24:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"67c5b8ad110253ddc7c5b7a5d57cd3fa5781442b7af665efd235cf54c51df09c","abstract_canon_sha256":"f5f0f63d9c04f1801349f74c54780172fbc1a244aec61125bbe4ed4204a5ff18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:03.214685Z","signature_b64":"L6/rmIjuLSUM9rZzV4/U7C8659BNnfGoYbxJmwj+78VlaPjApES52jAu5YlbllEi3qdB+pK652PPpDPSDgEcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abdfdd5c5ae813fab13b6dbca2c4e54e11f6f45743a4f4f22575c4ca5d399125","last_reissued_at":"2026-06-26T01:16:03.214267Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:03.214267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Vision and Language Concepts through Optimal Transport Semantic Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anqi Dong, Chenyang Zhang, Guangming Zhu, Liang Zhang, Lin Mei, Nuoye Xiong, Siyuan Wang","submitted_at":"2026-06-25T11:24:44Z","abstract_excerpt":"Concept Bottleneck Models (CBMs) promise transparent reasoning by predicting through human-interpretable concepts, yet their effectiveness fundamentally depends on how well visual and textual representations are aligned or matched. Existing vision-language CBMs often rely on pre-aligned encoders or global cosine similarity, which obscures fine-grained concept localization and fails to reflect true semantic geometry. In this work, we rethink concept alignment as a dynamic cross-modal transport process instead of static projection and propose the Optimal Transport Flow Concept Bottleneck Model ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26891","kind":"arxiv","version":1},"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/2606.26891/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":"2606.26891","created_at":"2026-06-26T01:16:03.214328+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26891v1","created_at":"2026-06-26T01:16:03.214328+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26891","created_at":"2026-06-26T01:16:03.214328+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPP52XC25AJ7","created_at":"2026-06-26T01:16:03.214328+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPP52XC25AJ7VMJ3","created_at":"2026-06-26T01:16:03.214328+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPP52XC2","created_at":"2026-06-26T01:16:03.214328+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY","json":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY.json","graph_json":"https://pith.science/api/pith-number/VPP52XC25AJ7VMJ3NW6KFRHFJY/graph.json","events_json":"https://pith.science/api/pith-number/VPP52XC25AJ7VMJ3NW6KFRHFJY/events.json","paper":"https://pith.science/paper/VPP52XC2"},"agent_actions":{"view_html":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY","download_json":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY.json","view_paper":"https://pith.science/paper/VPP52XC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26891&json=true","fetch_graph":"https://pith.science/api/pith-number/VPP52XC25AJ7VMJ3NW6KFRHFJY/graph.json","fetch_events":"https://pith.science/api/pith-number/VPP52XC25AJ7VMJ3NW6KFRHFJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY/action/storage_attestation","attest_author":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY/action/author_attestation","sign_citation":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY/action/citation_signature","submit_replication":"https://pith.science/pith/VPP52XC25AJ7VMJ3NW6KFRHFJY/action/replication_record"}},"created_at":"2026-06-26T01:16:03.214328+00:00","updated_at":"2026-06-26T01:16:03.214328+00:00"}