{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4WJ5WECERI2CEDMAGUPBWFGOCD","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":"01081846eabd48bb16b135d3b6b10fddd9c79ea1d0508816f472dfc7274286b1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T03:25:23Z","title_canon_sha256":"02b3f844775d876c9f61781e4a1f38ea70e6857030facadf34783dbc0c3a7067"},"schema_version":"1.0","source":{"id":"2412.11409","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11409","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11409v3","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11409","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"4WJ5WECERI2C","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"4WJ5WECERI2CEDMA","created_at":"2026-07-05T10:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"4WJ5WECE","created_at":"2026-07-05T10:01:18Z"}],"graph_snapshots":[{"event_id":"sha256:99b69eb5e229c5e07dd846c94c7f9b1b16f9e6b37b17449bd9979a25f9a8c0bf","target":"graph","created_at":"2026-07-05T10:01:18Z","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/2412.11409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Text-to-Speech (VTTS) aims to take the environmental image as the prompt to synthesize the reverberant speech for the spoken content. The challenge of this task lies in understanding the spatial environment from the image. Many attempts have been made to extract global spatial visual information from the RGB space of an spatial image. However, local and depth image information are crucial for understanding the spatial environment, which previous works have ignored. To address the issues, we propose a novel multi-modal and multi-scale spatial environment understanding scheme to achieve i","authors_text":"Haizhou Li, Rui Liu, Shuwei He, Yifan Hu","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T03:25:23Z","title":"Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11409","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":"sha256:6c5d9397a335f03dbbeda4ddaeed594ed9a18bf7009580999d9b80bddb28cd8f","target":"record","created_at":"2026-07-05T10:01:18Z","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":"01081846eabd48bb16b135d3b6b10fddd9c79ea1d0508816f472dfc7274286b1","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T03:25:23Z","title_canon_sha256":"02b3f844775d876c9f61781e4a1f38ea70e6857030facadf34783dbc0c3a7067"},"schema_version":"1.0","source":{"id":"2412.11409","kind":"arxiv","version":3}},"canonical_sha256":"e593db10448a34220d80351e1b14ce10dcb849e42aedbff7ac4e681a16526fb1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e593db10448a34220d80351e1b14ce10dcb849e42aedbff7ac4e681a16526fb1","first_computed_at":"2026-07-05T10:01:18.601415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:18.601415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5wWcL+OOWvlY+UcYZOS3reFJ+OrhzHZ6q1BFSddFXLlZksbULj02Y7qRH/9wpFkD3AoFE/KuJs0QgdH3OZ17DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:18.601886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11409","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c5d9397a335f03dbbeda4ddaeed594ed9a18bf7009580999d9b80bddb28cd8f","sha256:99b69eb5e229c5e07dd846c94c7f9b1b16f9e6b37b17449bd9979a25f9a8c0bf"],"state_sha256":"16d87b2f785a2e79c4fbee639cab12244c5cfc4a335403d78568a6c28b53b3bd"}