{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7BJ2K2YLIWCL6KTGP6IGRJBHU6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0dea45b50e92a8a79a4c58519d0f4bb4ff66b4aca2fad022323bf2888944d2a1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T07:51:01Z","title_canon_sha256":"de3aed9244ac95ba819c48b24d01f6a8894941d0dce8a43367b13e3d94778011"},"schema_version":"1.0","source":{"id":"2507.10015","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10015","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10015v3","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10015","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_12","alias_value":"7BJ2K2YLIWCL","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_16","alias_value":"7BJ2K2YLIWCL6KTG","created_at":"2026-07-05T11:38:31Z"},{"alias_kind":"pith_short_8","alias_value":"7BJ2K2YL","created_at":"2026-07-05T11:38:31Z"}],"graph_snapshots":[{"event_id":"sha256:af0d4fb034efda9bd569c54be1e14efcf00447ff8a0090b4036fe6754254f50c","target":"graph","created_at":"2026-07-05T11:38:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.10015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Antonio Orvieto, Boris Knyazev, Diganta Misra, Jaisidh Singh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T07:51:01Z","title":"(Almost) Free Modality Stitching of Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10015","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:968bd16d7fd4f16962bff191ed8e2928bd372b06dccfaaed921c47c56f7c7f7b","target":"record","created_at":"2026-07-05T11:38:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0dea45b50e92a8a79a4c58519d0f4bb4ff66b4aca2fad022323bf2888944d2a1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T07:51:01Z","title_canon_sha256":"de3aed9244ac95ba819c48b24d01f6a8894941d0dce8a43367b13e3d94778011"},"schema_version":"1.0","source":{"id":"2507.10015","kind":"arxiv","version":3}},"canonical_sha256":"f853a56b0b4584bf2a667f9068a427a7b21e05c4795f1d147239aee0ff23c09e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f853a56b0b4584bf2a667f9068a427a7b21e05c4795f1d147239aee0ff23c09e","first_computed_at":"2026-07-05T11:38:31.730750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:31.730750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q/bU/rF1beicX89GaAWqTWWLH54XGkMPjjSm9UlbbShXAwMZaYa2cPKB560oSyNsD/67bn8VDcRat3XSedp9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:31.731170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10015","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:968bd16d7fd4f16962bff191ed8e2928bd372b06dccfaaed921c47c56f7c7f7b","sha256:af0d4fb034efda9bd569c54be1e14efcf00447ff8a0090b4036fe6754254f50c"],"state_sha256":"71501e78e159280897cb73d0179d7ea90d23c8533570355daefd7c03dd210d70"}