{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ORJC5IC5QLGYRLG2U4UQSC4KUK","short_pith_number":"pith:ORJC5IC5","canonical_record":{"source":{"id":"2605.27772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T23:44:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c8fcbc2af471934056275d74ce7c78dc382e466b27657c86c4264d2d7019f3ba","abstract_canon_sha256":"67ea45aee0935ab7f5018a0cfd136a6408e5f2e0448ce67b8ee6f215b42e6dde"},"schema_version":"1.0"},"canonical_sha256":"74522ea05d82cd88acdaa729090b8aa2b5798a371188b0f00b60a10f265b6662","source":{"kind":"arxiv","id":"2605.27772","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27772","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27772v1","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27772","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"ORJC5IC5QLGY","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"ORJC5IC5QLGYRLG2","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"ORJC5IC5","created_at":"2026-05-28T01:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ORJC5IC5QLGYRLG2U4UQSC4KUK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T23:44:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c8fcbc2af471934056275d74ce7c78dc382e466b27657c86c4264d2d7019f3ba","abstract_canon_sha256":"67ea45aee0935ab7f5018a0cfd136a6408e5f2e0448ce67b8ee6f215b42e6dde"},"schema_version":"1.0"},"canonical_sha256":"74522ea05d82cd88acdaa729090b8aa2b5798a371188b0f00b60a10f265b6662","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:48.460015Z","signature_b64":"saTTjw4n+MJe7NgNNrAcfwaaVmHc0TYIu9f47PkQps70vLu/e6gfi9hF/3ZPEoYweaXrdDbwaQ6nLcTckYn9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74522ea05d82cd88acdaa729090b8aa2b5798a371188b0f00b60a10f265b6662","last_reissued_at":"2026-05-28T01:04:48.459519Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:48.459519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27772","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":"2026-05-28T01:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQ9CrwiSb058whCwFpvuXjdZrAdbN0rWfHrksYEqVLwrhtkrxO/AFf6IL2PG9LWjpwWIG0OHG64dFF69cLu1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T15:18:56.572879Z"},"content_sha256":"a5c5901f945e6efc6877580c8af315a9098d255332dc5e23f359d206c42a353a","schema_version":"1.0","event_id":"sha256:a5c5901f945e6efc6877580c8af315a9098d255332dc5e23f359d206c42a353a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ORJC5IC5QLGYRLG2U4UQSC4KUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SD","authors_text":"Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani","submitted_at":"2026-05-26T23:44:23Z","abstract_excerpt":"Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic information remains limited. To systematically quantify this issue, we introduce VoxParadox, an adversarial benchmark with 2,000 verified examples, spanning 10 paralinguistic tasks, created with controlled speech synthesis to intentionally mismatch transcript claims and speaking style, enabling direct measurement of speech paralinguistic understanding. Evaluation of a diverse set of Audio LLMs reveals consistently low accuracy on acoustic ground "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27772","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/2605.27772/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":"2026-05-28T01:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3xxfJpR7csw6fZmB5HKk+SqyYpRbYCnAPF8vc+fnwagELshT57ZZAGyDVkuZHKPKD0u/4FAWCRvmJNFcN9anAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T15:18:56.573258Z"},"content_sha256":"f505256a566b738b52be9bf5275d0fe7538adca3f32d13ed967e0bad1291a7f9","schema_version":"1.0","event_id":"sha256:f505256a566b738b52be9bf5275d0fe7538adca3f32d13ed967e0bad1291a7f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK/bundle.json","state_url":"https://pith.science/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK/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":"2026-06-29T15:18:56Z","links":{"resolver":"https://pith.science/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK","bundle":"https://pith.science/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK/bundle.json","state":"https://pith.science/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ORJC5IC5QLGYRLG2U4UQSC4KUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ORJC5IC5QLGYRLG2U4UQSC4KUK","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":"67ea45aee0935ab7f5018a0cfd136a6408e5f2e0448ce67b8ee6f215b42e6dde","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T23:44:23Z","title_canon_sha256":"c8fcbc2af471934056275d74ce7c78dc382e466b27657c86c4264d2d7019f3ba"},"schema_version":"1.0","source":{"id":"2605.27772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27772","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27772v1","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27772","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"ORJC5IC5QLGY","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"ORJC5IC5QLGYRLG2","created_at":"2026-05-28T01:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"ORJC5IC5","created_at":"2026-05-28T01:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:f505256a566b738b52be9bf5275d0fe7538adca3f32d13ed967e0bad1291a7f9","target":"graph","created_at":"2026-05-28T01:04:48Z","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/2605.27772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio large language models (Audio LLMs) demonstrate strong performance on speech understanding tasks, yet their ability to understand paralinguistic information remains limited. To systematically quantify this issue, we introduce VoxParadox, an adversarial benchmark with 2,000 verified examples, spanning 10 paralinguistic tasks, created with controlled speech synthesis to intentionally mismatch transcript claims and speaking style, enabling direct measurement of speech paralinguistic understanding. Evaluation of a diverse set of Audio LLMs reveals consistently low accuracy on acoustic ground ","authors_text":"Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T23:44:23Z","title":"Do Audio LLMs Listen or Read? Analyzing and Mitigating Paralinguistic Failures with VoxParadox"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27772","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:a5c5901f945e6efc6877580c8af315a9098d255332dc5e23f359d206c42a353a","target":"record","created_at":"2026-05-28T01:04:48Z","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":"67ea45aee0935ab7f5018a0cfd136a6408e5f2e0448ce67b8ee6f215b42e6dde","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T23:44:23Z","title_canon_sha256":"c8fcbc2af471934056275d74ce7c78dc382e466b27657c86c4264d2d7019f3ba"},"schema_version":"1.0","source":{"id":"2605.27772","kind":"arxiv","version":1}},"canonical_sha256":"74522ea05d82cd88acdaa729090b8aa2b5798a371188b0f00b60a10f265b6662","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74522ea05d82cd88acdaa729090b8aa2b5798a371188b0f00b60a10f265b6662","first_computed_at":"2026-05-28T01:04:48.459519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:48.459519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"saTTjw4n+MJe7NgNNrAcfwaaVmHc0TYIu9f47PkQps70vLu/e6gfi9hF/3ZPEoYweaXrdDbwaQ6nLcTckYn9BQ==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:48.460015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c5901f945e6efc6877580c8af315a9098d255332dc5e23f359d206c42a353a","sha256:f505256a566b738b52be9bf5275d0fe7538adca3f32d13ed967e0bad1291a7f9"],"state_sha256":"6ba92ecf2ebec2af222dd018182104bb804b812462be16cc5b2b2d210586f890"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kr6pqxvT9GQf+mdsYq1/H8xRhreE6hif3RrgcUsQs6mKJU3HMBIu6grPgoic57k3bEungyXJvJ5coNrx7ASxAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T15:18:56.575494Z","bundle_sha256":"2bf445b9135ea82c74e296a21ea2764dc6bd4bb9ea7ec468f8bc1bfe8522aa05"}}