{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5YSYGENU2ARQAKXGX5C6FVQM7J","short_pith_number":"pith:5YSYGENU","canonical_record":{"source":{"id":"2410.12028","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-15T19:57:37Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"e3e91715f978d96aa7b89aa7bfb4d4b81e286fccbbc3317e3a04763975fb2569","abstract_canon_sha256":"6656bc6a04ca9991de186982dcf1bd02584021b634f13557759cf6252e225d56"},"schema_version":"1.0"},"canonical_sha256":"ee258311b4d023002ae6bf45e2d60cfa57528d15af51681df0db116aa70d9989","source":{"kind":"arxiv","id":"2410.12028","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12028","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12028v1","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12028","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"pith_short_12","alias_value":"5YSYGENU2ARQ","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"pith_short_16","alias_value":"5YSYGENU2ARQAKXG","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"pith_short_8","alias_value":"5YSYGENU","created_at":"2026-07-05T09:21:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5YSYGENU2ARQAKXGX5C6FVQM7J","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12028","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-15T19:57:37Z","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"title_canon_sha256":"e3e91715f978d96aa7b89aa7bfb4d4b81e286fccbbc3317e3a04763975fb2569","abstract_canon_sha256":"6656bc6a04ca9991de186982dcf1bd02584021b634f13557759cf6252e225d56"},"schema_version":"1.0"},"canonical_sha256":"ee258311b4d023002ae6bf45e2d60cfa57528d15af51681df0db116aa70d9989","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:13.020615Z","signature_b64":"JGYIWtNbwhHmhOfuZ6XJlmCjC9IbmSUPQ73roWyjI16F9wDo0ik9RstveYJPWSNcXTZh2DUn1b4kcZ9FcOhACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee258311b4d023002ae6bf45e2d60cfa57528d15af51681df0db116aa70d9989","last_reissued_at":"2026-07-05T09:21:13.020156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:13.020156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12028","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":"2026-07-05T09:21:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MWg7NQTUW+m4Lpsfeyy725S00UfCVQnTz22BnnTjkzXVqH83D8BU7eNqUz5DqLT13HhlR8NQfc5r/xJqYX2mBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:04:03.800275Z"},"content_sha256":"cb5353861fa7e7ccc6d5e669f5c7336d24973399d0a19bcbc2c859b2c0abc3a3","schema_version":"1.0","event_id":"sha256:cb5353861fa7e7ccc6d5e669f5c7336d24973399d0a19bcbc2c859b2c0abc3a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5YSYGENU2ARQAKXGX5C6FVQM7J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.AS","eess.SP"],"primary_cat":"cs.SD","authors_text":"Mark Cartwright (1) ((1) New Jersey Institute of Technology), Mithun Manivannan (1), Vignesh Nethrapalli (1)","submitted_at":"2024-10-15T19:57:37Z","abstract_excerpt":"Recent progress in audio-language modeling, such as automated audio captioning, has benefited from training on synthetic data generated with the aid of large-language models. However, such approaches for environmental sound captioning have primarily focused on audio event tags and have not explored leveraging emotional information that may be present in recordings. In this work, we explore the benefit of generating emotion-augmented synthetic audio caption data by instructing ChatGPT with additional acoustic information in the form of estimated soundscape emotion. To do so, we introduce Emotio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12028","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/2410.12028/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":"2026-07-05T09:21:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwnBt0VESsEHho3S9kqJd5w9BoDcUO8Dr6Ck2cJUo/xx0LAfFczjTBXEN45WY0WJawdg3E8EpvG5Rqs7MPcADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:04:03.801257Z"},"content_sha256":"b1b70f7a3375c0110b789de872fa4938611b05d7af066013122501dd85820fd2","schema_version":"1.0","event_id":"sha256:b1b70f7a3375c0110b789de872fa4938611b05d7af066013122501dd85820fd2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YSYGENU2ARQAKXGX5C6FVQM7J/bundle.json","state_url":"https://pith.science/pith/5YSYGENU2