{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AY7CZ2DGKX7YIF7VR3B4MIDLUV","short_pith_number":"pith:AY7CZ2DG","canonical_record":{"source":{"id":"2306.14170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2023-06-25T08:31:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a270e81f3ce8d8dcc1335d5520ddbd61dfb5456fedcaa88eebf8cc1e84f9e529","abstract_canon_sha256":"ce48ac79f70de62b1abce4988d310a1cf1eb3452460b5c323af2510d1c61cd3a"},"schema_version":"1.0"},"canonical_sha256":"063e2ce86655ff8417f58ec3c6206ba558b482bc4fd24285b7664ea7d30be450","source":{"kind":"arxiv","id":"2306.14170","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14170","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14170v1","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14170","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_12","alias_value":"AY7CZ2DGKX7Y","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_16","alias_value":"AY7CZ2DGKX7YIF7V","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_8","alias_value":"AY7CZ2DG","created_at":"2026-07-05T06:24:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AY7CZ2DGKX7YIF7VR3B4MIDLUV","target":"record","payload":{"canonical_record":{"source":{"id":"2306.14170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2023-06-25T08:31:12Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a270e81f3ce8d8dcc1335d5520ddbd61dfb5456fedcaa88eebf8cc1e84f9e529","abstract_canon_sha256":"ce48ac79f70de62b1abce4988d310a1cf1eb3452460b5c323af2510d1c61cd3a"},"schema_version":"1.0"},"canonical_sha256":"063e2ce86655ff8417f58ec3c6206ba558b482bc4fd24285b7664ea7d30be450","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:32.458269Z","signature_b64":"a7mlRuqpwY9JypKhHfX7cmVAlJbZyZl5orRAA0TFqx/8VCFTMSwggd06/unIe6A3g8hlbczx3ypX12a+IgWeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"063e2ce86655ff8417f58ec3c6206ba558b482bc4fd24285b7664ea7d30be450","last_reissued_at":"2026-07-05T06:24:32.457803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:32.457803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.14170","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":"2026-07-05T06:24:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkooOqwOZewcSJv07UzXi8E2nsr/CNGwewVlJainFKoH8tj0LX2qw6xSG2UjfCFlRzQqIFzS5KH0p4KlObypBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T03:32:30.080325Z"},"content_sha256":"0b00a557952e0dcdb0f3ae64718454d46aacd1934ddb9a2b474db7e5ceac00ed","schema_version":"1.0","event_id":"sha256:0b00a557952e0dcdb0f3ae64718454d46aacd1934ddb9a2b474db7e5ceac00ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AY7CZ2DGKX7YIF7VR3B4MIDLUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AV-SepFormer: Cross-Attention SepFormer for Audio-Visual Target Speaker Extraction","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Heinrich Dinkel, Helen Meng, Jiuxin Lin, Junbo Zhang, Jun Chen, Xinyu Cai, Yongqing Wang, Yujun Wang, Zhiyong Wu, Zhiyong Yan","submitted_at":"2023-06-25T08:31:12Z","abstract_excerpt":"Visual information can serve as an effective cue for target speaker extraction (TSE) and is vital to improving extraction performance. In this paper, we propose AV-SepFormer, a SepFormer-based attention dual-scale model that utilizes cross- and self-attention to fuse and model features from audio and visual. AV-SepFormer splits the audio feature into a number of chunks, equivalent to the length of the visual feature. Then self- and cross-attention are employed to model and fuse the multi-modal features. Furthermore, we use a novel 2D positional encoding, that introduces the positional informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14170","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/2306.14170/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":"2026-07-05T06:24:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wm+/hOsCaK9XT99peCDvpQtEBIVgYP+od1m0832RVP4qkoqBUuJOz6c0jP/lcw3fVWIYDaQNxXNN/1ot7o57CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T03:32:30.080739Z"},"content_sha256":"2c6e06deca3ef07a2816675fc6e32acfd3e0293acf6dfb5f555beea1a66ab454","schema_version":"1.0","event_id":"sha256:2c6e06deca3ef07a2816675fc6e32acfd3e0293acf6dfb5f555beea1a66ab454"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV/bundle.json","state_url":"https://pith.science