{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DO6PVYKTXWNARBUJI46PGRQALS","short_pith_number":"pith:DO6PVYKT","schema_version":"1.0","canonical_sha256":"1bbcfae153bd9a088689473cf346005c8f372c71dd82380a283ef7a5b1aa23c2","source":{"kind":"arxiv","id":"2606.10233","version":1},"attestation_state":"computed","paper":{"title":"ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hye-Jin Shim, Jiatong Shi, Shinji Watanabe, Zhuoyan Tao","submitted_at":"2026-06-08T22:46:30Z","abstract_excerpt":"While speech quality is typically assessed on complete utterances, streaming and generative systems require incremental estimation from partial audio. Existing predictors assume full context, degrading on prefix-constrained inputs. Extending ARECHO, we propose ANCHOR, reformulating incremental assessment as a multi-resolution autoregressive task. It models chunk- and utterance-level quality within a single decoder using dual-resolution tokens and a resolution-aware hierarchy for coarse-to-fine refinement. Experiments show substantial robustness under partial input, including a 48% PLCMOS error"},"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":"2606.10233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T22:46:30Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"4f95c30b48537757128ef8035e3ffea68bb006563f6f5c19492e180d34eda66b","abstract_canon_sha256":"307366e12c8321f05308d98053aedbd01220addf4c6d5fc3b71c8d8b90ff3246"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:00.875629Z","signature_b64":"sMxDDknuLwODHJnFPC3Eq4urzZtQviNHjVBOyvZ63Y0trvUaedNg3C35rdhytvuqXMONBsi1giip3+hsedbSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bbcfae153bd9a088689473cf346005c8f372c71dd82380a283ef7a5b1aa23c2","last_reissued_at":"2026-06-10T01:09:00.874851Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:00.874851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hye-Jin Shim, Jiatong Shi, Shinji Watanabe, Zhuoyan Tao","submitted_at":"2026-06-08T22:46:30Z","abstract_excerpt":"While speech quality is typically assessed on complete utterances, streaming and generative systems require incremental estimation from partial audio. Existing predictors assume full context, degrading on prefix-constrained inputs. Extending ARECHO, we propose ANCHOR, reformulating incremental assessment as a multi-resolution autoregressive task. It models chunk- and utterance-level quality within a single decoder using dual-resolution tokens and a resolution-aware hierarchy for coarse-to-fine refinement. Experiments show substantial robustness under partial input, including a 48% PLCMOS error"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10233","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/2606.10233/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":"2606.10233","created_at":"2026-06-10T01:09:00.874965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10233v1","created_at":"2026-06-10T01:09:00.874965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10233","created_at":"2026-06-10T01:09:00.874965+00:00"},{"alias_kind":"pith_short_12","alias_value":"DO6PVYKTXWNA","created_at":"2026-06-10T01:09:00.874965+00:00"},{"alias_kind":"pith_short_16","alias_value":"DO6PVYKTXWNARBUJ","created_at":"2026-06-10T01:09:00.874965+00:00"},{"alias_kind":"pith_short_8","alias_value":"DO6PVYKT","created_at":"2026-06-10T01:09:00.874965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.10233","citing_title":"ANCHOR: Autoregressive Non-intrusive Chunk-Ordered Refinement for Joint Multi-Resolution Speech Quality Modeling","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS","json":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS.json","graph_json":"https://pith.science/api/pith-number/DO6PVYKTXWNARBUJI46PGRQALS/graph.json","events_json":"https://pith.science/api/pith-number/DO6PVYKTXWNARBUJI46PGRQALS/events.json","paper":"https://pith.science/paper/DO6PVYKT"},"agent_actions":{"view_html":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS","download_json":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS.json","view_paper":"https://pith.science/paper/DO6PVYKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10233&json=true","fetch_graph":"https://pith.science/api/pith-number/DO6PVYKTXWNARBUJI46PGRQALS/graph.json","fetch_events":"https://pith.science/api/pith-number/DO6PVYKTXWNARBUJI46PGRQALS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS/action/storage_attestation","attest_author":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS/action/author_attestation","sign_citation":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS/action/citation_signature","submit_replication":"https://pith.science/pith/DO6PVYKTXWNARBUJI46PGRQALS/action/replication_record"}},"created_at":"2026-06-10T01:09:00.874965+00:00","updated_at":"2026-06-10T01:09:00.874965+00:00"}