{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KOKH64SRDKPSH3W63K3SKD5BBG","short_pith_number":"pith:KOKH64SR","canonical_record":{"source":{"id":"2309.14405","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-25T17:59:05Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"8e1fbd79fbadb2c0fa3e96d7a883d6ff2e46e605ae15b2a21301a5c3356cea1c","abstract_canon_sha256":"ab8cc01d65e53d73ca158e319cea5eff9ce8de8e68261a6cc0d6f79ecdfa2ae9"},"schema_version":"1.0"},"canonical_sha256":"53947f72511a9f23eededab7250fa109af9b196189464f9c7387070e551cbe74","source":{"kind":"arxiv","id":"2309.14405","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.14405","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.14405v3","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14405","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"KOKH64SRDKPS","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"KOKH64SRDKPSH3W6","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"KOKH64SR","created_at":"2026-07-05T07:22:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KOKH64SRDKPSH3W63K3SKD5BBG","target":"record","payload":{"canonical_record":{"source":{"id":"2309.14405","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-25T17:59:05Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"8e1fbd79fbadb2c0fa3e96d7a883d6ff2e46e605ae15b2a21301a5c3356cea1c","abstract_canon_sha256":"ab8cc01d65e53d73ca158e319cea5eff9ce8de8e68261a6cc0d6f79ecdfa2ae9"},"schema_version":"1.0"},"canonical_sha256":"53947f72511a9f23eededab7250fa109af9b196189464f9c7387070e551cbe74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:23.900460Z","signature_b64":"CEEDpC8qUbYtOpRnFudxUGQ/mOfCG5GYBKCI57UijnoN1WMwazND6jIc1lJVMRsThg4Zj3xXgmMFP1f4dJNyDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53947f72511a9f23eededab7250fa109af9b196189464f9c7387070e551cbe74","last_reissued_at":"2026-07-05T07:22:23.899955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:23.899955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.14405","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UzWlfXym6DVusbQJiZ5oHoYvkO+sflHp157DChttrlvuie3JCNpoCit4uu9SuP8iRTfenTU/Danu+nZc9ItgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:57:39.718361Z"},"content_sha256":"d00778c6a348ec6ed143ff1aa38466494d7df34474e117155f5a540aa6b45d17","schema_version":"1.0","event_id":"sha256:d00778c6a348ec6ed143ff1aa38466494d7df34474e117155f5a540aa6b45d17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KOKH64SRDKPSH3W63K3SKD5BBG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Audio and Speech Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander H. Liu, Hongyin Luo, James Glass, Leonid Karlinsky, Yuan Gong","submitted_at":"2023-09-25T17:59:05Z","abstract_excerpt":"Humans are surrounded by audio signals that include both speech and non-speech sounds. The recognition and understanding of speech and non-speech audio events, along with a profound comprehension of the relationship between them, constitute fundamental cognitive capabilities. For the first time, we build a machine learning model, called LTU-AS, that has a conceptually similar universal audio perception and advanced reasoning ability. Specifically, by integrating Whisper as a perception module and LLaMA as a reasoning module, LTU-AS can simultaneously recognize and jointly understand spoken tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14405","kind":"arxiv","version":3},"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/2309.14405/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":"2026-07-05T07:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+Q+0arHE6si15GAURpLt2OUJNoqEEiNFc2bEwpCZDuWjjD0g+NgdzNYeUTzcwEYCWTaU13sihmXhUjf74gJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:57:39.718890Z"},"content_sha256":"1059714b00dd2f63a933fc282697223d256f9862f40af10475ead03e9dfc7b14","schema_version":"1.0","event_id":"sha256:1059714b00dd2f63a933fc282697223d256f9862f40af10475ead03e9dfc7b14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOKH64SRDKPSH3W63K3SKD5BBG/bundle.json","state_url":"https://pith.science/pith/KOKH64SRDKPSH3W63K3SKD5BBG