/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV/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":"2026-07-13T03:32:30Z","links":{"resolver":"https://pith.science/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV","bundle":"https://pith.science/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV/bundle.json","state":"https://pith.science/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AY7CZ2DGKX7YIF7VR3B4MIDLUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AY7CZ2DGKX7YIF7VR3B4MIDLUV","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":"ce48ac79f70de62b1abce4988d310a1cf1eb3452460b5c323af2510d1c61cd3a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2023-06-25T08:31:12Z","title_canon_sha256":"a270e81f3ce8d8dcc1335d5520ddbd61dfb5456fedcaa88eebf8cc1e84f9e529"},"schema_version":"1.0","source":{"id":"2306.14170","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14170","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14170v1","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14170","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_12","alias_value":"AY7CZ2DGKX7Y","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_16","alias_value":"AY7CZ2DGKX7YIF7V","created_at":"2026-07-05T06:24:32Z"},{"alias_kind":"pith_short_8","alias_value":"AY7CZ2DG","created_at":"2026-07-05T06:24:32Z"}],"graph_snapshots":[{"event_id":"sha256:2c6e06deca3ef07a2816675fc6e32acfd3e0293acf6dfb5f555beea1a66ab454","target":"graph","created_at":"2026-07-05T06:24:32Z","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/2306.14170/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual information can serve as an effective cue for target speaker extraction (TSE) and is vital to improving extraction performance. In this paper, we propose AV-SepFormer, a SepFormer-based attention dual-scale model that utilizes cross- and self-attention to fuse and model features from audio and visual. AV-SepFormer splits the audio feature into a number of chunks, equivalent to the length of the visual feature. Then self- and cross-attention are employed to model and fuse the multi-modal features. Furthermore, we use a novel 2D positional encoding, that introduces the positional informat","authors_text":"Heinrich Dinkel, Helen Meng, Jiuxin Lin, Junbo Zhang, Jun Chen, Xinyu Cai, Yongqing Wang, Yujun Wang, Zhiyong Wu, Zhiyong Yan","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2023-06-25T08:31:12Z","title":"AV-SepFormer: Cross-Attention SepFormer for Audio-Visual Target Speaker Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14170","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":"sha256:0b00a557952e0dcdb0f3ae64718454d46aacd1934ddb9a2b474db7e5ceac00ed","target":"record","created_at":"2026-07-05T06:24:32Z","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":"ce48ac79f70de62b1abce4988d310a1cf1eb3452460b5c323af2510d1c61cd3a","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.MM","submitted_at":"2023-06-25T08:31:12Z","title_canon_sha256":"a270e81f3ce8d8dcc1335d5520ddbd61dfb5456fedcaa88eebf8cc1e84f9e529"},"schema_version":"1.0","source":{"id":"2306.14170","kind":"arxiv","version":1}},"canonical_sha256":"063e2ce86655ff8417f58ec3c6206ba558b482bc4fd24285b7664ea7d30be450","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"063e2ce86655ff8417f58ec3c6206ba558b482bc4fd24285b7664ea7d30be450","first_computed_at":"2026-07-05T06:24:32.457803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:32.457803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a7mlRuqpwY9JypKhHfX7cmVAlJbZyZl5orRAA0TFqx/8VCFTMSwggd06/unIe6A3g8hlbczx3ypX12a+IgWeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:32.458269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14170","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b00a557952e0dcdb0f3ae64718454d46aacd1934ddb9a2b474db7e5ceac00ed","sha256:2c6e06deca3ef07a2816675fc6e32acfd3e0293acf6dfb5f555beea1a66ab454"],"state_sha256":"6ad162018006ba96de87ff890ac073db71666bf7c94e7a34d84de3bf01af056f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7z9f0DeN60ql9tM/LExboljeTJoVIsjiY3hxNw+ka28g6AWwRJBCKZaiuAnkfjb6I9edXvZ+NcGw8IiSN1d2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T03:32:30.083912Z","bundle_sha256":"483ddfacfc34f65870c195c9ceb2517178c4538cfa934eb04c36a42400441503"}}