{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CQ2TMODXJUVTA7Q7VEIJWMHAVZ","short_pith_number":"pith:CQ2TMODX","canonical_record":{"source":{"id":"2606.07309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T14:26:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce32138531c1497d1fd730c37a48b50f63f080756de46fb96b40a11a767a2dab","abstract_canon_sha256":"bb53d110f9fa115e2fcfa15d780a3d435ed63cd8cb86975786c00f8b78a247f8"},"schema_version":"1.0"},"canonical_sha256":"14353638774d2b307e1fa9109b30e0ae67a684cd88cfde236444760487a60c28","source":{"kind":"arxiv","id":"2606.07309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07309","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07309v1","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07309","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"CQ2TMODXJUVT","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"CQ2TMODXJUVTA7Q7","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"CQ2TMODX","created_at":"2026-06-08T01:05:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CQ2TMODXJUVTA7Q7VEIJWMHAVZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07309","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T14:26:06Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ce32138531c1497d1fd730c37a48b50f63f080756de46fb96b40a11a767a2dab","abstract_canon_sha256":"bb53d110f9fa115e2fcfa15d780a3d435ed63cd8cb86975786c00f8b78a247f8"},"schema_version":"1.0"},"canonical_sha256":"14353638774d2b307e1fa9109b30e0ae67a684cd88cfde236444760487a60c28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:18.943290Z","signature_b64":"pJV78fuv0mLYODGHuIoJpoPpm4rRuB7kw8fxWRrqxMk/uB/iVdMZILJctGTF6g9HYcPAnLAn47jk4Gr614EkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14353638774d2b307e1fa9109b30e0ae67a684cd88cfde236444760487a60c28","last_reissued_at":"2026-06-08T01:05:18.942429Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:18.942429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07309","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":"2026-06-08T01:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GBJ1mxIuU9rgH5td1n4DYTRZ9DBgMxd8d5Y/KfIVZdMpkNmq4WcjG/iKrdFnCqWXTMvG6aipQ3RWu9Hg36KlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:25:25.188441Z"},"content_sha256":"6adf2278edb40b79ee25643d64e2e6fdedc8110b8601ba7ae7f717c522fce054","schema_version":"1.0","event_id":"sha256:6adf2278edb40b79ee25643d64e2e6fdedc8110b8601ba7ae7f717c522fce054"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CQ2TMODXJUVTA7Q7VEIJWMHAVZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Iosif Tsangko","submitted_at":"2026-06-05T14:26:06Z","abstract_excerpt":"Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available. We study this question in speech emotion recognition (SER) by deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set. These tokens summarise energy, pitch, dynamics, brightness, formants, and voice quality, and are appended to the textual prompt while the audio input is kept unchanged. Across the widely used FAU-Aibo and IEMOCAP benchmarks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07309","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/2606.07309/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":"2026-06-08T01:05:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FFTPRNmciTvT8fJIik/ZZbj+CP0/LEg0tNuSMLF8W1fLSQfymXB3ox3IteijePPmP3E/7vBmfEuTKNQi6BHcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:25:25.188823Z"},"content_sha256":"238f3760158baa10362d0f464a2c9c242e98abc3a5457997eee3bd54da37ce6a","schema_version":"1.0","event_id":"sha256:238f3760158baa10362d0f464a2c9c242e98abc3a5457997eee3bd54da37ce6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ/bundle.json","state_url":"https://pith.science/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ/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":"2026-06-29T21:25:25Z","links":{"resolver":"https://pith.science/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ","bundle":"https://pith.science/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ/bundle.json","state":"https://pith.science/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQ2TMODXJUVTA7Q7VEIJWMHAVZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CQ2TMODXJUVTA7Q7VEIJWMHAVZ","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":"bb53d110f9fa115e2fcfa15d780a3d435ed63cd8cb86975786c00f8b78a247f8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T14:26:06Z","title_canon_sha256":"ce32138531c1497d1fd730c37a48b50f63f080756de46fb96b40a11a767a2dab"},"schema_version":"1.0","source":{"id":"2606.07309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07309","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07309v1","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07309","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"pith_short_12","alias_value":"CQ2TMODXJUVT","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"pith_short_16","alias_value":"CQ2TMODXJUVTA7Q7","created_at":"2026-06-08T01:05:18Z"},{"alias_kind":"pith_short_8","alias_value":"CQ2TMODX","created_at":"2026-06-08T01:05:18Z"}],"graph_snapshots":[{"event_id":"sha256:238f3760158baa10362d0f464a2c9c242e98abc3a5457997eee3bd54da37ce6a","target":"graph","created_at":"2026-06-08T01:05:18Z","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/2606.07309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available. We study this question in speech emotion recognition (SER) by deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set. These tokens summarise energy, pitch, dynamics, brightness, formants, and voice quality, and are appended to the textual prompt while the audio input is kept unchanged. Across the widely used FAU-Aibo and IEMOCAP benchmarks","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Iosif Tsangko","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T14:26:06Z","title":"Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07309","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":"sha256:6adf2278edb40b79ee25643d64e2e6fdedc8110b8601ba7ae7f717c522fce054","target":"record","created_at":"2026-06-08T01:05:18Z","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":"bb53d110f9fa115e2fcfa15d780a3d435ed63cd8cb86975786c00f8b78a247f8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-05T14:26:06Z","title_canon_sha256":"ce32138531c1497d1fd730c37a48b50f63f080756de46fb96b40a11a767a2dab"},"schema_version":"1.0","source":{"id":"2606.07309","kind":"arxiv","version":1}},"canonical_sha256":"14353638774d2b307e1fa9109b30e0ae67a684cd88cfde236444760487a60c28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14353638774d2b307e1fa9109b30e0ae67a684cd88cfde236444760487a60c28","first_computed_at":"2026-06-08T01:05:18.942429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:05:18.942429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pJV78fuv0mLYODGHuIoJpoPpm4rRuB7kw8fxWRrqxMk/uB/iVdMZILJctGTF6g9HYcPAnLAn47jk4Gr614EkAA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:05:18.943290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6adf2278edb40b79ee25643d64e2e6fdedc8110b8601ba7ae7f717c522fce054","sha256:238f3760158baa10362d0f464a2c9c242e98abc3a5457997eee3bd54da37ce6a"],"state_sha256":"5d0878c0947eea553002294029de67c17473a9b23da5e587fe4ead5c56bb395e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxhFZ8LGnMOYro/i/gLOkHiz8Tsv1IwDh6jic4YiGkLjrD8Y0O8R2o1QJuNrNYDrL0Q2UNSIAZDw6r/dO5tgCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T21:25:25.190839Z","bundle_sha256":"d1268a5b137859ad2a34dd63cb1eb6d5e3a830e45162db852d8f3e2bbb8eaae4"}}