{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UUX4HMX53VR6IAEJABQ3AZHMC5","short_pith_number":"pith:UUX4HMX5","canonical_record":{"source":{"id":"2305.18753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T05:28:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"63612545fe77154f3564bf61d0d76ff1f778e4dff068a65a0b446feb4a55b60a","abstract_canon_sha256":"3e0ce9c1ebe3a2320d1f12be8888a401b7311bdae1bbb565ddddce14b182594d"},"schema_version":"1.0"},"canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","source":{"kind":"arxiv","id":"2305.18753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18753","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18753v1","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18753","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"UUX4HMX53VR6","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"UUX4HMX53VR6IAEJ","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"UUX4HMX5","created_at":"2026-07-05T06:15:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UUX4HMX53VR6IAEJABQ3AZHMC5","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18753","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T05:28:07Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"63612545fe77154f3564bf61d0d76ff1f778e4dff068a65a0b446feb4a55b60a","abstract_canon_sha256":"3e0ce9c1ebe3a2320d1f12be8888a401b7311bdae1bbb565ddddce14b182594d"},"schema_version":"1.0"},"canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:04.517607Z","signature_b64":"sXdyALx4rM3i7/Bl8Ew/+aY+bq9m88JtbxakfhuJpsPDaxHb2k4qZTQulZRtufryLMT7wta16o0OWO25ClZTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","last_reissued_at":"2026-07-05T06:15:04.517188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:04.517188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18753","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":"2026-07-05T06:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/apn6xd7iiRrKQkyNECKfQJ9hx797WWtpjgQeSnQBCAGU1Iu5RLorppXAWHu+rj1K6rAgfweEQg/4nrUmoewBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:51:06.202790Z"},"content_sha256":"bc1ef213bdd4035b0125e312c141d6b5c0476acac8fec480c9ba3a6209535eab","schema_version":"1.0","event_id":"sha256:bc1ef213bdd4035b0125e312c141d6b5c0476acac8fec480c9ba3a6209535eab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UUX4HMX53VR6IAEJABQ3AZHMC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jianyuan Sun, Mark D. Plumbley, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2023-05-30T05:28:07Z","abstract_excerpt":"Automated audio captioning (AAC) which generates textual descriptions of audio content. Existing AAC models achieve good results but only use the high-dimensional representation of the encoder. There is always insufficient information learning of high-dimensional methods owing to high-dimensional representations having a large amount of information. In this paper, a new encoder-decoder model called the Low- and High-Dimensional Feature Fusion (LHDFF) is proposed. LHDFF uses a new PANNs encoder called Residual PANNs (RPANNs) to fuse low- and high-dimensional features. Low-dimensional features c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18753","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/2305.18753/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":"2026-07-05T06:15:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfiqFljQbGlMrJzNEp8RgER+hGKsQyA2yA5dqVbgHl2g21dzw5aGfKg+uu0o8DUaP3DJ25vaPCivWEP5PU5VBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:51:06.203298Z"},"content_sha256":"7e65ffa354de33c05746d4951cf8a9dc2d1cd1ea75828cda2dcbdfff4ed54e9f","schema_version":"1.0","event_id":"sha256:7e65ffa354de33c05746d4951cf8a9dc2d1cd1ea75828cda2dcbdfff4ed54e9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/bundle.json","state_url":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/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":"2026-08-14T06:51:06Z","links":{"resolver":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5","bundle":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/bundle.json","state":"https://pith.science/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UUX4HMX53VR6IAEJABQ3AZHMC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UUX4HMX53VR6IAEJABQ3AZHMC5","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":"3e0ce9c1ebe3a2320d1f12be8888a401b7311bdae1bbb565ddddce14b182594d","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T05:28:07Z","title_canon_sha256":"63612545fe77154f3564bf61d0d76ff1f778e4dff068a65a0b446feb4a55b60a"},"schema_version":"1.0","source":{"id":"2305.18753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18753","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18753v1","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18753","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"pith_short_12","alias_value":"UUX4HMX53VR6","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"pith_short_16","alias_value":"UUX4HMX53VR6IAEJ","created_at":"2026-07-05T06:15:04Z"},{"alias_kind":"pith_short_8","alias_value":"UUX4HMX5","created_at":"2026-07-05T06:15:04Z"}],"graph_snapshots":[{"event_id":"sha256:7e65ffa354de33c05746d4951cf8a9dc2d1cd1ea75828cda2dcbdfff4ed54e9f","target":"graph","created_at":"2026-07-05T06:15:04Z","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/2305.18753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning (AAC) which generates textual descriptions of audio content. Existing AAC models achieve good results but only use the high-dimensional representation of the encoder. There is always insufficient information learning of high-dimensional methods owing to high-dimensional representations having a large amount of information. In this paper, a new encoder-decoder model called the Low- and High-Dimensional Feature Fusion (LHDFF) is proposed. LHDFF uses a new PANNs encoder called Residual PANNs (RPANNs) to fuse low- and high-dimensional features. Low-dimensional features c","authors_text":"Jianyuan Sun, Mark D. Plumbley, Volkan K{\\i}l{\\i}\\c{c}, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T05:28:07Z","title":"Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18753","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:bc1ef213bdd4035b0125e312c141d6b5c0476acac8fec480c9ba3a6209535eab","target":"record","created_at":"2026-07-05T06:15:04Z","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":"3e0ce9c1ebe3a2320d1f12be8888a401b7311bdae1bbb565ddddce14b182594d","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-30T05:28:07Z","title_canon_sha256":"63612545fe77154f3564bf61d0d76ff1f778e4dff068a65a0b446feb4a55b60a"},"schema_version":"1.0","source":{"id":"2305.18753","kind":"arxiv","version":1}},"canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a52fc3b2fddd63e400890061b064ec177e8174af9026c90e43f6027e2c696ba3","first_computed_at":"2026-07-05T06:15:04.517188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:04.517188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sXdyALx4rM3i7/Bl8Ew/+aY+bq9m88JtbxakfhuJpsPDaxHb2k4qZTQulZRtufryLMT7wta16o0OWO25ClZTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:04.517607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc1ef213bdd4035b0125e312c141d6b5c0476acac8fec480c9ba3a6209535eab","sha256:7e65ffa354de33c05746d4951cf8a9dc2d1cd1ea75828cda2dcbdfff4ed54e9f"],"state_sha256":"1999325420371ff25eaa8422aaec05c7e0d68ed937058d99d785079153acd0f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bSJNZfrcNydt0S5dvkmQnlmezR195RRIUR4HQrQR0yem1yS+kShJaqu6bwcCqNiXa2aYC5VWBk+Bnplzy/6GBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:51:06.207260Z","bundle_sha256":"6fc266407e721ab9a84a8a40f0ed2f66633ac975a63d33320936c51044f29c6d"}}