{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CURRT7UF34SUY4ZCRHCNZ2C6T","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":"598f07d3b6332a9191ed7bef5d2ed883fe53b87218e6b1057a8e1b6e5e1f92b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T14:32:24Z","title_canon_sha256":"ca178cdba984b9ed28cafb8a45e01c9021cac248db966b61abbe8a65af10dc80"},"schema_version":"1.0","source":{"id":"2410.01594","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01594","created_at":"2026-07-05T09:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01594v1","created_at":"2026-07-05T09:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01594","created_at":"2026-07-05T09:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"6CURRT7UF34S","created_at":"2026-07-05T09:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"6CURRT7UF34SUY4Z","created_at":"2026-07-05T09:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"6CURRT7U","created_at":"2026-07-05T09:14:49Z"}],"graph_snapshots":[{"event_id":"sha256:c429d9bff8f97d0ba23589239f7bbf3e8cef93fbea6df03597bb229638cdb5ce","target":"graph","created_at":"2026-07-05T09:14:49Z","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/2410.01594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sounding Video Generation (SVG) is an audio-video joint generation task challenged by high-dimensional signal spaces, distinct data formats, and different patterns of content information. To address these issues, we introduce a novel multi-modal latent diffusion model (MM-LDM) for the SVG task. We first unify the representation of audio and video data by converting them into a single or a couple of images. Then, we introduce a hierarchical multi-modal autoencoder that constructs a low-level perceptual latent space for each modality and a shared high-level semantic feature space. The former spa","authors_text":"Jiahui Sun, Jing Liu, Longteng Guo, Mingzhen Sun, Weining Wang, Xinxin Zhu, Yanyuan Qiao, Zihan Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T14:32:24Z","title":"MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01594","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":"sha256:0b6c49816199f3a7bdf187185c21d6c819e12e5a317b0ff77e79be34df58d7f2","target":"record","created_at":"2026-07-05T09:14:49Z","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":"598f07d3b6332a9191ed7bef5d2ed883fe53b87218e6b1057a8e1b6e5e1f92b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-02T14:32:24Z","title_canon_sha256":"ca178cdba984b9ed28cafb8a45e01c9021cac248db966b61abbe8a65af10dc80"},"schema_version":"1.0","source":{"id":"2410.01594","kind":"arxiv","version":1}},"canonical_sha256":"f0a918cff42ef92a6399144e26e742f4f9e0b39bec60f25de9da53663ce413d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0a918cff42ef92a6399144e26e742f4f9e0b39bec60f25de9da53663ce413d1","first_computed_at":"2026-07-05T09:14:49.699394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:49.699394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EMgFWIki5itjqIgiORcAbWEUvT1c0OWa1jPHBNy57PnojLFuJIk41KLsSPP72FOtbOpKq6tgRWP1TopNEwKlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:49.699755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01594","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b6c49816199f3a7bdf187185c21d6c819e12e5a317b0ff77e79be34df58d7f2","sha256:c429d9bff8f97d0ba23589239f7bbf3e8cef93fbea6df03597bb229638cdb5ce"],"state_sha256":"89e9d8ad4491fbf21c052a3915e3f22b5f4428804457b96d899b74f6d19dde64"}