{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3KBP53WF62BNOXLYDZY3A7DBJ","short_pith_number":"pith:P3KBP53W","schema_version":"1.0","canonical_sha256":"7ed417f7762fb416baebc0f38d83e30a72cf54a19d797d5e9f280b076b28628c","source":{"kind":"arxiv","id":"2607.17867","version":1},"attestation_state":"computed","paper":{"title":"The tttAI System for the TSA-ASR Task of the SmartGlasses Challenge 2026","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Fengjie Zhu, Gaoyang Dong, Minchuan Chen, Xiaoxiao Li, Xuanji He","submitted_at":"2026-07-20T12:10:11Z","abstract_excerpt":"This paper presents the tttAI system submitted to the TSA-ASR task of the SmartGlasses Challenge 2026, evaluated on both two-person dialogues (Track 1) and multi-party meetings (Track 2). The task requires time-stamped speaker-attributed speech recognition from smart-glasses recordings. This is particularly challenging due to long-form audio, multiple speakers, and frequent overlapping speech.\n  We proposed a cascaded architecture consisting of speaker diarization, overlap detection, target-speaker extraction, post-processing, and automatic speech recognition. The diarization module extracts f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.17867","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-20T12:10:11Z","cross_cats_sorted":[],"title_canon_sha256":"800e34fa3d1b56719dbad54ffbc6d9e7988648054dc0b95b966fd82544fe8112","abstract_canon_sha256":"ca8b4170ea875dcd561f1f9b3dc83137d8816ec8c7585dda141b4017e1e7197f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T02:22:04.274841Z","signature_b64":"NYhrRMioQKwSHZgp8+K4ng6JOn86f2q22rS76MsJmYmRElGzCEcMNPvm9ZaaClGQPH75XNRKAGT0NJf1JyU7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ed417f7762fb416baebc0f38d83e30a72cf54a19d797d5e9f280b076b28628c","last_reissued_at":"2026-07-21T02:22:04.274021Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T02:22:04.274021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The tttAI System for the TSA-ASR Task of the SmartGlasses Challenge 2026","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Fengjie Zhu, Gaoyang Dong, Minchuan Chen, Xiaoxiao Li, Xuanji He","submitted_at":"2026-07-20T12:10:11Z","abstract_excerpt":"This paper presents the tttAI system submitted to the TSA-ASR task of the SmartGlasses Challenge 2026, evaluated on both two-person dialogues (Track 1) and multi-party meetings (Track 2). The task requires time-stamped speaker-attributed speech recognition from smart-glasses recordings. This is particularly challenging due to long-form audio, multiple speakers, and frequent overlapping speech.\n  We proposed a cascaded architecture consisting of speaker diarization, overlap detection, target-speaker extraction, post-processing, and automatic speech recognition. The diarization module extracts f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17867","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/2607.17867/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.17867","created_at":"2026-07-21T02:22:04.274447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17867v1","created_at":"2026-07-21T02:22:04.274447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17867","created_at":"2026-07-21T02:22:04.274447+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3KBP53WF62B","created_at":"2026-07-21T02:22:04.274447+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3KBP53WF62BNOXL","created_at":"2026-07-21T02:22:04.274447+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3KBP53W","created_at":"2026-07-21T02:22:04.274447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ","json":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ.json","graph_json":"https://pith.science/api/pith-number/P3KBP53WF62BNOXLYDZY3A7DBJ/graph.json","events_json":"https://pith.science/api/pith-number/P3KBP53WF62BNOXLYDZY3A7DBJ/events.json","paper":"https://pith.science/paper/P3KBP53W"},"agent_actions":{"view_html":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ","download_json":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ.json","view_paper":"https://pith.science/paper/P3KBP53W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17867&json=true","fetch_graph":"https://pith.science/api/pith-number/P3KBP53WF62BNOXLYDZY3A7DBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/P3KBP53WF62BNOXLYDZY3A7DBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ/action/storage_attestation","attest_author":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ/action/author_attestation","sign_citation":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ/action/citation_signature","submit_replication":"https://pith.science/pith/P3KBP53WF62BNOXLYDZY3A7DBJ/action/replication_record"}},"created_at":"2026-07-21T02:22:04.274447+00:00","updated_at":"2026-07-21T02:22:04.274447+00:00"}