{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:X7QBBURI4HXGLWFLNWWBV3B5PI","short_pith_number":"pith:X7QBBURI","canonical_record":{"source":{"id":"2210.05037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-10T22:39:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"cec989d6eadd71e5c993c2acce5bb297d3ce21dea97c7decfa804dcf62134c8e","abstract_canon_sha256":"dce21d096583f5ae752b104fa1900f93c059e7d366356aa341905460e3a3f58b"},"schema_version":"1.0"},"canonical_sha256":"bfe010d228e1ee65d8ab6dac1aec3d7a291fe806087dac6dbf69e272f8fbcf2c","source":{"kind":"arxiv","id":"2210.05037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05037","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05037v1","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05037","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"X7QBBURI4HXG","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"X7QBBURI4HXGLWFL","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"X7QBBURI","created_at":"2026-07-05T05:07:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:X7QBBURI4HXGLWFLNWWBV3B5PI","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-10T22:39:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"cec989d6eadd71e5c993c2acce5bb297d3ce21dea97c7decfa804dcf62134c8e","abstract_canon_sha256":"dce21d096583f5ae752b104fa1900f93c059e7d366356aa341905460e3a3f58b"},"schema_version":"1.0"},"canonical_sha256":"bfe010d228e1ee65d8ab6dac1aec3d7a291fe806087dac6dbf69e272f8fbcf2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:04.882564Z","signature_b64":"FjhvWieumJHXeshRGP9Dupxh0h8m2MJebYSugoyHux6p4KjpFc7OBHFMyFtm1g1dfQ2SvKwlrB0H8yJ21XKmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfe010d228e1ee65d8ab6dac1aec3d7a291fe806087dac6dbf69e272f8fbcf2c","last_reissued_at":"2026-07-05T05:07:04.882084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:04.882084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05037","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":"2026-07-05T05:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtsjyZ5tSo2NhY9z40Hcnd0yzRNL2SP9x43gqjnwhu0HjynWYxtKi7TdyIAXaJUmbJeAQwefvsXyMz/dX+UgDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:11:53.396785Z"},"content_sha256":"718dcf86e4cf2af5507157178f8c2100d69971acc1c8398e67033ebd12e54466","schema_version":"1.0","event_id":"sha256:718dcf86e4cf2af5507157178f8c2100d69971acc1c8398e67033ebd12e54466"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:X7QBBURI4HXGLWFLNWWBV3B5PI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Automated Audio Captioning via Fusion of Low- and High- Dimensional Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jianyuan Sun, Mark D. Plumbley, Volkan Kilic, Wenwu Wang, Xinhao Mei, Xubo Liu","submitted_at":"2022-10-10T22:39:41Z","abstract_excerpt":"Automated audio captioning (AAC) aims to describe the content of an audio clip using simple sentences. Existing AAC methods are developed based on an encoder-decoder architecture that success is attributed to the use of a pre-trained CNN10 called PANNs as the encoder to learn rich audio representations. AAC is a highly challenging task due to its high-dimensional talent space involves audio of various scenarios. Existing methods only use the high-dimensional representation of the PANNs as the input of the decoder. However, the low-dimension representation may retain as much audio information a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05037","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/2210.05037/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":"2026-07-05T05:07:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yvWPh9q1g0Yrr0pPFTKoqSCyMiOX7zIz7uB1I9j0rj7WhmHKi38IneLKB9viMEQKMHgqN9wz99xvxqhC1AsXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:11:53.397628Z"},"content_sha256":"aeba4911ed95976ef2e92660cbfb2d71bfac9d83b98a6aeaff86b8950391bf23","schema_version":"1.0","event_id":"sha256:aeba4911ed95976ef2e92660cbfb2d71bfac9d83b98a6aeaff86b8950391bf23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7QBBURI4HXGLWFLNWWBV3B5PI/bundle.json","state_url":"https://pith.science/pith/X7QBBURI4HXGLWFLNWWBV3B5PI