{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5S4CVV7Z26GBF3JRTLTNHGPGCJ","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":"01c72a358c5cf445a39a9485face6e7b0a52c5a23bbae61c07453af7400ea976","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T17:55:15Z","title_canon_sha256":"0a85ded6f19b2c1863483e69f417e1dc8e06241d29cfa6b72b231f5a64b9bc7c"},"schema_version":"1.0","source":{"id":"2607.15265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15265","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15265v1","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15265","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"5S4CVV7Z26GB","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"5S4CVV7Z26GBF3JR","created_at":"2026-07-17T01:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"5S4CVV7Z","created_at":"2026-07-17T01:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:75e966d90c229da350b7e65a99b63f3949bf97913c174480047703d403533a28","target":"graph","created_at":"2026-07-17T01:22:17Z","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/2607.15265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SceneBind, an omni-modal representation of realistic scenes with joint semantic and 3D spatial understanding across vision, audio and language. Existing omni-modal encoders excel at instance-level semantics (i.e., what is present), but often lack explicit spatial structure (i.e., where it is). SceneBind addresses this gap by representing each scene as a semantic-spatial entity, combining a global semantic embedding with object-centric semantic-spatial slots. This representation explicitly captures object-level semantics, spatial attributes, and uncertainty. We further propose SceneB","authors_text":"Eli Shlizerman, Hyeonggon Ryu, Mingfei Chen, Ruoke Zhang, Zijun Cui","cross_cats":["cs.AI","cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T17:55:15Z","title":"SceneBind: Binding What and Where Across Vision, Audio and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15265","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":"sha256:1d70a337efe4777f48df8519ac20827f9e55e08cdf4c74f9dbf05879186bd0c1","target":"record","created_at":"2026-07-17T01:22:17Z","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":"01c72a358c5cf445a39a9485face6e7b0a52c5a23bbae61c07453af7400ea976","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T17:55:15Z","title_canon_sha256":"0a85ded6f19b2c1863483e69f417e1dc8e06241d29cfa6b72b231f5a64b9bc7c"},"schema_version":"1.0","source":{"id":"2607.15265","kind":"arxiv","version":1}},"canonical_sha256":"ecb82ad7f9d78c12ed319ae6d399e61263b481aee16942df3c46b43301cb165e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ecb82ad7f9d78c12ed319ae6d399e61263b481aee16942df3c46b43301cb165e","first_computed_at":"2026-07-17T01:22:17.532887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:17.532887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sra7QhLTeIurYF1kBILKs3z9CcMKXfdIMm1Wq/vPRp0hcXv3j+RZy/O4COG28lG/3j/bpaHnQE8R3fJW0DkgAA==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:17.533733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d70a337efe4777f48df8519ac20827f9e55e08cdf4c74f9dbf05879186bd0c1","sha256:75e966d90c229da350b7e65a99b63f3949bf97913c174480047703d403533a28"],"state_sha256":"31531fdfa2abdf7c40963a0c6efd635e58a5733d0aac776c760749bf0185bf50"}