{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BQ6SYUPFHAC53HXZ6WZ7IMD5GK","short_pith_number":"pith:BQ6SYUPF","schema_version":"1.0","canonical_sha256":"0c3d2c51e53805dd9ef9f5b3f4307d32a0398b16d5492e799e124d75507dfdaf","source":{"kind":"arxiv","id":"2505.12322","version":1},"attestation_state":"computed","paper":{"title":"Model alignment using inter-modal bridges","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ali Gholamzadeh, Noor Sajid","submitted_at":"2025-05-18T09:30:02Z","abstract_excerpt":"Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal representations. Existing methods require extensive paired training data or are constrained to specific domains. We introduce a semi-supervised approach for model alignment via conditional flow matching. The conditional flow between latent spaces of different modalities (e.g., text-to-image or biological-to-artificial neuronal activity) can be learned in two se"},"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":"2505.12322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-18T09:30:02Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"cf1da5d9e9e52742af2dfba2f77377ec5840a7f2ef514d064cf34f23e78c6a7f","abstract_canon_sha256":"3ce749eb8b9bddeec39fc3bd227986d20bee58aa06a27c0add580b008c316f86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:02.268181Z","signature_b64":"rLIRIUy5v6S5o2yHppqq/Nso1AEj9gdpWQXZ7zS+EhiBOXgnOMZkK6xNpMWScOkWd2DI20ArKMZe16TBJXqrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c3d2c51e53805dd9ef9f5b3f4307d32a0398b16d5492e799e124d75507dfdaf","last_reissued_at":"2026-07-05T11:05:02.267660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:02.267660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model alignment using inter-modal bridges","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ali Gholamzadeh, Noor Sajid","submitted_at":"2025-05-18T09:30:02Z","abstract_excerpt":"Foundation models have demonstrated remarkable performance across modalities such as language and vision. However, model reuse across distinct modalities (e.g., text and vision) remains limited due to the difficulty of aligning internal representations. Existing methods require extensive paired training data or are constrained to specific domains. We introduce a semi-supervised approach for model alignment via conditional flow matching. The conditional flow between latent spaces of different modalities (e.g., text-to-image or biological-to-artificial neuronal activity) can be learned in two se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12322","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/2505.12322/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":"2505.12322","created_at":"2026-07-05T11:05:02.267721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12322v1","created_at":"2026-07-05T11:05:02.267721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12322","created_at":"2026-07-05T11:05:02.267721+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ6SYUPFHAC5","created_at":"2026-07-05T11:05:02.267721+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ6SYUPFHAC53HXZ","created_at":"2026-07-05T11:05:02.267721+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ6SYUPF","created_at":"2026-07-05T11:05:02.267721+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/BQ6SYUPFHAC53HXZ6WZ7IMD5GK","json":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK.json","graph_json":"https://pith.science/api/pith-number/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/graph.json","events_json":"https://pith.science/api/pith-number/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/events.json","paper":"https://pith.science/paper/BQ6SYUPF"},"agent_actions":{"view_html":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK","download_json":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK.json","view_paper":"https://pith.science/paper/BQ6SYUPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12322&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/action/storage_attestation","attest_author":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/action/author_attestation","sign_citation":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/action/citation_signature","submit_replication":"https://pith.science/pith/BQ6SYUPFHAC53HXZ6WZ7IMD5GK/action/replication_record"}},"created_at":"2026-07-05T11:05:02.267721+00:00","updated_at":"2026-07-05T11:05:02.267721+00:00"}