{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Z5GIDVFZHRUEYF5HW4EALTI6VH","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":"d901860fa325f6650536b6ee2c0108f2d36860ba9e9f1096210d9d9c8ad6066f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-09T03:10:16Z","title_canon_sha256":"5dddebbf4144af8503b4a99eca1cae42dc5d3875efd1a4ebe25eb21bfe700fe3"},"schema_version":"1.0","source":{"id":"2607.08800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08800","created_at":"2026-07-13T00:17:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08800v1","created_at":"2026-07-13T00:17:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08800","created_at":"2026-07-13T00:17:17Z"},{"alias_kind":"pith_short_12","alias_value":"Z5GIDVFZHRUE","created_at":"2026-07-13T00:17:17Z"},{"alias_kind":"pith_short_16","alias_value":"Z5GIDVFZHRUEYF5H","created_at":"2026-07-13T00:17:17Z"},{"alias_kind":"pith_short_8","alias_value":"Z5GIDVFZ","created_at":"2026-07-13T00:17:17Z"}],"graph_snapshots":[{"event_id":"sha256:da1d15b8105e1fe846988d26dd6cd3f39ec543007f7e813ef80e89334d46fc9c","target":"graph","created_at":"2026-07-13T00:17:17Z","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/2607.08800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hen-Hsen Huang, Shuo-Chun Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-09T03:10:16Z","title":"Dual-BEATs: Unlocking Zero-Shot Stereo Audio Perception in Audio Large Language Models via Dithering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08800","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:aedb3f961e35a971d7b35bb0a2ca385a7fc3633ea17a30507785b39f5235a773","target":"record","created_at":"2026-07-13T00:17:17Z","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":"d901860fa325f6650536b6ee2c0108f2d36860ba9e9f1096210d9d9c8ad6066f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-09T03:10:16Z","title_canon_sha256":"5dddebbf4144af8503b4a99eca1cae42dc5d3875efd1a4ebe25eb21bfe700fe3"},"schema_version":"1.0","source":{"id":"2607.08800","kind":"arxiv","version":1}},"canonical_sha256":"cf4c81d4b93c684c17a7b70805cd1ea9dcbfe3cf2d57ece83404f643dda1b221","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf4c81d4b93c684c17a7b70805cd1ea9dcbfe3cf2d57ece83404f643dda1b221","first_computed_at":"2026-07-13T00:17:17.700538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:17.700538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4W0FIudfCYCEGJeXHf51WYsxH+aJBmNy7rTLziU/0Uwsj+j14ZS+i7+xTGZLiO+fpwMONVpszUoSwhgNbGqfBw==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:17.701611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aedb3f961e35a971d7b35bb0a2ca385a7fc3633ea17a30507785b39f5235a773","sha256:da1d15b8105e1fe846988d26dd6cd3f39ec543007f7e813ef80e89334d46fc9c"],"state_sha256":"82ecc94555fd4fda9cbf25b6f43e46401b491cb28fdc3156ea48a0c428c2f5b3"}