{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VUGFVPTOPZPAQQ24F25Y54LKVU","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":"322c2fb9e5ca0eec3c7db100e2dc15a34218e42053a41a7925c2f2123d0ec78f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T18:56:18Z","title_canon_sha256":"534e5a3a00fe12e37dda67fcc99a8d27d35241efc6cf5ac5ad8a25b24fba755f"},"schema_version":"1.0","source":{"id":"2502.13133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.13133","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2502.13133v1","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13133","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"VUGFVPTOPZPA","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"VUGFVPTOPZPAQQ24","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"VUGFVPTO","created_at":"2026-07-05T10:16:30Z"}],"graph_snapshots":[{"event_id":"sha256:efe39a3485a601598b9b4859d4b44b7989ae2744a7f52bdfae56ab6fd0069741","target":"graph","created_at":"2026-07-05T10:16:30Z","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/2502.13133/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce AV-Flow, an audio-visual generative model that animates photo-realistic 4D talking avatars given only text input. In contrast to prior work that assumes an existing speech signal, we synthesize speech and vision jointly. We demonstrate human-like speech synthesis, synchronized lip motion, lively facial expressions and head pose; all generated from just text characters. The core premise of our approach lies in the architecture of our two parallel diffusion transformers. Intermediate highway connections ensure communication between the audio and visual modalities, and thus, synchron","authors_text":"Aggelina Chatziagapi, Alexander Richard, Dimitris Samaras, Hongyu Gong, Louis-Philippe Morency, Michael Zollhoefer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T18:56:18Z","title":"AV-Flow: Transforming Text to Audio-Visual Human-like Interactions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13133","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":"sha256:3dc9d7edafb1b4a948c745719518238fc74fd9b6645fe43187f2ce4b97f2cb1e","target":"record","created_at":"2026-07-05T10:16:30Z","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":"322c2fb9e5ca0eec3c7db100e2dc15a34218e42053a41a7925c2f2123d0ec78f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-18T18:56:18Z","title_canon_sha256":"534e5a3a00fe12e37dda67fcc99a8d27d35241efc6cf5ac5ad8a25b24fba755f"},"schema_version":"1.0","source":{"id":"2502.13133","kind":"arxiv","version":1}},"canonical_sha256":"ad0c5abe6e7e5e08435c2ebb8ef16aad250fb0db2150023bfb17691ddce671b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad0c5abe6e7e5e08435c2ebb8ef16aad250fb0db2150023bfb17691ddce671b3","first_computed_at":"2026-07-05T10:16:30.042960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:30.042960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"33xlm7NVsZQTz2GuP/iJmrD5x64ZLSmcfb3/i5R6pB+cXtVdwHW/Fy8mkaS2ftuyQuUsR3J2JOFNugeHTj78CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:30.043455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.13133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3dc9d7edafb1b4a948c745719518238fc74fd9b6645fe43187f2ce4b97f2cb1e","sha256:efe39a3485a601598b9b4859d4b44b7989ae2744a7f52bdfae56ab6fd0069741"],"state_sha256":"6983cfeabb88d97339976e6a2054818a7c543b0f2a2662cc3cba67858328eb79"}