{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SIAALO7VQTLMJRDJTPLT5TS4KU","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":"7f8d1c538067d3936faf4d2dcecb84fd4829c56061d56a239905b16880e508a1","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-11-04T18:55:08Z","title_canon_sha256":"a69bc8994c4b21d930417c9023a1fdb844638b047a6576844ec108bd666df481"},"schema_version":"1.0","source":{"id":"2311.02482","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02482","created_at":"2026-07-05T07:09:13Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02482v1","created_at":"2026-07-05T07:09:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02482","created_at":"2026-07-05T07:09:13Z"},{"alias_kind":"pith_short_12","alias_value":"SIAALO7VQTLM","created_at":"2026-07-05T07:09:13Z"},{"alias_kind":"pith_short_16","alias_value":"SIAALO7VQTLMJRDJ","created_at":"2026-07-05T07:09:13Z"},{"alias_kind":"pith_short_8","alias_value":"SIAALO7V","created_at":"2026-07-05T07:09:13Z"}],"graph_snapshots":[{"event_id":"sha256:a5a50565145b43c4619ee642772a0ab3229da6dc3f04bcca73e3ce41e5223d4e","target":"graph","created_at":"2026-07-05T07:09:13Z","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/2311.02482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken language understanding systems using audio-only data are gaining popularity, yet their ability to handle unseen intents remains limited. In this study, we propose a generalized zero-shot audio-to-intent classification framework with only a few sample text sentences per intent. To achieve this, we first train a supervised audio-to-intent classifier by making use of a self-supervised pre-trained model. We then leverage a neural audio synthesizer to create audio embeddings for sample text utterances and perform generalized zero-shot classification on unseen intents using cosine similarity.","authors_text":"Devang Kulshreshtha, Rohit Paturi, Sravan Bodapati, Srikanth Ronanki, Veera Raghavendra Elluru","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-11-04T18:55:08Z","title":"Generalized zero-shot audio-to-intent classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02482","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":"sha256:39dbf50acef055e517077bd1a341b59e59763e0c7164f1c41f49998848cca72c","target":"record","created_at":"2026-07-05T07:09:13Z","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":"7f8d1c538067d3936faf4d2dcecb84fd4829c56061d56a239905b16880e508a1","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-11-04T18:55:08Z","title_canon_sha256":"a69bc8994c4b21d930417c9023a1fdb844638b047a6576844ec108bd666df481"},"schema_version":"1.0","source":{"id":"2311.02482","kind":"arxiv","version":1}},"canonical_sha256":"920005bbf584d6c4c4699bd73ece5c551e01ceaeeadb10ebbc51000761e70d4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"920005bbf584d6c4c4699bd73ece5c551e01ceaeeadb10ebbc51000761e70d4e","first_computed_at":"2026-07-05T07:09:13.068659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:13.068659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nSEkpgiryibpYTi6tn/Gi4HdXsBn2VHlWWXEp7KuHnfpIhLFSzG5RHta461dP3pxJRjk6kgxZ6eNrjKVnTmxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:13.069069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02482","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39dbf50acef055e517077bd1a341b59e59763e0c7164f1c41f49998848cca72c","sha256:a5a50565145b43c4619ee642772a0ab3229da6dc3f04bcca73e3ce41e5223d4e"],"state_sha256":"acb2066264a54fa762bc361c0c8cb0502bd9ed02ae0beba5666068bbdf82c811"}