{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6BM5FHNXJ44J27Q3I2PRYSXY54","short_pith_number":"pith:6BM5FHNX","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"},"canonical_sha256":"f059d29db74f389d7e1b469f1c4af8ef342ac56b0f2ce783ebfd0c5fdb4154e0","source":{"kind":"arxiv","id":"2606.05717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05717","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05717v1","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05717","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"6BM5FHNXJ44J","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"6BM5FHNXJ44J27Q3","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"6BM5FHNX","created_at":"2026-06-05T01:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6BM5FHNXJ44J27Q3I2PRYSXY54","target":"record","payload":{"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"},"canonical_sha256":"f059d29db74f389d7e1b469f1c4af8ef342ac56b0f2ce783ebfd0c5fdb4154e0","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"},"source_kind":"arxiv","source_id":"2606.05717","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JvmUtBUyPu1q9Ot91gg1Mk35Ul+8SQBOziR1NonWG6eKNq51ASwwO3kRmWqFvxdVDo/CuRgjDEj3H5Yit+vJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:41:18.517449Z"},"content_sha256":"af8b54045422499d043789efdb67bbf6e35cc4e7957ffcee98e6bdb754bdeca5","schema_version":"1.0","event_id":"sha256:af8b54045422499d043789efdb67bbf6e35cc4e7957ffcee98e6bdb754bdeca5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6BM5FHNXJ44J27Q3I2PRYSXY54","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2TiwvzVE9+bJxcx7s3GR70vkKe70lX9cA250eY1zbYAFL/gyh79EdZbyJ89hVlxEWD8MjZpj95k8J8KobBHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T20:41:18.517813Z"},"content_sha256":"80f92077425da8d76a86c5e8dae857bf87a8fbf399df340356a932f85407b27e","schema_version":"1.0","event_id":"sha256:80f92077425da8d76a86c5e8dae857bf87a8fbf399df340356a932f85407b27e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/bundle.json","state_url":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T20:41:18Z","links":{"resolver":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54","bundle":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/bundle.json","state":"https://pith.science/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BM5FHNXJ44J27Q3I2PRYSXY54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6BM5FHNXJ44J27Q3I2PRYSXY54","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":"fcbc9e420aed99e98a933bdd43490fab560895fc8c440d3746c004dd286d9d84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T05:18:01Z","title_canon_sha256":"83a8bbfa5a94e3800a4ebdaf9238d9b7defb9c13d7c86e873e8556f1038886b7"},"schema_version":"1.0","source":{"id":"2606.05717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05717","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05717v1","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05717","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"6BM5FHNXJ44J","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"6BM5FHNXJ44J27Q3","created_at":"2026-06-05T01:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"6BM5FHNX","created_at":"2026-06-05T01:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:80f92077425da8d76a86c5e8dae857bf87a8fbf399df340356a932f85407b27e","target":"graph","created_at":"2026-06-05T01:15:00Z","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/2606.05717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adarsh Arigala, Shubham Gupta, Sri Rama Murty Kodukula","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T05:18:01Z","title":"Enhancing Audio Captioning with Auxiliary AudioSet Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05717","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:af8b54045422499d043789efdb67bbf6e35cc4e7957ffcee98e6bdb754bdeca5","target":"record","created_at":"2026-06-05T01:15:00Z","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":"fcbc9e420aed99e98a933bdd43490fab560895fc8c440d3746c004dd286d9d84","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-04T05:18:01Z","title_canon_sha256":"83a8bbfa5a94e3800a4ebdaf9238d9b7defb9c13d7c86e873e8556f1038886b7"},"schema_version":"1.0","source":{"id":"2606.05717","kind":"arxiv","version":1}},"canonical_sha256":"f059d29db74f389d7e1b469f1c4af8ef342ac56b0f2ce783ebfd0c5fdb4154e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f059d29db74f389d7e1b469f1c4af8ef342ac56b0f2ce783ebfd0c5fdb4154e0","first_computed_at":"2026-06-05T01:15:00.147027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:00.147027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q123JUDbmXpP+JocFzVpau7EHSB7+Dlbe1HXJ0+N66AdgbUxZn95f8Pu855vBWGaZmYcVlrXPfl6q8wGcFRLCg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:00.147545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af8b54045422499d043789efdb67bbf6e35cc4e7957ffcee98e6bdb754bdeca5","sha256:80f92077425da8d76a86c5e8dae857bf87a8fbf399df340356a932f85407b27e"],"state_sha256":"2986826dfe83b6c2cf0b48c4550e62124e4cb47b97b484b16dc4f0d25e18afbd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8kIsJeZVGgHa1rq3J1xlLEBBJZ9CBC6Lp5hqWOJDHtEFw9ohIX1gWASDqRbYi6fbTKiRg+8/h/eu+Fa2o+6Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T20:41:18.519740Z","bundle_sha256":"ec8249dafcf12e06ac78e592c4ed720860f1d871ae009106b9596822d5bc17c0"}}