{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q6JVZKAOAKX54L2BJRESW5E26I","short_pith_number":"pith:Q6JVZKAO","canonical_record":{"source":{"id":"2506.01270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T02:47:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f4294517a1246175294ab5d4c7ca29ecf0cebd1f1bac1ab0f322d7878abfc77e","abstract_canon_sha256":"cdf253cdc84f1ddff457a1f96d842c55da6510b4ab0f9998e9f10c431f33e0f0"},"schema_version":"1.0"},"canonical_sha256":"87935ca80e02afde2f414c492b749af234ea49c5dac21c1069fede8235701fc6","source":{"kind":"arxiv","id":"2506.01270","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01270","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01270v1","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01270","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q6JVZKAOAKX5","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q6JVZKAOAKX54L2B","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q6JVZKAO","created_at":"2026-07-05T11:14:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q6JVZKAOAKX54L2BJRESW5E26I","target":"record","payload":{"canonical_record":{"source":{"id":"2506.01270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T02:47:53Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"f4294517a1246175294ab5d4c7ca29ecf0cebd1f1bac1ab0f322d7878abfc77e","abstract_canon_sha256":"cdf253cdc84f1ddff457a1f96d842c55da6510b4ab0f9998e9f10c431f33e0f0"},"schema_version":"1.0"},"canonical_sha256":"87935ca80e02afde2f414c492b749af234ea49c5dac21c1069fede8235701fc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:11.017159Z","signature_b64":"EWHU52BvaUJnjV1n+khC6qFzJSXtMIcOsp5RytgUZneYS60JOXmxCuP4CLgBlC9quR1pXvTcrOqqvOtDvqREAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87935ca80e02afde2f414c492b749af234ea49c5dac21c1069fede8235701fc6","last_reissued_at":"2026-07-05T11:14:11.016701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:11.016701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.01270","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":"2026-07-05T11:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qmR0tf7y1v3zAEtR76Jou+Xfnf+/chrmXQW+2/kEtgSf5p2Dwi/d9aYrbW3Y2HXdMEi9hUHb+NBrprfoMuWMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:11:19.322636Z"},"content_sha256":"2c661f9e9af4a2cbd2ebd60f690c1adff0aed3e48e2757f57b9c31fc92cea9f1","schema_version":"1.0","event_id":"sha256:2c661f9e9af4a2cbd2ebd60f690c1adff0aed3e48e2757f57b9c31fc92cea9f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q6JVZKAOAKX54L2BJRESW5E26I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Audio-Visual Autoregressive Speaker Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bin Ma, Chong Zhang, Kun Zhou, Shengkui Zhao, Wupeng Wang, Yukun Ma, Zexu Pan","submitted_at":"2025-06-02T02:47:53Z","abstract_excerpt":"This paper proposes a novel online audio-visual speaker extraction model. In the streaming regime, most studies optimize the audio network only, leaving the visual frontend less explored. We first propose a lightweight visual frontend based on depth-wise separable convolution. Then, we propose a lightweight autoregressive acoustic encoder to serve as the second cue, to actively explore the information in the separated speech signal from past steps. Scenario-wise, for the first time, we study how the algorithm performs when there is a change in focus of attention, i.e., the target speaker. Expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01270","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/2506.01270/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":"2026-07-05T11:14:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGdc6Urc4g8C0T0w5w1FmbYJlcHymo85m7eQY860OV53a55vBzLRzM4nrpO638JABm31GhBH34hL3LXsAxElAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:11:19.323830Z"},"content_sha256":"c1b9f44250772872adf5bd573f361fa4e7ff0cea97d52f34ff6c46c1f15afa4a","schema_version":"1.0","event_id":"sha256:c1b9f44250772872adf5bd573f361fa4e7ff0cea97d52f34ff6c46c1f15afa4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6JVZKAOAKX54L2BJRESW5E26I/bundle.json","state_url":"https://pith.science/pith/Q6JVZKAOAKX54L2BJRESW5E26I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6JVZKAOAKX54L2BJRESW5E26I/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":"2026-08-21T06:11:19Z","links":{"resolver":"https://pith.science/pith/Q6JVZKAOAKX54L2BJRESW5E26I","bundle":"https://pith.science/pith/Q6JVZKAOAKX54L2BJRESW5E26I/bundle.json","state":"https://pith.science/pith/Q6JVZKAOAKX54L2BJRESW5E26I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6JVZKAOAKX54L2BJRESW5E26I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6JVZKAOAKX54L2BJRESW5E26I","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":"cdf253cdc84f1ddff457a1f96d842c55da6510b4ab0f9998e9f10c431f33e0f0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T02:47:53Z","title_canon_sha256":"f4294517a1246175294ab5d4c7ca29ecf0cebd1f1bac1ab0f322d7878abfc77e"},"schema_version":"1.0","source":{"id":"2506.01270","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01270","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01270v1","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01270","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_12","alias_value":"Q6JVZKAOAKX5","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_16","alias_value":"Q6JVZKAOAKX54L2B","created_at":"2026-07-05T11:14:11Z"},{"alias_kind":"pith_short_8","alias_value":"Q6JVZKAO","created_at":"2026-07-05T11:14:11Z"}],"graph_snapshots":[{"event_id":"sha256:c1b9f44250772872adf5bd573f361fa4e7ff0cea97d52f34ff6c46c1f15afa4a","target":"graph","created_at":"2026-07-05T11:14:11Z","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/2506.01270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a novel online audio-visual speaker extraction model. In the streaming regime, most studies optimize the audio network only, leaving the visual frontend less explored. We first propose a lightweight visual frontend based on depth-wise separable convolution. Then, we propose a lightweight autoregressive acoustic encoder to serve as the second cue, to actively explore the information in the separated speech signal from past steps. Scenario-wise, for the first time, we study how the algorithm performs when there is a change in focus of attention, i.e., the target speaker. Expe","authors_text":"Bin Ma, Chong Zhang, Kun Zhou, Shengkui Zhao, Wupeng Wang, Yukun Ma, Zexu Pan","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T02:47:53Z","title":"Online Audio-Visual Autoregressive Speaker Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01270","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":"sha256:2c661f9e9af4a2cbd2ebd60f690c1adff0aed3e48e2757f57b9c31fc92cea9f1","target":"record","created_at":"2026-07-05T11:14:11Z","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":"cdf253cdc84f1ddff457a1f96d842c55da6510b4ab0f9998e9f10c431f33e0f0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-02T02:47:53Z","title_canon_sha256":"f4294517a1246175294ab5d4c7ca29ecf0cebd1f1bac1ab0f322d7878abfc77e"},"schema_version":"1.0","source":{"id":"2506.01270","kind":"arxiv","version":1}},"canonical_sha256":"87935ca80e02afde2f414c492b749af234ea49c5dac21c1069fede8235701fc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"87935ca80e02afde2f414c492b749af234ea49c5dac21c1069fede8235701fc6","first_computed_at":"2026-07-05T11:14:11.016701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:11.016701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EWHU52BvaUJnjV1n+khC6qFzJSXtMIcOsp5RytgUZneYS60JOXmxCuP4CLgBlC9quR1pXvTcrOqqvOtDvqREAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:11.017159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01270","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c661f9e9af4a2cbd2ebd60f690c1adff0aed3e48e2757f57b9c31fc92cea9f1","sha256:c1b9f44250772872adf5bd573f361fa4e7ff0cea97d52f34ff6c46c1f15afa4a"],"state_sha256":"3b48411bdfa0d3c545ad1b967996422bef5c94c103f5236739f1731045632528"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cgkVKS9qdtm5eo+15+HM5ef6/gGNjUrIEdaO/ZMdCuE8GrHp0SAQy58OFrzgMEiL0+6FuOPEkdBUABnDFV1aDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T06:11:19.329521Z","bundle_sha256":"c977b183386a4754077b3f52862049653f9598552a6c18433b16a6db98191498"}}