ARQAKXGX5C6FVQM7J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YSYGENU2ARQAKXGX5C6FVQM7J/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":"2026-08-13T01:04:03Z","links":{"resolver":"https://pith.science/pith/5YSYGENU2ARQAKXGX5C6FVQM7J","bundle":"https://pith.science/pith/5YSYGENU2ARQAKXGX5C6FVQM7J/bundle.json","state":"https://pith.science/pith/5YSYGENU2ARQAKXGX5C6FVQM7J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YSYGENU2ARQAKXGX5C6FVQM7J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5YSYGENU2ARQAKXGX5C6FVQM7J","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":"6656bc6a04ca9991de186982dcf1bd02584021b634f13557759cf6252e225d56","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-15T19:57:37Z","title_canon_sha256":"e3e91715f978d96aa7b89aa7bfb4d4b81e286fccbbc3317e3a04763975fb2569"},"schema_version":"1.0","source":{"id":"2410.12028","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12028","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12028v1","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12028","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"pith_short_12","alias_value":"5YSYGENU2ARQ","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"pith_short_16","alias_value":"5YSYGENU2ARQAKXG","created_at":"2026-07-05T09:21:13Z"},{"alias_kind":"pith_short_8","alias_value":"5YSYGENU","created_at":"2026-07-05T09:21:13Z"}],"graph_snapshots":[{"event_id":"sha256:b1b70f7a3375c0110b789de872fa4938611b05d7af066013122501dd85820fd2","target":"graph","created_at":"2026-07-05T09:21:13Z","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/2410.12028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in audio-language modeling, such as automated audio captioning, has benefited from training on synthetic data generated with the aid of large-language models. However, such approaches for environmental sound captioning have primarily focused on audio event tags and have not explored leveraging emotional information that may be present in recordings. In this work, we explore the benefit of generating emotion-augmented synthetic audio caption data by instructing ChatGPT with additional acoustic information in the form of estimated soundscape emotion. To do so, we introduce Emotio","authors_text":"Mark Cartwright (1) ((1) New Jersey Institute of Technology), Mithun Manivannan (1), Vignesh Nethrapalli (1)","cross_cats":["cs.LG","eess.AS","eess.SP"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-15T19:57:37Z","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12028","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:cb5353861fa7e7ccc6d5e669f5c7336d24973399d0a19bcbc2c859b2c0abc3a3","target":"record","created_at":"2026-07-05T09:21:13Z","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":"6656bc6a04ca9991de186982dcf1bd02584021b634f13557759cf6252e225d56","cross_cats_sorted":["cs.LG","eess.AS","eess.SP"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-10-15T19:57:37Z","title_canon_sha256":"e3e91715f978d96aa7b89aa7bfb4d4b81e286fccbbc3317e3a04763975fb2569"},"schema_version":"1.0","source":{"id":"2410.12028","kind":"arxiv","version":1}},"canonical_sha256":"ee258311b4d023002ae6bf45e2d60cfa57528d15af51681df0db116aa70d9989","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee258311b4d023002ae6bf45e2d60cfa57528d15af51681df0db116aa70d9989","first_computed_at":"2026-07-05T09:21:13.020156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:13.020156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JGYIWtNbwhHmhOfuZ6XJlmCjC9IbmSUPQ73roWyjI16F9wDo0ik9RstveYJPWSNcXTZh2DUn1b4kcZ9FcOhACg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:13.020615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12028","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb5353861fa7e7ccc6d5e669f5c7336d24973399d0a19bcbc2c859b2c0abc3a3","sha256:b1b70f7a3375c0110b789de872fa4938611b05d7af066013122501dd85820fd2"],"state_sha256":"e678f86f2228ed85526fbb5f079c732972ca64b21af4844e3ebcf150614da651"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zTYtgRzpO7y9og++YBzZLzzw+eFyjOPZe3D5wcyoTUx0nLsISa98G/BMS1tKDlmoICGNXsgQ09YQbh4TlT/7CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:04:03.831900Z","bundle_sha256":"4eaacf1a84e01ff84ecb38b89e91b5cdcbf2f5d8f54f40c3c72b84aba8144427"}}