{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SLR5KDPVCTYSXFLRPR23U37LIQ","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":"3963d48a9b0ad4ee3ab2a719963798868a6efe4090f34c557bb6a26bc1fc1678","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T02:30:46Z","title_canon_sha256":"113744a1c059c83c6d0f3155ed6e649eed92d2802c85c682128196fdc83fc9ed"},"schema_version":"1.0","source":{"id":"2305.01864","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.01864","created_at":"2026-07-05T06:36:11Z"},{"alias_kind":"arxiv_version","alias_value":"2305.01864v3","created_at":"2026-07-05T06:36:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.01864","created_at":"2026-07-05T06:36:11Z"},{"alias_kind":"pith_short_12","alias_value":"SLR5KDPVCTYS","created_at":"2026-07-05T06:36:11Z"},{"alias_kind":"pith_short_16","alias_value":"SLR5KDPVCTYSXFLR","created_at":"2026-07-05T06:36:11Z"},{"alias_kind":"pith_short_8","alias_value":"SLR5KDPV","created_at":"2026-07-05T06:36:11Z"}],"graph_snapshots":[{"event_id":"sha256:688304e2798807a92aa2b100dde03f64bd373d769ee12888279785675edeb0b3","target":"graph","created_at":"2026-07-05T06:36:11Z","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/2305.01864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in using language models to obtain cross-modal audio-text representations have overcome the limitations of conventional training approaches that use predefined labels. This has allowed the community to make progress in tasks like zero-shot classification, which would otherwise not be possible. However, learning such representations requires a large amount of human-annotated audio-text pairs. In this paper, we study unsupervised approaches to improve the learning framework of such representations with unpaired text and audio. We explore domain-unspecific and domain-specific cura","authors_text":"Cem Subakan, Fabio Ayres, Junkai Wu, Krishna Subramani, Paris Smaragdis, Tiago Tavares, Zhepei Wang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T02:30:46Z","title":"Unsupervised Improvement of Audio-Text Cross-Modal Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.01864","kind":"arxiv","version":3},"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:c7cb2c991068ea56e93a6039fcf05063bb63a5037a2a2a5c04a8e38a29b193a4","target":"record","created_at":"2026-07-05T06:36:11Z","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":"3963d48a9b0ad4ee3ab2a719963798868a6efe4090f34c557bb6a26bc1fc1678","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-03T02:30:46Z","title_canon_sha256":"113744a1c059c83c6d0f3155ed6e649eed92d2802c85c682128196fdc83fc9ed"},"schema_version":"1.0","source":{"id":"2305.01864","kind":"arxiv","version":3}},"canonical_sha256":"92e3d50df514f12b95717c75ba6feb443bf8b740511ac5633478fe609a06c928","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92e3d50df514f12b95717c75ba6feb443bf8b740511ac5633478fe609a06c928","first_computed_at":"2026-07-05T06:36:11.805669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:11.805669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVUJUFwygufbk0Wz7UvEwI5lr3BlJoRGNjYYWSx5hdI969omWYKWllNiDn+wDTYm+DO3svLvYbqn7B0VzLBIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:11.806174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.01864","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7cb2c991068ea56e93a6039fcf05063bb63a5037a2a2a5c04a8e38a29b193a4","sha256:688304e2798807a92aa2b100dde03f64bd373d769ee12888279785675edeb0b3"],"state_sha256":"14db4d74867e533cbbce920f04aa02dc05e39bb44e0969fda1e7cb054018ac9b"}