{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TS7ZKKG4PYPNQMU3C3XJVAU5QO","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":"95ea5061430482feaa724e2b09a74aef836a30ead88ce3076d34e528cf540fa3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T03:39:34Z","title_canon_sha256":"39decbd776f4a52abddc187226a55359f3debe0b32e1dfe2c8af3e020c7bfd3f"},"schema_version":"1.0","source":{"id":"2607.21943","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21943","created_at":"2026-07-27T00:20:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21943v1","created_at":"2026-07-27T00:20:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21943","created_at":"2026-07-27T00:20:29Z"},{"alias_kind":"pith_short_12","alias_value":"TS7ZKKG4PYPN","created_at":"2026-07-27T00:20:29Z"},{"alias_kind":"pith_short_16","alias_value":"TS7ZKKG4PYPNQMU3","created_at":"2026-07-27T00:20:29Z"},{"alias_kind":"pith_short_8","alias_value":"TS7ZKKG4","created_at":"2026-07-27T00:20:29Z"}],"graph_snapshots":[{"event_id":"sha256:6ac68fbf92322ddd854d8be25eb3c5d954754b18dfa518b8c7caaba97230ba3d","target":"graph","created_at":"2026-07-27T00:20:29Z","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/2607.21943/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Biao Tian, Li Liu, Minghao Yang, Pengfei Zhang, Tianxin Xie, Xiangang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T03:39:34Z","title":"Listen, Do Not Copy: Internalizing Audio-Grounded Scaffold Context for Robust Omni-Model Speech Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21943","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":"sha256:8b8f0f860aba57afb7d658c94a2d23868078fc216628386f30f8bcb027468668","target":"record","created_at":"2026-07-27T00:20:29Z","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":"95ea5061430482feaa724e2b09a74aef836a30ead88ce3076d34e528cf540fa3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-24T03:39:34Z","title_canon_sha256":"39decbd776f4a52abddc187226a55359f3debe0b32e1dfe2c8af3e020c7bfd3f"},"schema_version":"1.0","source":{"id":"2607.21943","kind":"arxiv","version":1}},"canonical_sha256":"9cbf9528dc7e1ed8329b16ee9a829d83bf1ec123f5cb62ee2c73f443ebf125d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cbf9528dc7e1ed8329b16ee9a829d83bf1ec123f5cb62ee2c73f443ebf125d8","first_computed_at":"2026-07-27T00:20:29.050291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-27T00:20:29.050291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZeH/X/OOCunYjIVvtUZ68yK8LlHEPB7e9FtRy5GGyUS1Jm+yUJ4g8VFdYHBZQtz/HyHGlArmePLwXw27vHgGCQ==","signature_status":"signed_v1","signed_at":"2026-07-27T00:20:29.051140Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21943","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b8f0f860aba57afb7d658c94a2d23868078fc216628386f30f8bcb027468668","sha256:6ac68fbf92322ddd854d8be25eb3c5d954754b18dfa518b8c7caaba97230ba3d"],"state_sha256":"8d6b12dbe1623ec053e5e58f5d96c2315e55ce1f85123a35f857851685b71b7a"}