{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NEITGKFTEFEYFFLPC263WZC4YU","short_pith_number":"pith:NEITGKFT","schema_version":"1.0","canonical_sha256":"69113328b3214982956f16bdbb645cc5337f7d8cad406f1e524f3409ff4085be","source":{"kind":"arxiv","id":"2605.15723","version":1},"attestation_state":"computed","paper":{"title":"GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guoren Wang, Rong-Hua Li, Xunkai Li, Xu Wang, Yinlin Zhu","submitted_at":"2026-05-15T08:21:22Z","abstract_excerpt":"Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes and edges encode corpus structure, provide a natural setting for refining frozen vision-language embeddings. This refinement is challenging: visual, textual, and cross-modal relations often induce different neighborhood geometries, while unrestricted graph propagation can quickly over-smooth retrieval representations. Effectively leveraging graph context th"},"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":"2605.15723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T08:21:22Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"70c9fa88bed753654c38de9739719b510b85fe580d5c6c6997134ef174666751","abstract_canon_sha256":"958c226acf51ff2368a2669d2e01361fe2ca7cc9527574554036c192f29e7039"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:14.807668Z","signature_b64":"SyTGnXJNLR9PNrACccgbY3ubCvqAEvQRPgrzPQFlAtW1fhh//xK8my+Jh21iFbGLZb5FMPBch11OmqQSkmldDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69113328b3214982956f16bdbb645cc5337f7d8cad406f1e524f3409ff4085be","last_reissued_at":"2026-05-20T00:01:14.806699Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:14.806699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Guoren Wang, Rong-Hua Li, Xunkai Li, Xu Wang, Yinlin Zhu","submitted_at":"2026-05-15T08:21:22Z","abstract_excerpt":"Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities largely unused. Multimodal attributed graphs (MAGs), where nodes carry multimodal attributes and edges encode corpus structure, provide a natural setting for refining frozen vision-language embeddings. This refinement is challenging: visual, textual, and cross-modal relations often induce different neighborhood geometries, while unrestricted graph propagation can quickly over-smooth retrieval representations. Effectively leveraging graph context th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15723","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/2605.15723/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:25.153815Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.003742Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c240daecee9c35aa8e0ccb3d704bb7c4ebc0d3a8bb8bee7d63a71b2b6cf7f834"},"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":"2605.15723","created_at":"2026-05-20T00:01:14.806837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15723v1","created_at":"2026-05-20T00:01:14.806837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15723","created_at":"2026-05-20T00:01:14.806837+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEITGKFTEFEY","created_at":"2026-05-20T00:01:14.806837+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEITGKFTEFEYFFLP","created_at":"2026-05-20T00:01:14.806837+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEITGKFT","created_at":"2026-05-20T00:01:14.806837+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/NEITGKFTEFEYFFLPC263WZC4YU","json":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU.json","graph_json":"https://pith.science/api/pith-number/NEITGKFTEFEYFFLPC263WZC4YU/graph.json","events_json":"https://pith.science/api/pith-number/NEITGKFTEFEYFFLPC263WZC4YU/events.json","paper":"https://pith.science/paper/NEITGKFT"},"agent_actions":{"view_html":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU","download_json":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU.json","view_paper":"https://pith.science/paper/NEITGKFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15723&json=true","fetch_graph":"https://pith.science/api/pith-number/NEITGKFTEFEYFFLPC263WZC4YU/graph.json","fetch_events":"https://pith.science/api/pith-number/NEITGKFTEFEYFFLPC263WZC4YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU/action/storage_attestation","attest_author":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU/action/author_attestation","sign_citation":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU/action/citation_signature","submit_replication":"https://pith.science/pith/NEITGKFTEFEYFFLPC263WZC4YU/action/replication_record"}},"created_at":"2026-05-20T00:01:14.806837+00:00","updated_at":"2026-05-20T00:01:14.806837+00:00"}