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7QBBURI4HXGLWFLNWWBV3B5PI/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":"2026-07-31T15:11:53Z","links":{"resolver":"https://pith.science/pith/X7QBBURI4HXGLWFLNWWBV3B5PI","bundle":"https://pith.science/pith/X7QBBURI4HXGLWFLNWWBV3B5PI/bundle.json","state":"https://pith.science/pith/X7QBBURI4HXGLWFLNWWBV3B5PI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7QBBURI4HXGLWFLNWWBV3B5PI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:X7QBBURI4HXGLWFLNWWBV3B5PI","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":"dce21d096583f5ae752b104fa1900f93c059e7d366356aa341905460e3a3f58b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-10T22:39:41Z","title_canon_sha256":"cec989d6eadd71e5c993c2acce5bb297d3ce21dea97c7decfa804dcf62134c8e"},"schema_version":"1.0","source":{"id":"2210.05037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05037","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05037v1","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05037","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"pith_short_12","alias_value":"X7QBBURI4HXG","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"pith_short_16","alias_value":"X7QBBURI4HXGLWFL","created_at":"2026-07-05T05:07:04Z"},{"alias_kind":"pith_short_8","alias_value":"X7QBBURI","created_at":"2026-07-05T05:07:04Z"}],"graph_snapshots":[{"event_id":"sha256:aeba4911ed95976ef2e92660cbfb2d71bfac9d83b98a6aeaff86b8950391bf23","target":"graph","created_at":"2026-07-05T05:07:04Z","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/2210.05037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning (AAC) aims to describe the content of an audio clip using simple sentences. Existing AAC methods are developed based on an encoder-decoder architecture that success is attributed to the use of a pre-trained CNN10 called PANNs as the encoder to learn rich audio representations. AAC is a highly challenging task due to its high-dimensional talent space involves audio of various scenarios. Existing methods only use the high-dimensional representation of the PANNs as the input of the decoder. However, the low-dimension representation may retain as much audio information a","authors_text":"Jianyuan Sun, Mark D. Plumbley, Volkan Kilic, Wenwu Wang, Xinhao Mei, Xubo Liu","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-10T22:39:41Z","title":"Automated Audio Captioning via Fusion of Low- and High- Dimensional Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05037","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":"sha256:718dcf86e4cf2af5507157178f8c2100d69971acc1c8398e67033ebd12e54466","target":"record","created_at":"2026-07-05T05:07:04Z","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":"dce21d096583f5ae752b104fa1900f93c059e7d366356aa341905460e3a3f58b","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-10-10T22:39:41Z","title_canon_sha256":"cec989d6eadd71e5c993c2acce5bb297d3ce21dea97c7decfa804dcf62134c8e"},"schema_version":"1.0","source":{"id":"2210.05037","kind":"arxiv","version":1}},"canonical_sha256":"bfe010d228e1ee65d8ab6dac1aec3d7a291fe806087dac6dbf69e272f8fbcf2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfe010d228e1ee65d8ab6dac1aec3d7a291fe806087dac6dbf69e272f8fbcf2c","first_computed_at":"2026-07-05T05:07:04.882084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:04.882084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjhvWieumJHXeshRGP9Dupxh0h8m2MJebYSugoyHux6p4KjpFc7OBHFMyFtm1g1dfQ2SvKwlrB0H8yJ21XKmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:04.882564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:718dcf86e4cf2af5507157178f8c2100d69971acc1c8398e67033ebd12e54466","sha256:aeba4911ed95976ef2e92660cbfb2d71bfac9d83b98a6aeaff86b8950391bf23"],"state_sha256":"510d2d7848735f9963233a7e215aae5af0529a34b9c3ce55e49a1bdb5ac3dfec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WyKdLMfXwgBm6PZippJTW565XmVbcszrPVRrOn/IeJxzR1iBCBNxFCUVATgaUYjsIjFR4DHKqYM1P8CvUXc6Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:11:53.403967Z","bundle_sha256":"f673968f3f3e2ead622cbd3bfee06238d9b9ef04fa0bc8ab2b8905e8d04cc6ee"}}