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOKH64SRDKPSH3W63K3SKD5BBG/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":"2026-08-22T07:57:39Z","links":{"resolver":"https://pith.science/pith/KOKH64SRDKPSH3W63K3SKD5BBG","bundle":"https://pith.science/pith/KOKH64SRDKPSH3W63K3SKD5BBG/bundle.json","state":"https://pith.science/pith/KOKH64SRDKPSH3W63K3SKD5BBG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOKH64SRDKPSH3W63K3SKD5BBG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KOKH64SRDKPSH3W63K3SKD5BBG","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":"ab8cc01d65e53d73ca158e319cea5eff9ce8de8e68261a6cc0d6f79ecdfa2ae9","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-25T17:59:05Z","title_canon_sha256":"8e1fbd79fbadb2c0fa3e96d7a883d6ff2e46e605ae15b2a21301a5c3356cea1c"},"schema_version":"1.0","source":{"id":"2309.14405","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.14405","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2309.14405v3","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14405","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"KOKH64SRDKPS","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"KOKH64SRDKPSH3W6","created_at":"2026-07-05T07:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"KOKH64SR","created_at":"2026-07-05T07:22:23Z"}],"graph_snapshots":[{"event_id":"sha256:1059714b00dd2f63a933fc282697223d256f9862f40af10475ead03e9dfc7b14","target":"graph","created_at":"2026-07-05T07:22:23Z","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/2309.14405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans are surrounded by audio signals that include both speech and non-speech sounds. The recognition and understanding of speech and non-speech audio events, along with a profound comprehension of the relationship between them, constitute fundamental cognitive capabilities. For the first time, we build a machine learning model, called LTU-AS, that has a conceptually similar universal audio perception and advanced reasoning ability. Specifically, by integrating Whisper as a perception module and LLaMA as a reasoning module, LTU-AS can simultaneously recognize and jointly understand spoken tex","authors_text":"Alexander H. Liu, Hongyin Luo, James Glass, Leonid Karlinsky, Yuan Gong","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-25T17:59:05Z","title":"Joint Audio and Speech Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14405","kind":"arxiv","version":3},"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:d00778c6a348ec6ed143ff1aa38466494d7df34474e117155f5a540aa6b45d17","target":"record","created_at":"2026-07-05T07:22:23Z","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":"ab8cc01d65e53d73ca158e319cea5eff9ce8de8e68261a6cc0d6f79ecdfa2ae9","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-25T17:59:05Z","title_canon_sha256":"8e1fbd79fbadb2c0fa3e96d7a883d6ff2e46e605ae15b2a21301a5c3356cea1c"},"schema_version":"1.0","source":{"id":"2309.14405","kind":"arxiv","version":3}},"canonical_sha256":"53947f72511a9f23eededab7250fa109af9b196189464f9c7387070e551cbe74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53947f72511a9f23eededab7250fa109af9b196189464f9c7387070e551cbe74","first_computed_at":"2026-07-05T07:22:23.899955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:23.899955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CEEDpC8qUbYtOpRnFudxUGQ/mOfCG5GYBKCI57UijnoN1WMwazND6jIc1lJVMRsThg4Zj3xXgmMFP1f4dJNyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:23.900460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.14405","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d00778c6a348ec6ed143ff1aa38466494d7df34474e117155f5a540aa6b45d17","sha256:1059714b00dd2f63a933fc282697223d256f9862f40af10475ead03e9dfc7b14"],"state_sha256":"5910a4f94c0a776bcbc17a59db9445e06c9fc98a0355f4dd782acca7f7e25117"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j4KhWZAeXc5glXPEK4AUjPDyjsCHYzpEYtCfltqCL4INMEXlbAUuOUUknCVKYQKnxjjN4avz5MpyIKXhLeZfDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:57:39.723694Z","bundle_sha256":"89ca71ef6b1ac8698ad9393505fd4c4df6eba30bddc34c312ff44fad875af650"}}