{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IKQ7JTYSP4KAOVPOOH7PHZCL3R","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":"9ba9b504541570c60f9188276d4fee31004b70dd6624f8d4c3fa2fb438a7b9ad","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-09T17:59:07Z","title_canon_sha256":"7153b3777b6dcff1035b04fc71d5a21543c7f427672cbfd82f0364b78100c148"},"schema_version":"1.0","source":{"id":"2305.05665","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.05665","created_at":"2026-07-05T06:15:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.05665v2","created_at":"2026-07-05T06:15:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.05665","created_at":"2026-07-05T06:15:46Z"},{"alias_kind":"pith_short_12","alias_value":"IKQ7JTYSP4KA","created_at":"2026-07-05T06:15:46Z"},{"alias_kind":"pith_short_16","alias_value":"IKQ7JTYSP4KAOVPO","created_at":"2026-07-05T06:15:46Z"},{"alias_kind":"pith_short_8","alias_value":"IKQ7JTYS","created_at":"2026-07-05T06:15:46Z"}],"graph_snapshots":[{"event_id":"sha256:5c2f2efb667ed29f74d87dded6a97c070256d3db15923fa525d2d0bbf47152d7","target":"graph","created_at":"2026-07-05T06:15:46Z","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/2305.05665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint embedding, and only image-paired data is sufficient to bind the modalities together. ImageBind can leverage recent large scale vision-language models, and extends their zero-shot capabilities to new modalities just by using their natural pairing with images. It enables novel emergent applications 'out-of-the-box' including cross-modal retrieval, composing modalities ","authors_text":"Alaaeldin El-Nouby, Armand Joulin, Ishan Misra, Kalyan Vasudev Alwala, Mannat Singh, Rohit Girdhar, Zhuang Liu","cross_cats":["cs.AI","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-09T17:59:07Z","title":"ImageBind: One Embedding Space To Bind Them All"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.05665","kind":"arxiv","version":2},"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:f9fdc9693ffb62b2576cbf36f8fa9bf90590a85951388e24e12372eafc3eae22","target":"record","created_at":"2026-07-05T06:15:46Z","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":"9ba9b504541570c60f9188276d4fee31004b70dd6624f8d4c3fa2fb438a7b9ad","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-09T17:59:07Z","title_canon_sha256":"7153b3777b6dcff1035b04fc71d5a21543c7f427672cbfd82f0364b78100c148"},"schema_version":"1.0","source":{"id":"2305.05665","kind":"arxiv","version":2}},"canonical_sha256":"42a1f4cf127f140755ee71fef3e44bdc43610650c7f73c4e7ff59b8af37eae57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42a1f4cf127f140755ee71fef3e44bdc43610650c7f73c4e7ff59b8af37eae57","first_computed_at":"2026-07-05T06:15:46.849769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:46.849769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"721GgEEVbp83HjxBs6MaIUwsF3v1r7JrJJ4eFbCts5Ev1PQ144xp7a+u+dfnexiIaea9V0/g+Ab4P+DSIXiSCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:46.850357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.05665","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9fdc9693ffb62b2576cbf36f8fa9bf90590a85951388e24e12372eafc3eae22","sha256:5c2f2efb667ed29f74d87dded6a97c070256d3db15923fa525d2d0bbf47152d7"],"state_sha256":"7a90be0747df124f919e5e85e02be02575e1ef7eccd819fcca2019eb42aca733"}