{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AM5OWQPLQXPFBNY3AKIDUR3Q2Z","short_pith_number":"pith:AM5OWQPL","canonical_record":{"source":{"id":"2410.12948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T18:34:07Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"691fea16cc54532e33541b391fc8046eb9c72f1de2b943150e2beb0f26e2a574","abstract_canon_sha256":"b48869a06e9203abc34ac914f81353100adf08b3054822ce78226de39d592334"},"schema_version":"1.0"},"canonical_sha256":"033aeb41eb85de50b71b02903a4770d65e8082c2cb95fe89783074bae57787c1","source":{"kind":"arxiv","id":"2410.12948","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12948","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12948v1","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12948","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"AM5OWQPLQXPF","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"AM5OWQPLQXPFBNY3","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"AM5OWQPL","created_at":"2026-07-05T09:21:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AM5OWQPLQXPFBNY3AKIDUR3Q2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T18:34:07Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"691fea16cc54532e33541b391fc8046eb9c72f1de2b943150e2beb0f26e2a574","abstract_canon_sha256":"b48869a06e9203abc34ac914f81353100adf08b3054822ce78226de39d592334"},"schema_version":"1.0"},"canonical_sha256":"033aeb41eb85de50b71b02903a4770d65e8082c2cb95fe89783074bae57787c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:53.227765Z","signature_b64":"q3Cn/KD+rlfrGR4pHIlJPTo1xb5nEtLrha0FBNEUeJlT3pmq9p55DxSGN4s9oPDg4acpJ8KicHdKNUFSALo8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"033aeb41eb85de50b71b02903a4770d65e8082c2cb95fe89783074bae57787c1","last_reissued_at":"2026-07-05T09:21:53.227292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:53.227292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12948","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":"2026-07-05T09:21:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5SbXL+lSKGxtdH3r9BUzC+oCwY1+e+LeKkn0TAC/FTCPJ0z/7Ckq1n6KcvFIOlYYfgdvBV0brKHfD4UlKZuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:42:04.015861Z"},"content_sha256":"ff2df906e1e0cbb44b6ba41b4427710b51bb9cdf615bf3144d1fb1417b74d706","schema_version":"1.0","event_id":"sha256:ff2df906e1e0cbb44b6ba41b4427710b51bb9cdf615bf3144d1fb1417b74d706"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AM5OWQPLQXPFBNY3AKIDUR3Q2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Do Speech Foundation Models Not Learn About Speech?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Abdul Waheed, Bhiksha Raj, Hanin Atwany, Rita Singh","submitted_at":"2024-10-16T18:34:07Z","abstract_excerpt":"Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec, HuBERT, and Qwen2-Audio focusing on their learned representations in both paralinguistic and non-paralinguistic tasks from the Dynamic-SUPERB benchmark. Our study addresses three key questions: (1) What non-verbal cues (e.g., speaker intent, emotion, environmental context) are captured? (2) How are these cues represented across different layers of the models?"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12948","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/2410.12948/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":"2026-07-05T09:21:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2oLWCrd1gU+9ptg7htmOSOM4XYBdam2bEloY+lTrRX2O/vMxuk8I1aYvSwKcF+KKRQ93HVL/cSKCG3S7eXPGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:42:04.016799Z"},"content_sha256":"366b2ab67ae74344c7d02e8c786be2fa595e4a19c7b93f639c768abbb8b039f0","schema_version":"1.0","event_id":"sha256:366b2ab67ae74344c7d02e8c786be2fa595e4a19c7b93f639c768abbb8b039f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z/bundle.json","state_url":"https://pith.science/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z/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":"2026-08-08T14:42:04Z","links":{"resolver":"https://pith.science/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z","bundle":"https://pith.science/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z/bundle.json","state":"https://pith.science/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AM5OWQPLQXPFBNY3AKIDUR3Q2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AM5OWQPLQXPFBNY3AKIDUR3Q2Z","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":"b48869a06e9203abc34ac914f81353100adf08b3054822ce78226de39d592334","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T18:34:07Z","title_canon_sha256":"691fea16cc54532e33541b391fc8046eb9c72f1de2b943150e2beb0f26e2a574"},"schema_version":"1.0","source":{"id":"2410.12948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12948","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12948v1","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12948","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"AM5OWQPLQXPF","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"AM5OWQPLQXPFBNY3","created_at":"2026-07-05T09:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"AM5OWQPL","created_at":"2026-07-05T09:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:366b2ab67ae74344c7d02e8c786be2fa595e4a19c7b93f639c768abbb8b039f0","target":"graph","created_at":"2026-07-05T09:21:53Z","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/2410.12948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding how speech foundation models capture non-verbal cues is crucial for improving their interpretability and adaptability across diverse tasks. In our work, we analyze several prominent models such as Whisper, Seamless, Wav2Vec, HuBERT, and Qwen2-Audio focusing on their learned representations in both paralinguistic and non-paralinguistic tasks from the Dynamic-SUPERB benchmark. Our study addresses three key questions: (1) What non-verbal cues (e.g., speaker intent, emotion, environmental context) are captured? (2) How are these cues represented across different layers of the models?","authors_text":"Abdul Waheed, Bhiksha Raj, Hanin Atwany, Rita Singh","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T18:34:07Z","title":"What Do Speech Foundation Models Not Learn About Speech?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12948","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:ff2df906e1e0cbb44b6ba41b4427710b51bb9cdf615bf3144d1fb1417b74d706","target":"record","created_at":"2026-07-05T09:21:53Z","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":"b48869a06e9203abc34ac914f81353100adf08b3054822ce78226de39d592334","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T18:34:07Z","title_canon_sha256":"691fea16cc54532e33541b391fc8046eb9c72f1de2b943150e2beb0f26e2a574"},"schema_version":"1.0","source":{"id":"2410.12948","kind":"arxiv","version":1}},"canonical_sha256":"033aeb41eb85de50b71b02903a4770d65e8082c2cb95fe89783074bae57787c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"033aeb41eb85de50b71b02903a4770d65e8082c2cb95fe89783074bae57787c1","first_computed_at":"2026-07-05T09:21:53.227292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:53.227292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q3Cn/KD+rlfrGR4pHIlJPTo1xb5nEtLrha0FBNEUeJlT3pmq9p55DxSGN4s9oPDg4acpJ8KicHdKNUFSALo8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:53.227765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff2df906e1e0cbb44b6ba41b4427710b51bb9cdf615bf3144d1fb1417b74d706","sha256:366b2ab67ae74344c7d02e8c786be2fa595e4a19c7b93f639c768abbb8b039f0"],"state_sha256":"985c8843a83f50320cc1cc067a40b78188a0af2d2783fb6fd5e1a7c0b5923c90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yiwzv0xjhrMy7ikmFsaeqt19pN+KPJe82TwiJ9QqIWALptXIaR2UjNQD/vzyJK6Pl8EHtMiBsok178V/xdMVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:42:04.025141Z","bundle_sha256":"65fd628497678a173d675a7966853319223a903432d3df8d7af68283a5a78d89"}}