{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IHE23QM6QSZEIRHYVOFP77TANH","short_pith_number":"pith:IHE23QM6","canonical_record":{"source":{"id":"2606.02724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T18:00:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b652c04d3cc5fa266017f7876fada4d915ebf1fe69830bee3e623f819d843df6","abstract_canon_sha256":"e35ea9ea74e2080ee3ed7950b859df6c590677bde17605ecb97203d4e107bd38"},"schema_version":"1.0"},"canonical_sha256":"41c9adc19e84b24444f8ab8afffe6069cbc0d831b5a8620048c9efcc39564f36","source":{"kind":"arxiv","id":"2606.02724","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02724","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02724v1","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02724","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"IHE23QM6QSZE","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"IHE23QM6QSZEIRHY","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"IHE23QM6","created_at":"2026-06-03T00:05:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IHE23QM6QSZEIRHYVOFP77TANH","target":"record","payload":{"canonical_record":{"source":{"id":"2606.02724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T18:00:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b652c04d3cc5fa266017f7876fada4d915ebf1fe69830bee3e623f819d843df6","abstract_canon_sha256":"e35ea9ea74e2080ee3ed7950b859df6c590677bde17605ecb97203d4e107bd38"},"schema_version":"1.0"},"canonical_sha256":"41c9adc19e84b24444f8ab8afffe6069cbc0d831b5a8620048c9efcc39564f36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T00:05:08.058935Z","signature_b64":"4QOn3/h45zvk02hxJAWMbbAXKaIeN7cTvqmnysSpQcQ/Re1Ldbol8oJSwxNBQqyyZEHfDxN8sp54IYxlcp1OCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c9adc19e84b24444f8ab8afffe6069cbc0d831b5a8620048c9efcc39564f36","last_reissued_at":"2026-06-03T00:05:08.058568Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T00:05:08.058568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.02724","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":"2026-06-03T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KMxtDxwcd0cmpE1jnQ1IYZeX9/yWI9LXIcyIy64v2cvZIzyVeUIH1BldrILdria/hy+SkpRyNo2vPucwcMJTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T11:02:54.124918Z"},"content_sha256":"01601cdfaa3dae3faa264df41244b71faf700c2688d6274f4e526be1c19d1072","schema_version":"1.0","event_id":"sha256:01601cdfaa3dae3faa264df41244b71faf700c2688d6274f4e526be1c19d1072"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IHE23QM6QSZEIRHYVOFP77TANH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Henghui Ding, Yaoting Wang, Yun Zhou, Zipei Zhang","submitted_at":"2026-06-01T18:00:08Z","abstract_excerpt":"Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding. This capability is essential for real-world applications such as intelligent video editing, surveillance, and human-computer interaction. However, existing datasets are largely limited to simple or homogeneous audio-visual scenes with coarse annotations. Such oversimplified settings bias evaluation toward static audio-visual co-occurrence, rather than rigorously assessing robust spatiotemporal modeling and cross-modal reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02724","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/2606.02724/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":"2026-06-03T00:05:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UqFws7f2XgAVAaZwOn+nxM9IrbIQoW0FIcvgW1xONC8M2xUaV0vD9jcTBIm6Uzp96Iauun/OBg6lTlOwf4wGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T11:02:54.125289Z"},"content_sha256":"ca3def74d3763788286ee4b0332bf8d32f10d786ca6640fbe485e6178f5dc2db","schema_version":"1.0","event_id":"sha256:ca3def74d3763788286ee4b0332bf8d32f10d786ca6640fbe485e6178f5dc2db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IHE23QM6QSZEIRHYVOFP77TANH/bundle.json","state_url":"https://pith.science/pith/IHE23QM6QSZEIRHYVOFP77TANH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IHE23QM6QSZEIRHYVOFP77TANH/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":"2026-06-04T11:02:54Z","links":{"resolver":"https://pith.science/pith/IHE23QM6QSZEIRHYVOFP77TANH","bundle":"https://pith.science/pith/IHE23QM6QSZEIRHYVOFP77TANH/bundle.json","state":"https://pith.science/pith/IHE23QM6QSZEIRHYVOFP77TANH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IHE23QM6QSZEIRHYVOFP77TANH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IHE23QM6QSZEIRHYVOFP77TANH","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":"e35ea9ea74e2080ee3ed7950b859df6c590677bde17605ecb97203d4e107bd38","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T18:00:08Z","title_canon_sha256":"b652c04d3cc5fa266017f7876fada4d915ebf1fe69830bee3e623f819d843df6"},"schema_version":"1.0","source":{"id":"2606.02724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02724","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02724v1","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02724","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"pith_short_12","alias_value":"IHE23QM6QSZE","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"pith_short_16","alias_value":"IHE23QM6QSZEIRHY","created_at":"2026-06-03T00:05:08Z"},{"alias_kind":"pith_short_8","alias_value":"IHE23QM6","created_at":"2026-06-03T00:05:08Z"}],"graph_snapshots":[{"event_id":"sha256:ca3def74d3763788286ee4b0332bf8d32f10d786ca6640fbe485e6178f5dc2db","target":"graph","created_at":"2026-06-03T00:05:08Z","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/2606.02724/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding. This capability is essential for real-world applications such as intelligent video editing, surveillance, and human-computer interaction. However, existing datasets are largely limited to simple or homogeneous audio-visual scenes with coarse annotations. Such oversimplified settings bias evaluation toward static audio-visual co-occurrence, rather than rigorously assessing robust spatiotemporal modeling and cross-modal reasoni","authors_text":"Henghui Ding, Yaoting Wang, Yun Zhou, Zipei Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T18:00:08Z","title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02724","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":"sha256:01601cdfaa3dae3faa264df41244b71faf700c2688d6274f4e526be1c19d1072","target":"record","created_at":"2026-06-03T00:05:08Z","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":"e35ea9ea74e2080ee3ed7950b859df6c590677bde17605ecb97203d4e107bd38","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T18:00:08Z","title_canon_sha256":"b652c04d3cc5fa266017f7876fada4d915ebf1fe69830bee3e623f819d843df6"},"schema_version":"1.0","source":{"id":"2606.02724","kind":"arxiv","version":1}},"canonical_sha256":"41c9adc19e84b24444f8ab8afffe6069cbc0d831b5a8620048c9efcc39564f36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41c9adc19e84b24444f8ab8afffe6069cbc0d831b5a8620048c9efcc39564f36","first_computed_at":"2026-06-03T00:05:08.058568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T00:05:08.058568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4QOn3/h45zvk02hxJAWMbbAXKaIeN7cTvqmnysSpQcQ/Re1Ldbol8oJSwxNBQqyyZEHfDxN8sp54IYxlcp1OCA==","signature_status":"signed_v1","signed_at":"2026-06-03T00:05:08.058935Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01601cdfaa3dae3faa264df41244b71faf700c2688d6274f4e526be1c19d1072","sha256:ca3def74d3763788286ee4b0332bf8d32f10d786ca6640fbe485e6178f5dc2db"],"state_sha256":"15dd7e687e06010eed6dbadf63a1364688bae8b0fff976f753c548df6399cada"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m/o26dtIntUixnFkvPuwRa9bVyRhWsVEjeCrE7brkYMh+sLtQOsE602orADOXPYKTzcTfrcoBf2TJRH4IQXBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T11:02:54.127407Z","bundle_sha256":"76531a9b94b76b06b4be1bbd09f9ddd272a5989cca5e25d4fa95376b9ec303ff"}}