{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7BJ2K2YLIWCL6KTGP6IGRJBHU6","short_pith_number":"pith:7BJ2K2YL","schema_version":"1.0","canonical_sha256":"f853a56b0b4584bf2a667f9068a427a7b21e05c4795f1d147239aee0ff23c09e","source":{"kind":"arxiv","id":"2507.10015","version":3},"attestation_state":"computed","paper":{"title":"(Almost) Free Modality Stitching of Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Orvieto, Boris Knyazev, Diganta Misra, Jaisidh Singh","submitted_at":"2025-07-14T07:51:01Z","abstract_excerpt":"Foundation multi-modal models are often designed by stitching of multiple existing pretrained uni-modal models: for example, an image classifier with an text model. This stitching process is performed by training a connector module that aims to align the representation spaces of these uni-modal models towards a multi-modal objective. However, given the complexity of training such connectors on large scale web-based datasets coupled with the ever-increasing number of available pretrained uni-modal models, the task of uni-modal models selection and subsequent connector module training becomes co"},"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":"2507.10015","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T07:51:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"de3aed9244ac95ba819c48b24d01f6a8894941d0dce8a43367b13e3d94778011","abstract_canon_sha256":"0dea45b50e92a8a79a4c58519d0f4bb4ff66b4aca2fad022323bf2888944d2a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:31.731170Z","signature_b64":"Q/bU/rF1beicX89GaAWqTWWLH54XGkMPjjSm9UlbbShXAwMZaYa2cPKB560oSyNsD/67bn8VDcRat3XSedp9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f853a56b0b4584bf2a667f9068a427a7b21e05c4795f1d147239aee0ff23c09e","last_reissued_at":"2026-07-05T11:38:31.730750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:31.730750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"(Almost) Free Modality Stitching of Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Orvieto, Boris Knyazev, Diganta Misra, Jaisidh Singh","submitted_at":"2025-07-14T07:51:01Z","abstract_excerpt":"Foundation multi-modal models are often designed by stitching of multiple existing pretrained uni-modal models: for example, an image classifier with an text model. This stitching process is performed by training a connector module that aims to align the representation spaces of these uni-modal models towards a multi-modal objective. However, given the complexity of training such connectors on large scale web-based datasets coupled with the ever-increasing number of available pretrained uni-modal models, the task of uni-modal models selection and subsequent connector module training becomes co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10015","kind":"arxiv","version":3},"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/2507.10015/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":"2507.10015","created_at":"2026-07-05T11:38:31.730806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10015v3","created_at":"2026-07-05T11:38:31.730806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10015","created_at":"2026-07-05T11:38:31.730806+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BJ2K2YLIWCL","created_at":"2026-07-05T11:38:31.730806+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BJ2K2YLIWCL6KTG","created_at":"2026-07-05T11:38:31.730806+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BJ2K2YL","created_at":"2026-07-05T11:38:31.730806+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/7BJ2K2YLIWCL6KTGP6IGRJBHU6","json":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6.json","graph_json":"https://pith.science/api/pith-number/7BJ2K2YLIWCL6KTGP6IGRJBHU6/graph.json","events_json":"https://pith.science/api/pith-number/7BJ2K2YLIWCL6KTGP6IGRJBHU6/events.json","paper":"https://pith.science/paper/7BJ2K2YL"},"agent_actions":{"view_html":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6","download_json":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6.json","view_paper":"https://pith.science/paper/7BJ2K2YL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10015&json=true","fetch_graph":"https://pith.science/api/pith-number/7BJ2K2YLIWCL6KTGP6IGRJBHU6/graph.json","fetch_events":"https://pith.science/api/pith-number/7BJ2K2YLIWCL6KTGP6IGRJBHU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6/action/storage_attestation","attest_author":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6/action/author_attestation","sign_citation":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6/action/citation_signature","submit_replication":"https://pith.science/pith/7BJ2K2YLIWCL6KTGP6IGRJBHU6/action/replication_record"}},"created_at":"2026-07-05T11:38:31.730806+00:00","updated_at":"2026-07-05T11:38:31.730806+00:00"}