{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JMVGCJGTAWWAIJRS5NHCI2GB4W","short_pith_number":"pith:JMVGCJGT","canonical_record":{"source":{"id":"2503.08307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T11:18:47Z","cross_cats_sorted":[],"title_canon_sha256":"ccd275261141463d6ac80d8928117d42e76d0a1eb3bdff99a253cf585308738e","abstract_canon_sha256":"482d273d038534cd006ee5fb535bdc220d0a04279c27e6528afe5c265b131d25"},"schema_version":"1.0"},"canonical_sha256":"4b2a6124d305ac042632eb4e2468c1e583a0306070eea15b1c8d5d6e0b8884da","source":{"kind":"arxiv","id":"2503.08307","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08307","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08307v2","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08307","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"pith_short_12","alias_value":"JMVGCJGTAWWA","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"JMVGCJGTAWWAIJRS","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"JMVGCJGT","created_at":"2026-07-05T10:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JMVGCJGTAWWAIJRS5NHCI2GB4W","target":"record","payload":{"canonical_record":{"source":{"id":"2503.08307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T11:18:47Z","cross_cats_sorted":[],"title_canon_sha256":"ccd275261141463d6ac80d8928117d42e76d0a1eb3bdff99a253cf585308738e","abstract_canon_sha256":"482d273d038534cd006ee5fb535bdc220d0a04279c27e6528afe5c265b131d25"},"schema_version":"1.0"},"canonical_sha256":"4b2a6124d305ac042632eb4e2468c1e583a0306070eea15b1c8d5d6e0b8884da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:37.924078Z","signature_b64":"R1nmCir50efpuNRBJGWmJ2Eb2gMaT9WffmGR8qxPjLIhuRurzxArT1KMXv6M3J3s9smMwNUTI3Fqczr9zNplDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b2a6124d305ac042632eb4e2468c1e583a0306070eea15b1c8d5d6e0b8884da","last_reissued_at":"2026-07-05T10:29:37.923237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:37.923237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.08307","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FY30vZ9mW2j1RfFpGeXHKjI8pi1Z37y9A3y61Lyeklb0fEXvQzrN+KH/HENEbE0OpTwEN1xzR5OtlifHrtSjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:38:04.165597Z"},"content_sha256":"08417b7cabfc02596e191aede1b5f2db2e29807a16bbf15e1325e87476259774","schema_version":"1.0","event_id":"sha256:08417b7cabfc02596e191aede1b5f2db2e29807a16bbf15e1325e87476259774"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JMVGCJGTAWWAIJRS5NHCI2GB4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$^R$FLAV: Rolling Flow matching for infinite Audio Video generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Ergasti, Andrea Prati, Claudio Ferrari, Filippo Botti, Giuseppe Gabriele Tarollo, Massimo Bertozzi, Tomaso Fontanini","submitted_at":"2025-03-11T11:18:47Z","abstract_excerpt":"Joint audio-video (AV) generation is still a significant challenge in generative AI, primarily due to three critical requirements: quality of the generated samples, seamless multimodal synchronization and temporal coherence, with audio tracks that match the visual data and vice versa, and limitless video duration. In this paper, we present $^R$-FLAV, a novel transformer-based architecture that addresses all the key challenges of AV generation. We explore three distinct cross modality interaction modules, with our lightweight temporal fusion module emerging as the most effective and computation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08307","kind":"arxiv","version":2},"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/2503.08307/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W9uQx37AQxTb9iznLXY2rWDNjYDNse1px8jW7s81qv46FNJAhGBlFmtXm+P5xHnWomBpftOMztUpuxnrrj/XDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:38:04.166183Z"},"content_sha256":"613a9662a2b1ed8152452038d36a7d717ec43ab98a9c0bc77a431a6d9cc76f6e","schema_version":"1.0","event_id":"sha256:613a9662a2b1ed8152452038d36a7d717ec43ab98a9c0bc77a431a6d9cc76f6e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W/bundle.json","state_url":"https://pith.science/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T20:38:04Z","links":{"resolver":"https://pith.science/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W","bundle":"https://pith.science/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W/bundle.json","state":"https://pith.science/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMVGCJGTAWWAIJRS5NHCI2GB4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JMVGCJGTAWWAIJRS5NHCI2GB4W","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":"482d273d038534cd006ee5fb535bdc220d0a04279c27e6528afe5c265b131d25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T11:18:47Z","title_canon_sha256":"ccd275261141463d6ac80d8928117d42e76d0a1eb3bdff99a253cf585308738e"},"schema_version":"1.0","source":{"id":"2503.08307","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08307","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08307v2","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08307","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"pith_short_12","alias_value":"JMVGCJGTAWWA","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"JMVGCJGTAWWAIJRS","created_at":"2026-07-05T10:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"JMVGCJGT","created_at":"2026-07-05T10:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:613a9662a2b1ed8152452038d36a7d717ec43ab98a9c0bc77a431a6d9cc76f6e","target":"graph","created_at":"2026-07-05T10:29:37Z","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/2503.08307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint audio-video (AV) generation is still a significant challenge in generative AI, primarily due to three critical requirements: quality of the generated samples, seamless multimodal synchronization and temporal coherence, with audio tracks that match the visual data and vice versa, and limitless video duration. In this paper, we present $^R$-FLAV, a novel transformer-based architecture that addresses all the key challenges of AV generation. We explore three distinct cross modality interaction modules, with our lightweight temporal fusion module emerging as the most effective and computation","authors_text":"Alex Ergasti, Andrea Prati, Claudio Ferrari, Filippo Botti, Giuseppe Gabriele Tarollo, Massimo Bertozzi, Tomaso Fontanini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T11:18:47Z","title":"$^R$FLAV: Rolling Flow matching for infinite Audio Video generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08307","kind":"arxiv","version":2},"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":"sha256:08417b7cabfc02596e191aede1b5f2db2e29807a16bbf15e1325e87476259774","target":"record","created_at":"2026-07-05T10:29:37Z","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":"482d273d038534cd006ee5fb535bdc220d0a04279c27e6528afe5c265b131d25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-11T11:18:47Z","title_canon_sha256":"ccd275261141463d6ac80d8928117d42e76d0a1eb3bdff99a253cf585308738e"},"schema_version":"1.0","source":{"id":"2503.08307","kind":"arxiv","version":2}},"canonical_sha256":"4b2a6124d305ac042632eb4e2468c1e583a0306070eea15b1c8d5d6e0b8884da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b2a6124d305ac042632eb4e2468c1e583a0306070eea15b1c8d5d6e0b8884da","first_computed_at":"2026-07-05T10:29:37.923237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:37.923237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R1nmCir50efpuNRBJGWmJ2Eb2gMaT9WffmGR8qxPjLIhuRurzxArT1KMXv6M3J3s9smMwNUTI3Fqczr9zNplDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:37.924078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08307","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08417b7cabfc02596e191aede1b5f2db2e29807a16bbf15e1325e87476259774","sha256:613a9662a2b1ed8152452038d36a7d717ec43ab98a9c0bc77a431a6d9cc76f6e"],"state_sha256":"611a758cdb8ff5df2202a1dca2f9b34760fe32ca228a22cc3cb1fb3f33c40e0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VM8IM6yh0HS6s3mZyfugSXoAn+nRErmso1p5YGXPbF1b2otoJDUOPjLF4RaqCq9URNxUqYxqwj1B8qV9ZBy4Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:38:04.170301Z","bundle_sha256":"0af6e8a550a0153700b2e3076c06aef391b705ecec3df06721621fe2f7495f90"}}