{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6BM5FHNXJ44J27Q3I2PRYSXY54","short_pith_number":"pith:6BM5FHNX","schema_version":"1.0","canonical_sha256":"f059d29db74f389d7e1b469f1c4af8ef342ac56b0f2ce783ebfd0c5fdb4154e0","source":{"kind":"arxiv","id":"2606.05717","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Audio Captioning with Auxiliary AudioSet Semantics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Adarsh Arigala, Shubham Gupta, Sri Rama Murty Kodukula","submitted_at":"2026-06-04T05:18:01Z","abstract_excerpt":"Automatic Audio Captioning (AAC) seeks to generate natural language descriptions of complex acoustic scenes, bridging auditory perception and language understanding. However, word-selection indeterminacy and increasing reliance on large-scale sequence-to-sequence or LLM-based models limit practical deployment. We propose a resource-efficient AAC framework that explicitly grounds caption generation in auxiliary AudioSet semantics. Frame-level acoustic representations extracted using a ConvNeXt encoder are augmented with top-$K$ predicted AudioSet keywords, providing structured contextual cues f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.05717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T05:18:01Z","cross_cats_sorted":[],"title_canon_sha256":"83a8bbfa5a94e3800a4ebdaf9238d9b7defb9c13d7c86e873e8556f1038886b7","abstract_canon_sha256":"fcbc9e420aed99e98a933bdd43490fab560895fc8c440d3746c004dd286d9d84"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:00.147545Z","signature_b64":"q123JUDbmXpP+JocFzVpau7EHSB7+Dlbe1HXJ0+N66AdgbUxZn95f8Pu855vBWGaZmYcVlrXPfl6q8wGcFRLCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f059d29db74f389d7e1b469f1c4af8ef342ac56b0f2ce783ebfd0c5fdb4154e0","last_reissued_at":"2026-06-05T01:15:00.147027Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:00.147027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Audio Captioning with Auxiliary AudioSet Semantics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Adarsh Arigala, Shubham Gupta, Sri Rama Murty Kodukula","submitted_at":"2026-06-04T05:18:01Z","abstract_excerpt":"Automatic Audio Captioning (AAC) seeks to generate natural language descriptions of complex acoustic scenes, bridging auditory perception and language understanding. However, word-selection indeterminacy and increasing reliance on large-scale sequence-to-sequence or LLM-based models limit practical deployment. We propose a resource-efficient AAC framework that explicitly grounds caption generation in auxiliary AudioSet semantics. Frame-level acoustic representations extracted using a ConvNeXt encoder are augmented with top-$K$ predicted AudioSet keywords, providing structured contextual cues f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05717","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.05717/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.05717","created_at":"2026-06-05T01:15:00.147113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05717v1","created_at":"2026-06-05T01:15:00.147113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05717","created_at":"2026-06-05T01:15:00.147113+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BM5FHNXJ44J","created_at":"2026-06-05T01:15:00.147113+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BM5FHNXJ44J27Q3","created_at":"2026-06-05T01:15:00.147113+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BM5FHNX","created_at":"2026-06-05T01:15:00.147113+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54","json":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54.json","graph_json":"https://pith.science/api/pith-number/6BM5FHNXJ44J27Q3I2PRYSXY54/graph.json","events_json":"https://pith.science/api/pith-number/6BM5FHNXJ44J27Q3I2PRYSXY54/events.json","paper":"https://pith.science/paper/6BM5FHNX"},"agent_actions":{"view_html":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54","download_json":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54.json","view_paper":"https://pith.science/paper/6BM5FHNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05717&json=true","fetch_graph":"https://pith.science/api/pith-number/6BM5FHNXJ44J27Q3I2PRYSXY54/graph.json","fetch_events":"https://pith.science/api/pith-number/6BM5FHNXJ44J27Q3I2PRYSXY54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/action/storage_attestation","attest_author":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/action/author_attestation","sign_citation":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/action/citation_signature","submit_replication":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/action/replication_record"}},"created_at":"2026-06-05T01:15:00.147113+00:00","updated_at":"2026-06-05T01:15:00.147113+00:00"}