{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Z5GIDVFZHRUEYF5HW4EALTI6VH","short_pith_number":"pith:Z5GIDVFZ","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"},"canonical_sha256":"cf4c81d4b93c684c17a7b70805cd1ea9dcbfe3cf2d57ece83404f643dda1b221","source":{"kind":"arxiv","id":"2607.08800","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Z5GIDVFZHRUEYF5HW4EALTI6VH","target":"record","payload":{"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"},"canonical_sha256":"cf4c81d4b93c684c17a7b70805cd1ea9dcbfe3cf2d57ece83404f643dda1b221","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"},"source_kind":"arxiv","source_id":"2607.08800","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T00:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7h9t32pcFqzQnSqiXazSFI+LHZXidKvEM3Tgb6i2g5o6TawLpFFSK9GWsaUGgU/oIa7embd6CPHLgB95KJqSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:30:27.854576Z"},"content_sha256":"aedb3f961e35a971d7b35bb0a2ca385a7fc3633ea17a30507785b39f5235a773","schema_version":"1.0","event_id":"sha256:aedb3f961e35a971d7b35bb0a2ca385a7fc3633ea17a30507785b39f5235a773"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Z5GIDVFZHRUEYF5HW4EALTI6VH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-13T00:17:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJtNKnGptbPqOLve7Qp6QuAQ1CAOQSMsptwGzuvMmdYGsnwfGrpynUIejoMEI4GbDxVANU1k41uBzlYvmaFiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:30:27.855456Z"},"content_sha256":"da1d15b8105e1fe846988d26dd6cd3f39ec543007f7e813ef80e89334d46fc9c","schema_version":"1.0","event_id":"sha256:da1d15b8105e1fe846988d26dd6cd3f39ec543007f7e813ef80e89334d46fc9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/bundle.json","state_url":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T16:30:27Z","links":{"resolver":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH","bundle":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/bundle.json","state":"https://pith.science/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5GIDVFZHRUEYF5HW4EALTI6VH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9dbfxGEYKHUCiI3t9cysg4BkyoCtYYvPhC+iCCJFe8BTl6z8M4s1vB0M6UaluydSr6gVcBP72mvndp0n5dbBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:30:27.861849Z","bundle_sha256":"a8053c11541654680f999f20dd8c46c111f2538efda1aa303affaef51ef00b88"}}