{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NR56754HXGIYXBIL7ATEKYSNTJ","short_pith_number":"pith:NR56754H","canonical_record":{"source":{"id":"2502.09940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T06:34:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"202a163106ef4ee81fd622b432c77880f60dc58f2df33818f2d156d13768958f","abstract_canon_sha256":"1b16de3a8f3c3d1158bb6c58b14f36211e42845c188957931f02fd8356abae19"},"schema_version":"1.0"},"canonical_sha256":"6c7beff787b9918b850bf82645624d9a73a47cb768897d4f7d9f8eea03c24548","source":{"kind":"arxiv","id":"2502.09940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09940","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09940v1","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09940","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"NR56754HXGIY","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"NR56754HXGIYXBIL","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"NR56754H","created_at":"2026-07-05T10:14:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NR56754HXGIYXBIL7ATEKYSNTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T06:34:08Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"202a163106ef4ee81fd622b432c77880f60dc58f2df33818f2d156d13768958f","abstract_canon_sha256":"1b16de3a8f3c3d1158bb6c58b14f36211e42845c188957931f02fd8356abae19"},"schema_version":"1.0"},"canonical_sha256":"6c7beff787b9918b850bf82645624d9a73a47cb768897d4f7d9f8eea03c24548","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:14.945544Z","signature_b64":"Bc4aoHKI9+BjE7wwGipNH4iSR0a3QhbqDclwpVmgMuDFRph0AhZ1VZ6SN6wZX36H8X7IP038mHY8TaZl5B8NBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c7beff787b9918b850bf82645624d9a73a47cb768897d4f7d9f8eea03c24548","last_reissued_at":"2026-07-05T10:14:14.944998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:14.944998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09940","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":"2026-07-05T10:14:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDmo8VhQ0CeoGwYDEm8bQtyjIXM4Ey1/XxvP2OLRn1xTvbQy74uaRRokZWaiI/n+ldefm85KCfoXHgHF0CrTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:30:39.863904Z"},"content_sha256":"12d1423c2bad60cbaaf9eacb5e56b737099f00a0e1291a9b8f5181a8d86b5478","schema_version":"1.0","event_id":"sha256:12d1423c2bad60cbaaf9eacb5e56b737099f00a0e1291a9b8f5181a8d86b5478"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NR56754HXGIYXBIL7ATEKYSNTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Preliminary Exploration with GPT-4o Voice Mode","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chen-An Li, Chien-yu Huang, Chih-Kai Yang, Hung-yi Lee, Wei-Chih Chen, Xuanjun Chen, Yu-Xiang Lin","submitted_at":"2025-02-14T06:34:08Z","abstract_excerpt":"With the rise of multimodal large language models, GPT-4o stands out as a pioneering model, driving us to evaluate its capabilities. This report assesses GPT-4o across various tasks to analyze its audio processing and reasoning abilities. We find that GPT-4o exhibits strong knowledge in audio, speech, and music understanding, performing well in tasks like intent classification, spoken command classification, semantic and grammatical reasoning., multilingual speech recognition, and singing analysis. It also shows greater robustness against hallucinations than other large audio-language models ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09940","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/2502.09940/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":"2026-07-05T10:14:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjOrAg6jlwUMHLtCyrRNlf9Sh+PNtmTpvnm6lVMgG1X7AZdju9fx3egAks7okbL7q0l1OFkErS5DRH/q6i4WDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:30:39.865066Z"},"content_sha256":"1b5df7ba2b0017c2667d24a9e1ccaf55538a23c105b572db579b94e43b5be4b8","schema_version":"1.0","event_id":"sha256:1b5df7ba2b0017c2667d24a9e1ccaf55538a23c105b572db579b94e43b5be4b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NR56754HXGIYXBIL7ATEKYSNTJ/bundle.json","state_url":"https://pith.science/pith/NR56754HXGIYXBIL7ATEKYSNTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NR56754HXGIYXBIL7ATEKYSNTJ/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":"2026-08-15T21:30:39Z","links":{"resolver":"https://pith.science/pith/NR56754HXGIYXBIL7ATEKYSNTJ","bundle":"https://pith.science/pith/NR56754HXGIYXBIL7ATEKYSNTJ/bundle.json","state":"https://pith.science/pith/NR56754HXGIYXBIL7ATEKYSNTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NR56754HXGIYXBIL7ATEKYSNTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NR56754HXGIYXBIL7ATEKYSNTJ","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":"1b16de3a8f3c3d1158bb6c58b14f36211e42845c188957931f02fd8356abae19","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T06:34:08Z","title_canon_sha256":"202a163106ef4ee81fd622b432c77880f60dc58f2df33818f2d156d13768958f"},"schema_version":"1.0","source":{"id":"2502.09940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09940","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09940v1","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09940","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_12","alias_value":"NR56754HXGIY","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_16","alias_value":"NR56754HXGIYXBIL","created_at":"2026-07-05T10:14:14Z"},{"alias_kind":"pith_short_8","alias_value":"NR56754H","created_at":"2026-07-05T10:14:14Z"}],"graph_snapshots":[{"event_id":"sha256:1b5df7ba2b0017c2667d24a9e1ccaf55538a23c105b572db579b94e43b5be4b8","target":"graph","created_at":"2026-07-05T10:14:14Z","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/2502.09940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of multimodal large language models, GPT-4o stands out as a pioneering model, driving us to evaluate its capabilities. This report assesses GPT-4o across various tasks to analyze its audio processing and reasoning abilities. We find that GPT-4o exhibits strong knowledge in audio, speech, and music understanding, performing well in tasks like intent classification, spoken command classification, semantic and grammatical reasoning., multilingual speech recognition, and singing analysis. It also shows greater robustness against hallucinations than other large audio-language models (","authors_text":"Chen-An Li, Chien-yu Huang, Chih-Kai Yang, Hung-yi Lee, Wei-Chih Chen, Xuanjun Chen, Yu-Xiang Lin","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T06:34:08Z","title":"A Preliminary Exploration with GPT-4o Voice Mode"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09940","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":"sha256:12d1423c2bad60cbaaf9eacb5e56b737099f00a0e1291a9b8f5181a8d86b5478","target":"record","created_at":"2026-07-05T10:14:14Z","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":"1b16de3a8f3c3d1158bb6c58b14f36211e42845c188957931f02fd8356abae19","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-14T06:34:08Z","title_canon_sha256":"202a163106ef4ee81fd622b432c77880f60dc58f2df33818f2d156d13768958f"},"schema_version":"1.0","source":{"id":"2502.09940","kind":"arxiv","version":1}},"canonical_sha256":"6c7beff787b9918b850bf82645624d9a73a47cb768897d4f7d9f8eea03c24548","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c7beff787b9918b850bf82645624d9a73a47cb768897d4f7d9f8eea03c24548","first_computed_at":"2026-07-05T10:14:14.944998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:14.944998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bc4aoHKI9+BjE7wwGipNH4iSR0a3QhbqDclwpVmgMuDFRph0AhZ1VZ6SN6wZX36H8X7IP038mHY8TaZl5B8NBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:14.945544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12d1423c2bad60cbaaf9eacb5e56b737099f00a0e1291a9b8f5181a8d86b5478","sha256:1b5df7ba2b0017c2667d24a9e1ccaf55538a23c105b572db579b94e43b5be4b8"],"state_sha256":"1618a65c492c60fb4fa467da002f6e740f079352c621839f074381c78acdfc7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QTu1dyjaKdUEdZ/nX9jaewi6/KkknSFJmg/sjDVEnRYToI8PkyACiEgau45su+0PhnYTxNYOLvpQpDE+AUTDCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:30:39.872169Z","bundle_sha256":"0809f4a443228f67343baa4dd54dffc6708f4556ef4f5823386fee9e209efbe7"}}