{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DYZYVF42LVSPYTHAMZSYLXDH2L","short_pith_number":"pith:DYZYVF42","canonical_record":{"source":{"id":"2402.07729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-12T15:41:22Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"5182871546dec2eeeaca0de5f7175f558775134286995f9528fcf143b8fb8bfd","abstract_canon_sha256":"de208811bbec2b79d67a2c2ff74d7cb568274c8498e840f52e782c0daca530d7"},"schema_version":"1.0"},"canonical_sha256":"1e338a979a5d64fc4ce0666585dc67d2db64b7267075cc9501b4405b13ea5db7","source":{"kind":"arxiv","id":"2402.07729","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07729","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07729v2","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07729","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"DYZYVF42LVSP","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"DYZYVF42LVSPYTHA","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"DYZYVF42","created_at":"2026-07-05T08:48:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DYZYVF42LVSPYTHAMZSYLXDH2L","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-12T15:41:22Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"5182871546dec2eeeaca0de5f7175f558775134286995f9528fcf143b8fb8bfd","abstract_canon_sha256":"de208811bbec2b79d67a2c2ff74d7cb568274c8498e840f52e782c0daca530d7"},"schema_version":"1.0"},"canonical_sha256":"1e338a979a5d64fc4ce0666585dc67d2db64b7267075cc9501b4405b13ea5db7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:41.228014Z","signature_b64":"sVQu2EXY6a7PYaMRQl4XaCTiv6ougGVGr+CDK39DNV91SkiC2wK/QeK2XT7hotRjndP4zFutQGVIVC82Ojx0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e338a979a5d64fc4ce0666585dc67d2db64b7267075cc9501b4405b13ea5db7","last_reissued_at":"2026-07-05T08:48:41.227600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:41.227600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07729","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":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L+GyqpukgwS8ARqY5NkWZRVztyfbmamOlIUE5ja2P4Qc0/RzCS+CIRv0sCnDzv4XBcxA6cQeM8Ug/kO5oMkDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:11:05.933411Z"},"content_sha256":"a7048e5876c7e099996302eeddf6498a7e5e8a4b6eef7baf1530223604c1d2fe","schema_version":"1.0","event_id":"sha256:a7048e5876c7e099996302eeddf6498a7e5e8a4b6eef7baf1530223604c1d2fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DYZYVF42LVSPYTHAMZSYLXDH2L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chang Zhou, Jingren Zhou, Jin Xu, Qian Yang, Wenrui Liu, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Yunfei Chu, Zhou Zhao, Ziyue Jiang","submitted_at":"2024-02-12T15:41:22Z","abstract_excerpt":"Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as Automatic Speech Recognition (ASR), and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07729","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/2402.07729/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":"2026-07-05T08:48:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0tNPOmk13Zsd+awnbXsoXVmFVgVtupQbaDqp+mvYmIFpjTLOnJD/nKe7Z1ReRpF8wLFaNTB97wrZgLOGLKSCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:11:05.934195Z"},"content_sha256":"697b90a7f910e65b64e6e8a61e38b2d9cbfefbda519e1a901facbc48822338ec","schema_version":"1.0","event_id":"sha256:697b90a7f910e65b64e6e8a61e38b2d9cbfefbda519e1a901facbc48822338ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYZYVF42LVSPYTHAMZSYLXDH2L/bundle.json","state_url":"https://pith.science/pith/DYZYVF42LVSPYTHAMZSYLXDH2L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYZYVF42LVSPYTHAMZSYLXDH2L/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":"2026-07-09T03:11:05Z","links":{"resolver":"https://pith.science/pith/DYZYVF42LVSPYTHAMZSYLXDH2L","bundle":"https://pith.science/pith/DYZYVF42LVSPYTHAMZSYLXDH2L/bundle.json","state":"https://pith.science/pith/DYZYVF42LVSPYTHAMZSYLXDH2L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYZYVF42LVSPYTHAMZSYLXDH2L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DYZYVF42LVSPYTHAMZSYLXDH2L","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":"de208811bbec2b79d67a2c2ff74d7cb568274c8498e840f52e782c0daca530d7","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-12T15:41:22Z","title_canon_sha256":"5182871546dec2eeeaca0de5f7175f558775134286995f9528fcf143b8fb8bfd"},"schema_version":"1.0","source":{"id":"2402.07729","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07729","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07729v2","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07729","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_12","alias_value":"DYZYVF42LVSP","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_16","alias_value":"DYZYVF42LVSPYTHA","created_at":"2026-07-05T08:48:41Z"},{"alias_kind":"pith_short_8","alias_value":"DYZYVF42","created_at":"2026-07-05T08:48:41Z"}],"graph_snapshots":[{"event_id":"sha256:697b90a7f910e65b64e6e8a61e38b2d9cbfefbda519e1a901facbc48822338ec","target":"graph","created_at":"2026-07-05T08:48:41Z","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/2402.07729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, instruction-following audio-language models have received broad attention for human-audio interaction. However, the absence of benchmarks capable of evaluating audio-centric interaction capabilities has impeded advancements in this field. Previous models primarily focus on assessing different fundamental tasks, such as Automatic Speech Recognition (ASR), and lack an assessment of the open-ended generative capabilities centered around audio. Thus, it is challenging to track the progression in the Large Audio-Language Models (LALMs) domain and to provide guidance for future improvement","authors_text":"Chang Zhou, Jingren Zhou, Jin Xu, Qian Yang, Wenrui Liu, Xiaohuan Zhou, Yichong Leng, Yuanjun Lv, Yunfei Chu, Zhou Zhao, Ziyue Jiang","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-12T15:41:22Z","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07729","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:a7048e5876c7e099996302eeddf6498a7e5e8a4b6eef7baf1530223604c1d2fe","target":"record","created_at":"2026-07-05T08:48:41Z","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":"de208811bbec2b79d67a2c2ff74d7cb568274c8498e840f52e782c0daca530d7","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-12T15:41:22Z","title_canon_sha256":"5182871546dec2eeeaca0de5f7175f558775134286995f9528fcf143b8fb8bfd"},"schema_version":"1.0","source":{"id":"2402.07729","kind":"arxiv","version":2}},"canonical_sha256":"1e338a979a5d64fc4ce0666585dc67d2db64b7267075cc9501b4405b13ea5db7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e338a979a5d64fc4ce0666585dc67d2db64b7267075cc9501b4405b13ea5db7","first_computed_at":"2026-07-05T08:48:41.227600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:41.227600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sVQu2EXY6a7PYaMRQl4XaCTiv6ougGVGr+CDK39DNV91SkiC2wK/QeK2XT7hotRjndP4zFutQGVIVC82Ojx0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:41.228014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07729","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7048e5876c7e099996302eeddf6498a7e5e8a4b6eef7baf1530223604c1d2fe","sha256:697b90a7f910e65b64e6e8a61e38b2d9cbfefbda519e1a901facbc48822338ec"],"state_sha256":"7a1b314c070cfc82311dccf13bae74159d308dd5dde4e782aada5bb5837d7d9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1UcuUriLLd3+kJbC0EMTSasIKl2TtQ5+m2jIaCw+XQAUymwM6C6CQxEVgncPCPuUIDtw+3cHV/PTLN0FZeQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:11:05.938194Z","bundle_sha256":"00a32d48ef79f125b38e3c853ae6818a0f77054c7f5d18ec8d161b0fafb72ca9"}}