{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4XNARLCOFKEYICMR6QWC4ZFWRG","short_pith_number":"pith:4XNARLCO","schema_version":"1.0","canonical_sha256":"e5da08ac4e2a89840991f42c2e64b689918d5a5c12b0d6997a74cda2ace2f312","source":{"kind":"arxiv","id":"2605.23619","version":1},"attestation_state":"computed","paper":{"title":"Frame-Aligned Fusion of Canary and WavLM for Non-Intrusive Intelligibility Prediction of Hearing-Aid-Processed Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kazushi Nakazawa","submitted_at":"2026-05-22T13:26:47Z","abstract_excerpt":"Non-intrusive intelligibility prediction estimates how well hearing-impaired listeners understand hearing-aid-processed speech without a clean reference. We study this task in the 3rd Clarity Prediction Challenge using two frozen speech encoders, Canary and WavLM. The central question is not only whether complementary pretrained representations should be combined, but where their interaction should occur. We compare single-backbone baselines, uniform score averaging, pool-late fusion, cross-attention, frame-aligned fusion, and reverse alignment under a shared left/right-preserving binaural fra"},"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":"2605.23619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-22T13:26:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"4f741f9bcb58c02fe901484a2f87ec618529d1f0f18b819023482caf21ce6214","abstract_canon_sha256":"9d2fc6ab0bc338dede847e46e99f59fa6c7b6db8e22beb57195f4d226033138f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:22.308702Z","signature_b64":"IjUyHbd0nnArRIj1/wx/BGqM9fipAaofNu3hiW51dPZI9Is2UHGo2/62PukZH5+rHJPPIeF5yqBpXJoQgoKcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5da08ac4e2a89840991f42c2e64b689918d5a5c12b0d6997a74cda2ace2f312","last_reissued_at":"2026-05-25T02:02:22.308050Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:22.308050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frame-Aligned Fusion of Canary and WavLM for Non-Intrusive Intelligibility Prediction of Hearing-Aid-Processed Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Kazushi Nakazawa","submitted_at":"2026-05-22T13:26:47Z","abstract_excerpt":"Non-intrusive intelligibility prediction estimates how well hearing-impaired listeners understand hearing-aid-processed speech without a clean reference. We study this task in the 3rd Clarity Prediction Challenge using two frozen speech encoders, Canary and WavLM. The central question is not only whether complementary pretrained representations should be combined, but where their interaction should occur. We compare single-backbone baselines, uniform score averaging, pool-late fusion, cross-attention, frame-aligned fusion, and reverse alignment under a shared left/right-preserving binaural fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23619","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/2605.23619/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":"2605.23619","created_at":"2026-05-25T02:02:22.308151+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23619v1","created_at":"2026-05-25T02:02:22.308151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23619","created_at":"2026-05-25T02:02:22.308151+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XNARLCOFKEY","created_at":"2026-05-25T02:02:22.308151+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XNARLCOFKEYICMR","created_at":"2026-05-25T02:02:22.308151+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XNARLCO","created_at":"2026-05-25T02:02:22.308151+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/4XNARLCOFKEYICMR6QWC4ZFWRG","json":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG.json","graph_json":"https://pith.science/api/pith-number/4XNARLCOFKEYICMR6QWC4ZFWRG/graph.json","events_json":"https://pith.science/api/pith-number/4XNARLCOFKEYICMR6QWC4ZFWRG/events.json","paper":"https://pith.science/paper/4XNARLCO"},"agent_actions":{"view_html":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG","download_json":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG.json","view_paper":"https://pith.science/paper/4XNARLCO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23619&json=true","fetch_graph":"https://pith.science/api/pith-number/4XNARLCOFKEYICMR6QWC4ZFWRG/graph.json","fetch_events":"https://pith.science/api/pith-number/4XNARLCOFKEYICMR6QWC4ZFWRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG/action/storage_attestation","attest_author":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG/action/author_attestation","sign_citation":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG/action/citation_signature","submit_replication":"https://pith.science/pith/4XNARLCOFKEYICMR6QWC4ZFWRG/action/replication_record"}},"created_at":"2026-05-25T02:02:22.308151+00:00","updated_at":"2026-05-25T02:02:22.308151+00:00"}