{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5S4CVV7Z26GBF3JRTLTNHGPGCJ","short_pith_number":"pith:5S4CVV7Z","schema_version":"1.0","canonical_sha256":"ecb82ad7f9d78c12ed319ae6d399e61263b481aee16942df3c46b43301cb165e","source":{"kind":"arxiv","id":"2607.15265","version":1},"attestation_state":"computed","paper":{"title":"SceneBind: Binding What and Where Across Vision, Audio and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Eli Shlizerman, Hyeonggon Ryu, Mingfei Chen, Ruoke Zhang, Zijun Cui","submitted_at":"2026-07-16T17:55:15Z","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"},"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":"2607.15265","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-16T17:55:15Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD"],"title_canon_sha256":"0a85ded6f19b2c1863483e69f417e1dc8e06241d29cfa6b72b231f5a64b9bc7c","abstract_canon_sha256":"01c72a358c5cf445a39a9485face6e7b0a52c5a23bbae61c07453af7400ea976"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:17.533733Z","signature_b64":"sra7QhLTeIurYF1kBILKs3z9CcMKXfdIMm1Wq/vPRp0hcXv3j+RZy/O4COG28lG/3j/bpaHnQE8R3fJW0DkgAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecb82ad7f9d78c12ed319ae6d399e61263b481aee16942df3c46b43301cb165e","last_reissued_at":"2026-07-17T01:22:17.532887Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:17.532887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SceneBind: Binding What and Where Across Vision, Audio and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD"],"primary_cat":"cs.CV","authors_text":"Eli Shlizerman, Hyeonggon Ryu, Mingfei Chen, Ruoke Zhang, Zijun Cui","submitted_at":"2026-07-16T17:55:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15265","kind":"arxiv","version":1},"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/2607.15265/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":"2607.15265","created_at":"2026-07-17T01:22:17.533327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.15265v1","created_at":"2026-07-17T01:22:17.533327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15265","created_at":"2026-07-17T01:22:17.533327+00:00"},{"alias_kind":"pith_short_12","alias_value":"5S4CVV7Z26GB","created_at":"2026-07-17T01:22:17.533327+00:00"},{"alias_kind":"pith_short_16","alias_value":"5S4CVV7Z26GBF3JR","created_at":"2026-07-17T01:22:17.533327+00:00"},{"alias_kind":"pith_short_8","alias_value":"5S4CVV7Z","created_at":"2026-07-17T01:22:17.533327+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/5S4CVV7Z26GBF3JRTLTNHGPGCJ","json":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ.json","graph_json":"https://pith.science/api/pith-number/5S4CVV7Z26GBF3JRTLTNHGPGCJ/graph.json","events_json":"https://pith.science/api/pith-number/5S4CVV7Z26GBF3JRTLTNHGPGCJ/events.json","paper":"https://pith.science/paper/5S4CVV7Z"},"agent_actions":{"view_html":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ","download_json":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ.json","view_paper":"https://pith.science/paper/5S4CVV7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.15265&json=true","fetch_graph":"https://pith.science/api/pith-number/5S4CVV7Z26GBF3JRTLTNHGPGCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/5S4CVV7Z26GBF3JRTLTNHGPGCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ/action/storage_attestation","attest_author":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ/action/author_attestation","sign_citation":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ/action/citation_signature","submit_replication":"https://pith.science/pith/5S4CVV7Z26GBF3JRTLTNHGPGCJ/action/replication_record"}},"created_at":"2026-07-17T01:22:17.533327+00:00","updated_at":"2026-07-17T01:22:17.533327+00:00"}