{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TS7ZKKG4PYPNQMU3C3XJVAU5QO","short_pith_number":"pith:TS7ZKKG4","schema_version":"1.0","canonical_sha256":"9cbf9528dc7e1ed8329b16ee9a829d83bf1ec123f5cb62ee2c73f443ebf125d8","source":{"kind":"arxiv","id":"2607.21943","version":1},"attestation_state":"computed","paper":{"title":"Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Biao Tian, Li Liu, Minghao Yang, Pengfei Zhang, Tianxin Xie, Xiangang Li","submitted_at":"2026-07-24T03:39:34Z","abstract_excerpt":"Omni models transcribe clean, single-speaker speech well, but their accuracy drops sharply when speakers overlap and the scene is noisy, exactly where knowing who said what matters most. A natural fix is a short scene description. We show why this is risky: answer-bearing text lets the model copy instead of listen, so the score rises although nothing has been heard; a silent test exposes this shortcut at once. We call this failure mode perception bypass and address it with Audio-Grounded Scaffold Context (AGSC). AGSC links three steps: first, we build clues from audio to guide listening withou"},"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":"2607.21943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T03:39:34Z","cross_cats_sorted":[],"title_canon_sha256":"39decbd776f4a52abddc187226a55359f3debe0b32e1dfe2c8af3e020c7bfd3f","abstract_canon_sha256":"95ea5061430482feaa724e2b09a74aef836a30ead88ce3076d34e528cf540fa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:29.051140Z","signature_b64":"ZeH/X/OOCunYjIVvtUZ68yK8LlHEPB7e9FtRy5GGyUS1Jm+yUJ4g8VFdYHBZQtz/HyHGlArmePLwXw27vHgGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cbf9528dc7e1ed8329b16ee9a829d83bf1ec123f5cb62ee2c73f443ebf125d8","last_reissued_at":"2026-07-27T00:20:29.050291Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:29.050291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Biao Tian, Li Liu, Minghao Yang, Pengfei Zhang, Tianxin Xie, Xiangang Li","submitted_at":"2026-07-24T03:39:34Z","abstract_excerpt":"Omni models transcribe clean, single-speaker speech well, but their accuracy drops sharply when speakers overlap and the scene is noisy, exactly where knowing who said what matters most. A natural fix is a short scene description. We show why this is risky: answer-bearing text lets the model copy instead of listen, so the score rises although nothing has been heard; a silent test exposes this shortcut at once. We call this failure mode perception bypass and address it with Audio-Grounded Scaffold Context (AGSC). AGSC links three steps: first, we build clues from audio to guide listening withou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21943","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/2607.21943/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":"2607.21943","created_at":"2026-07-27T00:20:29.050737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21943v1","created_at":"2026-07-27T00:20:29.050737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21943","created_at":"2026-07-27T00:20:29.050737+00:00"},{"alias_kind":"pith_short_12","alias_value":"TS7ZKKG4PYPN","created_at":"2026-07-27T00:20:29.050737+00:00"},{"alias_kind":"pith_short_16","alias_value":"TS7ZKKG4PYPNQMU3","created_at":"2026-07-27T00:20:29.050737+00:00"},{"alias_kind":"pith_short_8","alias_value":"TS7ZKKG4","created_at":"2026-07-27T00:20:29.050737+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/TS7ZKKG4PYPNQMU3C3XJVAU5QO","json":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO.json","graph_json":"https://pith.science/api/pith-number/TS7ZKKG4PYPNQMU3C3XJVAU5QO/graph.json","events_json":"https://pith.science/api/pith-number/TS7ZKKG4PYPNQMU3C3XJVAU5QO/events.json","paper":"https://pith.science/paper/TS7ZKKG4"},"agent_actions":{"view_html":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO","download_json":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO.json","view_paper":"https://pith.science/paper/TS7ZKKG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21943&json=true","fetch_graph":"https://pith.science/api/pith-number/TS7ZKKG4PYPNQMU3C3XJVAU5QO/graph.json","fetch_events":"https://pith.science/api/pith-number/TS7ZKKG4PYPNQMU3C3XJVAU5QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO/action/storage_attestation","attest_author":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO/action/author_attestation","sign_citation":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO/action/citation_signature","submit_replication":"https://pith.science/pith/TS7ZKKG4PYPNQMU3C3XJVAU5QO/action/replication_record"}},"created_at":"2026-07-27T00:20:29.050737+00:00","updated_at":"2026-07-27T00:20:29.050737+00:00"}