{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RABDLMWJDI2X74R2LC3EY4BLJQ","short_pith_number":"pith:RABDLMWJ","canonical_record":{"source":{"id":"2409.14526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-22T16:45:57Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"68041423ceb72cd1d35bc7a19d9987db3d01953c9878ade00fc9c5a51a2fa2d6","abstract_canon_sha256":"e028ba5750fe2f40656a39cb4e3ed32f38fb24884a0ea83b0130442dc555315d"},"schema_version":"1.0"},"canonical_sha256":"880235b2c91a357ff23a58b64c702b4c1988c0ae142cddd9833f66f02e042b40","source":{"kind":"arxiv","id":"2409.14526","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14526","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14526v2","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14526","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_12","alias_value":"RABDLMWJDI2X","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_16","alias_value":"RABDLMWJDI2X74R2","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_8","alias_value":"RABDLMWJ","created_at":"2026-07-05T09:59:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RABDLMWJDI2X74R2LC3EY4BLJQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14526","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-22T16:45:57Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"68041423ceb72cd1d35bc7a19d9987db3d01953c9878ade00fc9c5a51a2fa2d6","abstract_canon_sha256":"e028ba5750fe2f40656a39cb4e3ed32f38fb24884a0ea83b0130442dc555315d"},"schema_version":"1.0"},"canonical_sha256":"880235b2c91a357ff23a58b64c702b4c1988c0ae142cddd9833f66f02e042b40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:52.918088Z","signature_b64":"VlDujSANn9Fmu5FF982U2m4hgq2I07Iij5gn4iGwK7OKzn0GmgKQ29W1Q0UlxjNwQP9srI75YsHE+VuPtkbUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"880235b2c91a357ff23a58b64c702b4c1988c0ae142cddd9833f66f02e042b40","last_reissued_at":"2026-07-05T09:59:52.917657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:52.917657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14526","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:59:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wbARFgf1V2TuGzq+1OB2Zi2e7QoV9Wy1E2wdlddZfWoUJzyBHG7mbfd7D6FkP2wvtqijSwYluGvWuyxdOZirBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:48:48.608799Z"},"content_sha256":"bda2ed1886b8545adb7a3e8cde4f46eb7ac4b1c72def87950e164f0c86bf04fa","schema_version":"1.0","event_id":"sha256:bda2ed1886b8545adb7a3e8cde4f46eb7ac4b1c72def87950e164f0c86bf04fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RABDLMWJDI2X74R2LC3EY4BLJQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Are They Doing? Joint Audio-Speech Co-Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Artem Ploujnikov, Mirco Ravanelli, Pooneh Mousavi, Yingzhi Wang","submitted_at":"2024-09-22T16:45:57Z","abstract_excerpt":"In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are present in the same audio clip. Recent Auditory Large Language Models (ALLMs) have made it possible to process audio and speech simultaneously within a single model, leading to further considerations of joint audio-speech tasks.\n  In this paper, we establish a novel benchmark to investigate how well ALLMs can perform joint audio-speech processing. Specifically, we introduce Joint Audio-Speech Co-Reasoning (JASCO), a novel task that unifies audio and speech proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14526","kind":"arxiv","version":2},"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/2409.14526/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":"2026-07-05T09:59:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"luAZgov7bJ+Gf0jjpXOg3vbQmFtFCRkmcd1gK53Fw3VQlbWj8sOXVK2conrwQuVACQSA4udm3yXMJpUu6zg2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:48:48.609175Z"},"content_sha256":"c036423fd2d063dba260d5a7c52d6f22f1bcfa2c45cadc770e0b6ec96a764b57","schema_version":"1.0","event_id":"sha256:c036423fd2d063dba260d5a7c52d6f22f1bcfa2c45cadc770e0b6ec96a764b57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RABDLMWJDI2X74R2LC3EY4BLJQ/bundle.json","state_url":"https://pith.science/pith/RABDLMWJDI2X74R2LC3EY4BLJQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RABDLMWJDI2X74R2LC3EY4BLJQ/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":"2026-07-06T15:48:48Z","links":{"resolver":"https://pith.science/pith/RABDLMWJDI2X74R2LC3EY4BLJQ","bundle":"https://pith.science/pith/RABDLMWJDI2X74R2LC3EY4BLJQ/bundle.json","state":"https://pith.science/pith/RABDLMWJDI2X74R2LC3EY4BLJQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RABDLMWJDI2X74R2LC3EY4BLJQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RABDLMWJDI2X74R2LC3EY4BLJQ","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":"e028ba5750fe2f40656a39cb4e3ed32f38fb24884a0ea83b0130442dc555315d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-22T16:45:57Z","title_canon_sha256":"68041423ceb72cd1d35bc7a19d9987db3d01953c9878ade00fc9c5a51a2fa2d6"},"schema_version":"1.0","source":{"id":"2409.14526","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14526","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14526v2","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14526","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_12","alias_value":"RABDLMWJDI2X","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_16","alias_value":"RABDLMWJDI2X74R2","created_at":"2026-07-05T09:59:52Z"},{"alias_kind":"pith_short_8","alias_value":"RABDLMWJ","created_at":"2026-07-05T09:59:52Z"}],"graph_snapshots":[{"event_id":"sha256:c036423fd2d063dba260d5a7c52d6f22f1bcfa2c45cadc770e0b6ec96a764b57","target":"graph","created_at":"2026-07-05T09:59:52Z","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/2409.14526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In audio and speech processing, tasks usually focus on either the audio or speech modality, even when both sounds and human speech are present in the same audio clip. Recent Auditory Large Language Models (ALLMs) have made it possible to process audio and speech simultaneously within a single model, leading to further considerations of joint audio-speech tasks.\n  In this paper, we establish a novel benchmark to investigate how well ALLMs can perform joint audio-speech processing. Specifically, we introduce Joint Audio-Speech Co-Reasoning (JASCO), a novel task that unifies audio and speech proc","authors_text":"Artem Ploujnikov, Mirco Ravanelli, Pooneh Mousavi, Yingzhi Wang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-22T16:45:57Z","title":"What Are They Doing? Joint Audio-Speech Co-Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14526","kind":"arxiv","version":2},"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:bda2ed1886b8545adb7a3e8cde4f46eb7ac4b1c72def87950e164f0c86bf04fa","target":"record","created_at":"2026-07-05T09:59:52Z","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":"e028ba5750fe2f40656a39cb4e3ed32f38fb24884a0ea83b0130442dc555315d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-22T16:45:57Z","title_canon_sha256":"68041423ceb72cd1d35bc7a19d9987db3d01953c9878ade00fc9c5a51a2fa2d6"},"schema_version":"1.0","source":{"id":"2409.14526","kind":"arxiv","version":2}},"canonical_sha256":"880235b2c91a357ff23a58b64c702b4c1988c0ae142cddd9833f66f02e042b40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"880235b2c91a357ff23a58b64c702b4c1988c0ae142cddd9833f66f02e042b40","first_computed_at":"2026-07-05T09:59:52.917657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:52.917657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VlDujSANn9Fmu5FF982U2m4hgq2I07Iij5gn4iGwK7OKzn0GmgKQ29W1Q0UlxjNwQP9srI75YsHE+VuPtkbUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:52.918088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14526","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bda2ed1886b8545adb7a3e8cde4f46eb7ac4b1c72def87950e164f0c86bf04fa","sha256:c036423fd2d063dba260d5a7c52d6f22f1bcfa2c45cadc770e0b6ec96a764b57"],"state_sha256":"efa36f5bdb314ed49a6d96829ded3ff81cf4c281981ffbb20fe1632650846679"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vx7SYPukOzXDQ56MV6OplCbWLr9RDj4+rDt7xc3DKYUZl/I/4xEcUqIvn5WayARkJHYNn7spw88vE9ST666bDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:48:48.612288Z","bundle_sha256":"9751f69f353d74b0f00dcf004934aa9f1e98b5ca000272cf0fef57ce621797b6"}}