{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ACMZASJEP2YHRUV7QK6VN6YGG4","short_pith_number":"pith:ACMZASJE","canonical_record":{"source":{"id":"2106.03932","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T19:44:56Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"d5f782a0848432432cc57778ad4e7729ac815e9055fa51382d94635884ed45b4","abstract_canon_sha256":"5a3c13d7e88dd20ac58a7dae25d450e9eddd4633d913137e23bf16dcb9faee58"},"schema_version":"1.0"},"canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","source":{"kind":"arxiv","id":"2106.03932","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03932","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03932v2","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03932","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"ACMZASJEP2YH","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"ACMZASJEP2YHRUV7","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"ACMZASJE","created_at":"2026-07-05T03:12:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ACMZASJEP2YHRUV7QK6VN6YGG4","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03932","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T19:44:56Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"d5f782a0848432432cc57778ad4e7729ac815e9055fa51382d94635884ed45b4","abstract_canon_sha256":"5a3c13d7e88dd20ac58a7dae25d450e9eddd4633d913137e23bf16dcb9faee58"},"schema_version":"1.0"},"canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:07.227773Z","signature_b64":"Y9tyZQ1p0riii2xaTas4Az1Tpxe/yJLV3vBwldYzfu0+8K+gXpqFVo3hcgWykReYVtfEgNqVSL4LX307kAvYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","last_reissued_at":"2026-07-05T03:12:07.227312Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:07.227312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03932","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":"2026-07-05T03:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uPNWAxQQNOn0CD5flgX91NWwZq4IrVZ1PXxw2mWTDaXZTItRe4rONxba1G6hX3nBwaPt529jkcRm3xNZ41JoBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:46.341554Z"},"content_sha256":"5253c8de16e3399b2a75143dddae47c9c48d1c9302e35e7a8ed3c388399c332c","schema_version":"1.0","event_id":"sha256:5253c8de16e3399b2a75143dddae47c9c48d1c9302e35e7a8ed3c388399c332c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ACMZASJEP2YHRUV7QK6VN6YGG4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Gerhard Rigoll, Maja Taseska, Okan K\\\"op\\\"ukl\\\"u","submitted_at":"2021-06-07T19:44:56Z","abstract_excerpt":"Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each stage of this pipeline plays an important role for the final performance of the created architecture. Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection. Correspondingly, we present a new architecture called ASDNet, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03932","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/2106.03932/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":"2026-07-05T03:12:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p4KGHVnRFjDGDc/sMV6r1PeORz3bhXv5x9DyXYfJvNieY1LYKQgLSFvBbDWsC7ZWa3iVthDZO+qMCgn/fkQxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:23:46.342077Z"},"content_sha256":"eff2f11c169fb22d09de173963ff98041e0d5c79921577c6d534f3ea64ca67e9","schema_version":"1.0","event_id":"sha256:eff2f11c169fb22d09de173963ff98041e0d5c79921577c6d534f3ea64ca67e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/bundle.json","state_url":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/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":"2026-08-09T00:23:46Z","links":{"resolver":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4","bundle":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/bundle.json","state":"https://pith.science/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ACMZASJEP2YHRUV7QK6VN6YGG4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ACMZASJEP2YHRUV7QK6VN6YGG4","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":"5a3c13d7e88dd20ac58a7dae25d450e9eddd4633d913137e23bf16dcb9faee58","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T19:44:56Z","title_canon_sha256":"d5f782a0848432432cc57778ad4e7729ac815e9055fa51382d94635884ed45b4"},"schema_version":"1.0","source":{"id":"2106.03932","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03932","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03932v2","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03932","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"pith_short_12","alias_value":"ACMZASJEP2YH","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"pith_short_16","alias_value":"ACMZASJEP2YHRUV7","created_at":"2026-07-05T03:12:07Z"},{"alias_kind":"pith_short_8","alias_value":"ACMZASJE","created_at":"2026-07-05T03:12:07Z"}],"graph_snapshots":[{"event_id":"sha256:eff2f11c169fb22d09de173963ff98041e0d5c79921577c6d534f3ea64ca67e9","target":"graph","created_at":"2026-07-05T03:12:07Z","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/2106.03932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a reference speaker and the background speakers within each frame, and (iii) temporal modeling for the reference speaker. Each stage of this pipeline plays an important role for the final performance of the created architecture. Based on a series of controlled experiments, this work presents several practical guidelines for audio-visual active speaker detection. Correspondingly, we present a new architecture called ASDNet, whi","authors_text":"Gerhard Rigoll, Maja Taseska, Okan K\\\"op\\\"ukl\\\"u","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T19:44:56Z","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03932","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":"sha256:5253c8de16e3399b2a75143dddae47c9c48d1c9302e35e7a8ed3c388399c332c","target":"record","created_at":"2026-07-05T03:12:07Z","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":"5a3c13d7e88dd20ac58a7dae25d450e9eddd4633d913137e23bf16dcb9faee58","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-06-07T19:44:56Z","title_canon_sha256":"d5f782a0848432432cc57778ad4e7729ac815e9055fa51382d94635884ed45b4"},"schema_version":"1.0","source":{"id":"2106.03932","kind":"arxiv","version":2}},"canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00999049247eb078d2bf82bd56fb06371cb4759d2a25b446c65be320a983304e","first_computed_at":"2026-07-05T03:12:07.227312Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:07.227312Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y9tyZQ1p0riii2xaTas4Az1Tpxe/yJLV3vBwldYzfu0+8K+gXpqFVo3hcgWykReYVtfEgNqVSL4LX307kAvYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:07.227773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03932","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5253c8de16e3399b2a75143dddae47c9c48d1c9302e35e7a8ed3c388399c332c","sha256:eff2f11c169fb22d09de173963ff98041e0d5c79921577c6d534f3ea64ca67e9"],"state_sha256":"9cf04f55548463ce93ce1ef0de33e2fd3fa9d86811c3477513ad0bed09e99381"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PpWj0EiBLa4SGD81JU41Tfy4iMV2CP9ss6ljlBkcrS3wVWvBHy5A6LRoY1YXM3YyBvn33vMe8bDlk16Pbt11AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:23:46.346047Z","bundle_sha256":"f98b51a11d17e505cf677cddce7307547ace580ef66d9024ac1ea9dd57732e31"}}