{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QVQDJOKUH7JAMZY3TRVRNZGQS4","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":"4837004a25073b77a44b667ad8a7e09c9b39df52a9055c67c855fe9cbffb2d95","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T16:40:46Z","title_canon_sha256":"7dfc4223169f77258dae24adc457c962b53125581bd0742348f6e99c7e463521"},"schema_version":"1.0","source":{"id":"2309.12242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12242","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12242v1","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12242","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"QVQDJOKUH7JA","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"QVQDJOKUH7JAMZY3","created_at":"2026-07-05T06:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"QVQDJOKU","created_at":"2026-07-05T06:53:00Z"}],"graph_snapshots":[{"event_id":"sha256:70c2b6bba56dcf7668f3b4cef0f2a57358ad6713da33ed6749149c30cf6177b0","target":"graph","created_at":"2026-07-05T06:53:00Z","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/2309.12242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, datasets of paired audio and captions have enabled remarkable success in automatically generating descriptions for audio clips, namely Automated Audio Captioning (AAC). However, it is labor-intensive and time-consuming to collect a sufficient number of paired audio and captions. Motivated by the recent advances in Contrastive Language-Audio Pretraining (CLAP), we propose a weakly-supervised approach to train an AAC model assuming only text data and a pre-trained CLAP model, alleviating the need for paired target data. Our approach leverages the similarity between audio and tex","authors_text":"Theodoros Kouzelis, Vassilis Katsouros","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T16:40:46Z","title":"Weakly-supervised Automated Audio Captioning via text only training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12242","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":"sha256:174497ce8c75941d4659aec97b0700b9b4d8cb2b1c40fb0fe959393fcca6e936","target":"record","created_at":"2026-07-05T06:53:00Z","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":"4837004a25073b77a44b667ad8a7e09c9b39df52a9055c67c855fe9cbffb2d95","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-21T16:40:46Z","title_canon_sha256":"7dfc4223169f77258dae24adc457c962b53125581bd0742348f6e99c7e463521"},"schema_version":"1.0","source":{"id":"2309.12242","kind":"arxiv","version":1}},"canonical_sha256":"856034b9543fd206671b9c6b16e4d0973dce6f4e931b7b6c51bacd9343fe4148","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"856034b9543fd206671b9c6b16e4d0973dce6f4e931b7b6c51bacd9343fe4148","first_computed_at":"2026-07-05T06:53:00.670282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:00.670282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PXU9B4uGTye5Uw7kJ5zYVtZju2Tna9oFdIc4BfD/UVvLJzSIeXMRrRyIYfq+1qvycPzlkSjpmh0bTF+nimYYAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:00.670796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:174497ce8c75941d4659aec97b0700b9b4d8cb2b1c40fb0fe959393fcca6e936","sha256:70c2b6bba56dcf7668f3b4cef0f2a57358ad6713da33ed6749149c30cf6177b0"],"state_sha256":"708385a4d3f20e560debf73bc55c7aed5406f868e023f2bac54fce39bc45f57c"}