{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QNQN3OBGZGQRJMYZUJFEGXMNCP","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":"00c90194f675e0ca9d775593eba7ea76a5cdcb3837b212f6fb2b3dd68544b5e5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-19T14:14:46Z","title_canon_sha256":"7600fa769bf0ca06b82f4fcf2415b49ab5e9bcbdfeae19df5d85707904ff5797"},"schema_version":"1.0","source":{"id":"2303.10667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.10667","created_at":"2026-07-05T05:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"2303.10667v1","created_at":"2026-07-05T05:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10667","created_at":"2026-07-05T05:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"QNQN3OBGZGQR","created_at":"2026-07-05T05:52:34Z"},{"alias_kind":"pith_short_16","alias_value":"QNQN3OBGZGQRJMYZ","created_at":"2026-07-05T05:52:34Z"},{"alias_kind":"pith_short_8","alias_value":"QNQN3OBG","created_at":"2026-07-05T05:52:34Z"}],"graph_snapshots":[{"event_id":"sha256:af40b66ec6c5ce8ee686c4044f07a134848d789b0143eb12238434b1b7adb1f5","target":"graph","created_at":"2026-07-05T05:52:34Z","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/2303.10667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal contrastive learning techniques in the audio-text domain have quickly become a highly active area of research. Most works are evaluated with standard audio retrieval and classification benchmarks assuming that (i) these models are capable of leveraging the rich information contained in natural language, and (ii) current benchmarks are able to capture the nuances of such information. In this work, we show that state-of-the-art audio-text models do not yet really understand natural language, especially contextual concepts such as sequential or concurrent ordering of sound events. Our","authors_text":"Ho-Hsiang Wu, Juan Pablo Bello, Justin Salamon, Oriol Nieto","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-19T14:14:46Z","title":"Audio-Text Models Do Not Yet Leverage Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10667","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:bc5d0e261a4b574b67ce6328338c2614a28102a7d7a97a4f66ced9f666d3660a","target":"record","created_at":"2026-07-05T05:52:34Z","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":"00c90194f675e0ca9d775593eba7ea76a5cdcb3837b212f6fb2b3dd68544b5e5","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-19T14:14:46Z","title_canon_sha256":"7600fa769bf0ca06b82f4fcf2415b49ab5e9bcbdfeae19df5d85707904ff5797"},"schema_version":"1.0","source":{"id":"2303.10667","kind":"arxiv","version":1}},"canonical_sha256":"8360ddb826c9a114b319a24a435d8d13d7295086e5fdbbb9544ef43aea0e7b9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8360ddb826c9a114b319a24a435d8d13d7295086e5fdbbb9544ef43aea0e7b9a","first_computed_at":"2026-07-05T05:52:34.991043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:34.991043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BgJeUbPLesyyqd/lA5ujIdhODDsGQWlR3R6hsKGoynLqJfnC6DLwk0wqrWuW9qOlfklDrcpP2OiYxID7gukkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:34.991399Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.10667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc5d0e261a4b574b67ce6328338c2614a28102a7d7a97a4f66ced9f666d3660a","sha256:af40b66ec6c5ce8ee686c4044f07a134848d789b0143eb12238434b1b7adb1f5"],"state_sha256":"fc6764f68e8164aa196d6d839ff64f068f0cabfe7934fcd03caa1dd6a13fd093"}