{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UWDAAXJHTTPZOWA5PMKWV3A55X","short_pith_number":"pith:UWDAAXJH","canonical_record":{"source":{"id":"2309.17352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T15:57:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"145fdfb613c329b7aa13dcbf07b1e6d2d980fcad975e03d2520e25a77cacf185","abstract_canon_sha256":"203e82f009f6bff94a96ed1fba7dd424a0bec8b2767c83a7d5b8f07210064fac"},"schema_version":"1.0"},"canonical_sha256":"a586005d279cdf97581d7b156aec1dede055898dd3abb678c6d54f84cf8a7384","source":{"kind":"arxiv","id":"2309.17352","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17352","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17352v2","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17352","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"UWDAAXJHTTPZ","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"pith_short_16","alias_value":"UWDAAXJHTTPZOWA5","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"pith_short_8","alias_value":"UWDAAXJH","created_at":"2026-07-05T07:31:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UWDAAXJHTTPZOWA5PMKWV3A55X","target":"record","payload":{"canonical_record":{"source":{"id":"2309.17352","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T15:57:46Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"145fdfb613c329b7aa13dcbf07b1e6d2d980fcad975e03d2520e25a77cacf185","abstract_canon_sha256":"203e82f009f6bff94a96ed1fba7dd424a0bec8b2767c83a7d5b8f07210064fac"},"schema_version":"1.0"},"canonical_sha256":"a586005d279cdf97581d7b156aec1dede055898dd3abb678c6d54f84cf8a7384","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:54.658731Z","signature_b64":"OzWC8FFMysUET/e2QfZ9Ys8SVWsvcIkEkkmqqr19HOV+YVzuBLgMjeI/JsAzuCtW+g4KMDuWSZjXTOWbWnT8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a586005d279cdf97581d7b156aec1dede055898dd3abb678c6d54f84cf8a7384","last_reissued_at":"2026-07-05T07:31:54.658237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:54.658237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.17352","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:31:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPgWwpDF/aHofNCp8DK3GfFvqyb7AJjr7DhojyljfYcoZW1eJ2rOAujriNRqgcxEdS7HphZRAGkBcwrBDcqmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:32:49.717573Z"},"content_sha256":"5d5fd39ca64ad2e3b735807bdfdd13f2046a99915c3d47f02f772095c8475ffd","schema_version":"1.0","event_id":"sha256:5d5fd39ca64ad2e3b735807bdfdd13f2046a99915c3d47f02f772095c8475ffd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UWDAAXJHTTPZOWA5PMKWV3A55X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Fran\\c{c}ois Germain, Gordon Wichern, Jee-weon Jung, Jonathan Le Roux, Shih-Lun Wu, Shinji Watanabe, Xuankai Chang","submitted_at":"2023-09-29T15:57:46Z","abstract_excerpt":"Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a sequence-to-sequence (seq2seq) backbone powered by strong models such as Transformers. Following the macro-trend of applied machine learning research, in this work, we strive to improve the performance of seq2seq AAC models by extensively leveraging pretrained models and large language models (LLMs). Specifically, we utilize BEATs to extract fine-grained aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17352","kind":"arxiv","version":2},"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/2309.17352/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":"2026-07-05T07:31:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5bULDo9f6ibMhwvi5Yi6H3snwpHkmvs/SDswIgKO5k9hHkCA9HXJO7udUkmxqubyIWP5PoBH1GHX2E/Dc/MKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:32:49.717964Z"},"content_sha256":"3146103ad5f049101c3c77995cb92311ced60036ca050b8efe07b0bc997221d4","schema_version":"1.0","event_id":"sha256:3146103ad5f049101c3c77995cb92311ced60036ca050b8efe07b0bc997221d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UWDAAXJHTTPZOWA5PMKWV3A55X/bundle.json","state_url":"https://pith.science/pith/UWDAAXJHTTPZOWA5PMKWV3A55X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UWDAAXJHTTPZOWA5PMKWV3A55X/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":"2026-07-09T03:32:49Z","links":{"resolver":"https://pith.science/pith/UWDAAXJHTTPZOWA5PMKWV3A55X","bundle":"https://pith.science/pith/UWDAAXJHTTPZOWA5PMKWV3A55X/bundle.json","state":"https://pith.science/pith/UWDAAXJHTTPZOWA5PMKWV3A55X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UWDAAXJHTTPZOWA5PMKWV3A55X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UWDAAXJHTTPZOWA5PMKWV3A55X","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":"203e82f009f6bff94a96ed1fba7dd424a0bec8b2767c83a7d5b8f07210064fac","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T15:57:46Z","title_canon_sha256":"145fdfb613c329b7aa13dcbf07b1e6d2d980fcad975e03d2520e25a77cacf185"},"schema_version":"1.0","source":{"id":"2309.17352","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17352","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17352v2","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17352","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"UWDAAXJHTTPZ","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"pith_short_16","alias_value":"UWDAAXJHTTPZOWA5","created_at":"2026-07-05T07:31:54Z"},{"alias_kind":"pith_short_8","alias_value":"UWDAAXJH","created_at":"2026-07-05T07:31:54Z"}],"graph_snapshots":[{"event_id":"sha256:3146103ad5f049101c3c77995cb92311ced60036ca050b8efe07b0bc997221d4","target":"graph","created_at":"2026-07-05T07:31:54Z","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/2309.17352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning (AAC) aims to generate informative descriptions for various sounds from nature and/or human activities. In recent years, AAC has quickly attracted research interest, with state-of-the-art systems now relying on a sequence-to-sequence (seq2seq) backbone powered by strong models such as Transformers. Following the macro-trend of applied machine learning research, in this work, we strive to improve the performance of seq2seq AAC models by extensively leveraging pretrained models and large language models (LLMs). Specifically, we utilize BEATs to extract fine-grained aud","authors_text":"Fran\\c{c}ois Germain, Gordon Wichern, Jee-weon Jung, Jonathan Le Roux, Shih-Lun Wu, Shinji Watanabe, Xuankai Chang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T15:57:46Z","title":"Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17352","kind":"arxiv","version":2},"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":"sha256:5d5fd39ca64ad2e3b735807bdfdd13f2046a99915c3d47f02f772095c8475ffd","target":"record","created_at":"2026-07-05T07:31:54Z","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":"203e82f009f6bff94a96ed1fba7dd424a0bec8b2767c83a7d5b8f07210064fac","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-09-29T15:57:46Z","title_canon_sha256":"145fdfb613c329b7aa13dcbf07b1e6d2d980fcad975e03d2520e25a77cacf185"},"schema_version":"1.0","source":{"id":"2309.17352","kind":"arxiv","version":2}},"canonical_sha256":"a586005d279cdf97581d7b156aec1dede055898dd3abb678c6d54f84cf8a7384","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a586005d279cdf97581d7b156aec1dede055898dd3abb678c6d54f84cf8a7384","first_computed_at":"2026-07-05T07:31:54.658237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:31:54.658237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OzWC8FFMysUET/e2QfZ9Ys8SVWsvcIkEkkmqqr19HOV+YVzuBLgMjeI/JsAzuCtW+g4KMDuWSZjXTOWbWnT8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:31:54.658731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.17352","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d5fd39ca64ad2e3b735807bdfdd13f2046a99915c3d47f02f772095c8475ffd","sha256:3146103ad5f049101c3c77995cb92311ced60036ca050b8efe07b0bc997221d4"],"state_sha256":"93a407228a9d8072e1259fcd4117930b0c24e28fe59c178e7f6b08fdd984698a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23s5hb9jlffu0wEhTiJjwEdNPo6UoAmkPVm2kHt7H5J70bgt022jCLogzC69MUpDcADnzAl8A4bwn7tX3imTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:32:49.720116Z","bundle_sha256":"1aef988548fd088c7229ebb01d9068d3ea602e7e07c49f66e1789bf59eaff2bc"}}