{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z5GIDVFZHRUEYF5HW4EALTI6VH","short_pith_number":"pith:Z5GIDVFZ","schema_version":"1.0","canonical_sha256":"cf4c81d4b93c684c17a7b70805cd1ea9dcbfe3cf2d57ece83404f643dda1b221","source":{"kind":"arxiv","id":"2607.08800","version":1},"attestation_state":"computed","paper":{"title":"Dual-BEATs: Unlocking Zero-Shot Stereo Audio Perception in Audio Large Language Models via Dithering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Hen-Hsen Huang, Shuo-Chun Lin","submitted_at":"2026-07-09T03:10:16Z","abstract_excerpt":"Multimodal Large Language Models (LLMs) have remarkable semantic audio understanding, yet they remain \"spatially agnostic\" due to their reliance on mono-channel audio representations. Currently, spatial audio perception methods mainly focus on complex room simulations and custom-trained, geometry-aware stereo encoders, which limits their accessibility and generalizability. In this paper, we introduce the Dual-BEATs architecture, in which the left and right audio channels are routed independently through two identical semantic encoders as an alternative to specialized spatial modules. To circum"},"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":"2607.08800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-09T03:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"5dddebbf4144af8503b4a99eca1cae42dc5d3875efd1a4ebe25eb21bfe700fe3","abstract_canon_sha256":"d901860fa325f6650536b6ee2c0108f2d36860ba9e9f1096210d9d9c8ad6066f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:17.701611Z","signature_b64":"4W0FIudfCYCEGJeXHf51WYsxH+aJBmNy7rTLziU/0Uwsj+j14ZS+i7+xTGZLiO+fpwMONVpszUoSwhgNbGqfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf4c81d4b93c684c17a7b70805cd1ea9dcbfe3cf2d57ece83404f643dda1b221","last_reissued_at":"2026-07-13T00:17:17.700538Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:17.700538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-BEATs: Unlocking Zero-Shot Stereo Audio Perception in Audio Large Language Models via Dithering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Hen-Hsen Huang, Shuo-Chun Lin","submitted_at":"2026-07-09T03:10:16Z","abstract_excerpt":"Multimodal Large Language Models (LLMs) have remarkable semantic audio understanding, yet they remain \"spatially agnostic\" due to their reliance on mono-channel audio representations. Currently, spatial audio perception methods mainly focus on complex room simulations and custom-trained, geometry-aware stereo encoders, which limits their accessibility and generalizability. In this paper, we introduce the Dual-BEATs architecture, in which the left and right audio channels are routed independently through two identical semantic encoders as an alternative to specialized spatial modules. To circum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08800","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/2607.08800/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":"2607.08800","created_at":"2026-07-13T00:17:17.701103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08800v1","created_at":"2026-07-13T00:17:17.701103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08800","created_at":"2026-07-13T00:17:17.701103+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5GIDVFZHRUE","created_at":"2026-07-13T00:17:17.701103+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5GIDVFZHRUEYF5H","created_at":"2026-07-13T00:17:17.701103+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5GIDVFZ","created_at":"2026-07-13T00:17:17.701103+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/Z5GIDVFZHRUEYF5HW4EALTI6VH","json":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH.json","graph_json":"https://pith.science/api/pith-number/Z5GIDVFZHRUEYF5HW4EALTI6VH/graph.json","events_json":"https://pith.science/api/pith-number/Z5GIDVFZHRUEYF5HW4EALTI6VH/events.json","paper":"https://pith.science/paper/Z5GIDVFZ"},"agent_actions":{"view_html":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH","download_json":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH.json","view_paper":"https://pith.science/paper/Z5GIDVFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08800&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5GIDVFZHRUEYF5HW4EALTI6VH/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5GIDVFZHRUEYF5HW4EALTI6VH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/action/storage_attestation","attest_author":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/action/author_attestation","sign_citation":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/action/citation_signature","submit_replication":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/action/replication_record"}},"created_at":"2026-07-13T00:17:17.701103+00:00","updated_at":"2026-07-13T00:17:17.701103+00:00"}