{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5ZOUQOIPIM7QXTKFGTXP644LCN","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":"4312eeb7282894b88aed0e070f1fd650c6e0b991e0101a861f7a0a376b034909","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-25T14:17:56Z","title_canon_sha256":"4a293ce6a623fb3b1beeb59aa34d03c41d01c69469ffb76b6f5c562489346549"},"schema_version":"1.0","source":{"id":"2407.18062","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18062","created_at":"2026-07-05T08:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18062v1","created_at":"2026-07-05T08:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18062","created_at":"2026-07-05T08:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"5ZOUQOIPIM7Q","created_at":"2026-07-05T08:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"5ZOUQOIPIM7QXTKF","created_at":"2026-07-05T08:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"5ZOUQOIP","created_at":"2026-07-05T08:48:33Z"}],"graph_snapshots":[{"event_id":"sha256:e302564592761e366d39939a47eb28eb99cc27eb68c178d68ca99d3f3fdcd38d","target":"graph","created_at":"2026-07-05T08:48:33Z","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/2407.18062/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent literature uses language to build foundation models for audio. These Audio-Language Models (ALMs) are trained on a vast number of audio-text pairs and show remarkable performance in tasks including Text-to-Audio Retrieval, Captioning, and Question Answering. However, their ability to engage in more complex open-ended tasks, like Interactive Question-Answering, requires proficiency in logical reasoning -- a skill not yet benchmarked. We introduce the novel task of Audio Entailment to evaluate an ALM's deductive reasoning ability. This task assesses whether a text description (hypothesis)","authors_text":"Benjamin Elizalde, Bhiksha Raj, Hannes Gamper, Hazim Bukhari, Rita Singh, Shuo Han, Soham Deshmukh","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-25T14:17:56Z","title":"Audio Entailment: Assessing Deductive Reasoning for Audio Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18062","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:ca2b9b27aa953076a776cc1d3a097e36204921e2d07025195c8c3a6f524c124b","target":"record","created_at":"2026-07-05T08:48:33Z","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":"4312eeb7282894b88aed0e070f1fd650c6e0b991e0101a861f7a0a376b034909","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-25T14:17:56Z","title_canon_sha256":"4a293ce6a623fb3b1beeb59aa34d03c41d01c69469ffb76b6f5c562489346549"},"schema_version":"1.0","source":{"id":"2407.18062","kind":"arxiv","version":1}},"canonical_sha256":"ee5d48390f433f0bcd4534eeff738b134c52a2b7d97e3890aeb5ef93625afacd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee5d48390f433f0bcd4534eeff738b134c52a2b7d97e3890aeb5ef93625afacd","first_computed_at":"2026-07-05T08:48:33.872347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:33.872347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m93uapcak+8pH2MM0Lj1QkcvSxiYEbJSeGmjZ8brFJNJQyB08JG7gHnZ/yDlKZXER4x5Tx49PI6/j/XLC13xCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:33.872759Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18062","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca2b9b27aa953076a776cc1d3a097e36204921e2d07025195c8c3a6f524c124b","sha256:e302564592761e366d39939a47eb28eb99cc27eb68c178d68ca99d3f3fdcd38d"],"state_sha256":"c46b9cb42ada2351ea58230c3cad095388df7fbd8eb808079ee25533edad7765"}