{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BTOKXAPGIOCXYRVGBDQWWQWY5V","short_pith_number":"pith:BTOKXAPG","canonical_record":{"source":{"id":"2605.30940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:28:24Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"3324c8104a001bdee8879d1e656d290df8a2c0e2119bc7d0bf57cd1b8d0f165d","abstract_canon_sha256":"279ddd86971b7e3c934efd7762f92c0b6c17afddf3c1efd2062fd223dfe77770"},"schema_version":"1.0"},"canonical_sha256":"0cdcab81e643857c46a608e16b42d8ed5411cb92e666cacbe142b13fe2b6685c","source":{"kind":"arxiv","id":"2605.30940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30940","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30940v1","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30940","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"BTOKXAPGIOCX","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"BTOKXAPGIOCXYRVG","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"BTOKXAPG","created_at":"2026-06-01T01:03:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BTOKXAPGIOCXYRVGBDQWWQWY5V","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:28:24Z","cross_cats_sorted":["cs.MM","cs.SD"],"title_canon_sha256":"3324c8104a001bdee8879d1e656d290df8a2c0e2119bc7d0bf57cd1b8d0f165d","abstract_canon_sha256":"279ddd86971b7e3c934efd7762f92c0b6c17afddf3c1efd2062fd223dfe77770"},"schema_version":"1.0"},"canonical_sha256":"0cdcab81e643857c46a608e16b42d8ed5411cb92e666cacbe142b13fe2b6685c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:26.869776Z","signature_b64":"7V/9MwPXfUM8FXxnm/fDN/M8khpZBHpePUtDL5LaPz6vNHDDinrWS4DV5KTs8GAYcJkuikkIhXJqsPzRgWIJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cdcab81e643857c46a608e16b42d8ed5411cb92e666cacbe142b13fe2b6685c","last_reissued_at":"2026-06-01T01:03:26.868789Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:26.868789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30940","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T01:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGQktSJ20wLCnA5jvUulHJfGhVIVQyNcszjwhqVaepdW14POQgizK6gZiHMNTMvkx+U/CflArirQVLH9E2pyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:01:15.119781Z"},"content_sha256":"5c3789beb633a5b6ffcaeff4b0b1682336d6b26488dc5f0b4f51c524efa4b6c9","schema_version":"1.0","event_id":"sha256:5c3789beb633a5b6ffcaeff4b0b1682336d6b26488dc5f0b4f51c524efa4b6c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BTOKXAPGIOCXYRVGBDQWWQWY5V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changhao Pan, Ke Lei, Ruiqi Li, Wenxiang Guo, Xueyi Pu, Yu Zhang, Zhou Zhao","submitted_at":"2026-05-29T07:28:24Z","abstract_excerpt":"Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose SwanSphere, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. SwanSphere mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30940","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/2605.30940/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":"2026-06-01T01:03:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nH4OPSAm3Exb9c5EjlEMv2e9dVCHA4ih2L4HK+n0nolPUqZbeV9LIlQnPmzxmBz9GWKSgsocTYCX9slhtNv0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T21:01:15.120575Z"},"content_sha256":"395a7438b4dac4d38e59bbcf88ceb7c734101dc58b0d18a908ad9cd78e2ced27","schema_version":"1.0","event_id":"sha256:395a7438b4dac4d38e59bbcf88ceb7c734101dc58b0d18a908ad9cd78e2ced27"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V/bundle.json","state_url":"https://pith.science/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V/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":"2026-06-08T21:01:15Z","links":{"resolver":"https://pith.science/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V","bundle":"https://pith.science/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V/bundle.json","state":"https://pith.science/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BTOKXAPGIOCXYRVGBDQWWQWY5V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BTOKXAPGIOCXYRVGBDQWWQWY5V","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":"279ddd86971b7e3c934efd7762f92c0b6c17afddf3c1efd2062fd223dfe77770","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:28:24Z","title_canon_sha256":"3324c8104a001bdee8879d1e656d290df8a2c0e2119bc7d0bf57cd1b8d0f165d"},"schema_version":"1.0","source":{"id":"2605.30940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30940","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30940v1","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30940","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_12","alias_value":"BTOKXAPGIOCX","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_16","alias_value":"BTOKXAPGIOCXYRVG","created_at":"2026-06-01T01:03:26Z"},{"alias_kind":"pith_short_8","alias_value":"BTOKXAPG","created_at":"2026-06-01T01:03:26Z"}],"graph_snapshots":[{"event_id":"sha256:395a7438b4dac4d38e59bbcf88ceb7c734101dc58b0d18a908ad9cd78e2ced27","target":"graph","created_at":"2026-06-01T01:03:26Z","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/2605.30940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial information from multimodal inputs. To address these challenges, we propose SwanSphere, a unified streaming framework for high-fidelity spatial audio generation from panoramic videos and text prompts. SwanSphere mainly makes the following contributions: 1) We introduce a causal autoregressive diffusion t","authors_text":"Changhao Pan, Ke Lei, Ruiqi Li, Wenxiang Guo, Xueyi Pu, Yu Zhang, Zhou Zhao","cross_cats":["cs.MM","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:28:24Z","title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30940","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":"sha256:5c3789beb633a5b6ffcaeff4b0b1682336d6b26488dc5f0b4f51c524efa4b6c9","target":"record","created_at":"2026-06-01T01:03:26Z","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":"279ddd86971b7e3c934efd7762f92c0b6c17afddf3c1efd2062fd223dfe77770","cross_cats_sorted":["cs.MM","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-29T07:28:24Z","title_canon_sha256":"3324c8104a001bdee8879d1e656d290df8a2c0e2119bc7d0bf57cd1b8d0f165d"},"schema_version":"1.0","source":{"id":"2605.30940","kind":"arxiv","version":1}},"canonical_sha256":"0cdcab81e643857c46a608e16b42d8ed5411cb92e666cacbe142b13fe2b6685c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cdcab81e643857c46a608e16b42d8ed5411cb92e666cacbe142b13fe2b6685c","first_computed_at":"2026-06-01T01:03:26.868789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:26.868789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7V/9MwPXfUM8FXxnm/fDN/M8khpZBHpePUtDL5LaPz6vNHDDinrWS4DV5KTs8GAYcJkuikkIhXJqsPzRgWIJBg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:26.869776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c3789beb633a5b6ffcaeff4b0b1682336d6b26488dc5f0b4f51c524efa4b6c9","sha256:395a7438b4dac4d38e59bbcf88ceb7c734101dc58b0d18a908ad9cd78e2ced27"],"state_sha256":"e69e750ad255108981f1cc8366249e45ba8029675a6c401f37842ac5ee5170b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gX8nTfY8Uy8v3AM3B3uZfDejnAWtxi1c2kQtuvNQe7eMXVNNo43pnfnaRg7gw5hwpHbzwvSaZDaJhgYenklsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T21:01:15.125477Z","bundle_sha256":"104e0f50151b713d1078b39b5f3c281b62b5f3fdbfded88956c856b58242c1af"}}