{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UAPCIN4BPWPMDIHFGGWPFCZEB2","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":"430ec83a17b101f0eef2cfa81092b51795f0b38746cd7988eccc66086c9c290f","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-02-25T13:27:13Z","title_canon_sha256":"7ac1d11e9074b441e59825906bb36a541923e97170b8c0cf6271a2b31af68b37"},"schema_version":"1.0","source":{"id":"1902.09254","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09254","created_at":"2026-07-05T01:01:19Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09254v4","created_at":"2026-07-05T01:01:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09254","created_at":"2026-07-05T01:01:19Z"},{"alias_kind":"pith_short_12","alias_value":"UAPCIN4BPWPM","created_at":"2026-07-05T01:01:19Z"},{"alias_kind":"pith_short_16","alias_value":"UAPCIN4BPWPMDIHF","created_at":"2026-07-05T01:01:19Z"},{"alias_kind":"pith_short_8","alias_value":"UAPCIN4B","created_at":"2026-07-05T01:01:19Z"}],"graph_snapshots":[{"event_id":"sha256:be8a92ed55e5681e87a09b5994dedcf317bb4cab133d0e01de5dd64c677b3e11","target":"graph","created_at":"2026-07-05T01:01:19Z","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/1902.09254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Increasing amount of research has shed light on machine perception of audio events, most of which concerns detection and classification tasks. However, human-like perception of audio scenes involves not only detecting and classifying audio sounds, but also summarizing the relationship between different audio events. Comparable research such as image caption has been conducted, yet the audio field is still quite barren. This paper introduces a manually-annotated dataset for audio caption. The purpose is to automatically generate natural sentences for audio scene description and to bridge the ga","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-02-25T13:27:13Z","title":"Audio Caption: Listen and Tell"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09254","kind":"arxiv","version":4},"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":"sha256:9a6ab23aa7664fca19a02d82ad87024dab9c15fe342e2f26b324b279b8be9a26","target":"record","created_at":"2026-07-05T01:01:19Z","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":"430ec83a17b101f0eef2cfa81092b51795f0b38746cd7988eccc66086c9c290f","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2019-02-25T13:27:13Z","title_canon_sha256":"7ac1d11e9074b441e59825906bb36a541923e97170b8c0cf6271a2b31af68b37"},"schema_version":"1.0","source":{"id":"1902.09254","kind":"arxiv","version":4}},"canonical_sha256":"a01e2437817d9ec1a0e531acf28b240eaf49e941cc1234ae6088cdf98173e43a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a01e2437817d9ec1a0e531acf28b240eaf49e941cc1234ae6088cdf98173e43a","first_computed_at":"2026-07-05T01:01:19.334923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:01:19.334923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tbEhH8tgC+2rlFUG+T3AXWNh3V0LKF2ygCQDQSUuK9H6nGPvJAoI0wOE39YmhdFg+6iD4ooPqwrP4s4wSDSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:01:19.335469Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09254","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a6ab23aa7664fca19a02d82ad87024dab9c15fe342e2f26b324b279b8be9a26","sha256:be8a92ed55e5681e87a09b5994dedcf317bb4cab133d0e01de5dd64c677b3e11"],"state_sha256":"02d3f829cf858e4c979f2c611461dc5f2dd1538d086c4ce64fce731bfda1b0ad"}