{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EOYDJFMY3OG5RJJ6HE3HU2WGAT","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":"cf26403c9f5551794a082f32cffd11f305cfed8493a4be9eacf9163da222acba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T16:24:31Z","title_canon_sha256":"be5cb3ffcd0a20746835167b40a9158a8b3b8a39e45d5b280992667e80c4e158"},"schema_version":"1.0","source":{"id":"2407.11895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11895","created_at":"2026-07-05T08:44:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11895v1","created_at":"2026-07-05T08:44:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11895","created_at":"2026-07-05T08:44:42Z"},{"alias_kind":"pith_short_12","alias_value":"EOYDJFMY3OG5","created_at":"2026-07-05T08:44:42Z"},{"alias_kind":"pith_short_16","alias_value":"EOYDJFMY3OG5RJJ6","created_at":"2026-07-05T08:44:42Z"},{"alias_kind":"pith_short_8","alias_value":"EOYDJFMY","created_at":"2026-07-05T08:44:42Z"}],"graph_snapshots":[{"event_id":"sha256:71dfb5f2905fa7a7c9ed803f53d938d48471f5659a759a056eb21ade128a24b0","target":"graph","created_at":"2026-07-05T08:44:42Z","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/2407.11895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, human-computer interaction with various modalities has shown promising applications, like GPT-4o and Gemini. Given the foundational role of multimodal joint representation in understanding and generation pipelines, high-quality omni joint representations would be a step toward co-processing more diverse multimodal information. In this work, we present OmniBind, large-scale multimodal joint representation models ranging in scale from 7 billion to 30 billion parameters, which support 3D, audio, image, and language inputs. Due to the scarcity of data pairs across all modalities, instead","authors_text":"Hang Zhang, Hengshuang Zhao, Luping Liu, Rongjie Huang, Xize Cheng, Zehan Wang, Zhou Zhao, Ziang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T16:24:31Z","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11895","kind":"arxiv","version":1},"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":"sha256:805caf2941bc9d535c33a34173aa85f0f969a150182af2e668e94fbee4b10d86","target":"record","created_at":"2026-07-05T08:44:42Z","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":"cf26403c9f5551794a082f32cffd11f305cfed8493a4be9eacf9163da222acba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T16:24:31Z","title_canon_sha256":"be5cb3ffcd0a20746835167b40a9158a8b3b8a39e45d5b280992667e80c4e158"},"schema_version":"1.0","source":{"id":"2407.11895","kind":"arxiv","version":1}},"canonical_sha256":"23b0349598db8dd8a53e39367a6ac604dd06209a0b7195a287186137f70093ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23b0349598db8dd8a53e39367a6ac604dd06209a0b7195a287186137f70093ae","first_computed_at":"2026-07-05T08:44:42.192360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:42.192360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jLPpATsX4DJSZmPvvz4Xjtn9Zewzze6AyUXVVpLy5VXFqW4tgi5/YMGXIxyqN9ZtVC7nasnAx23rHMDUGGcpBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:42.192847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:805caf2941bc9d535c33a34173aa85f0f969a150182af2e668e94fbee4b10d86","sha256:71dfb5f2905fa7a7c9ed803f53d938d48471f5659a759a056eb21ade128a24b0"],"state_sha256":"e6bad70239e254e9db458df993d28bb9f26b343a49bd78ea8df704dcba5efcae"}