{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5PZCARUTPDCTG6CAXI4XB3LWWK","short_pith_number":"pith:5PZCARUT","canonical_record":{"source":{"id":"2204.08409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-18T17:07:31Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e8adbfe0ab72db33b2f130ce616b1ce5f1958c87b5b268d71660c409b8b25e38","abstract_canon_sha256":"a2f15fde01a941d4319c5c90c462a8f835fc3fa9379308860076af5083ab8485"},"schema_version":"1.0"},"canonical_sha256":"ebf220469378c5337840ba3970ed76b2b178ddbc2e8cab219dd3d6281d1a02e2","source":{"kind":"arxiv","id":"2204.08409","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08409","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08409v1","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08409","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"5PZCARUTPDCT","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"5PZCARUTPDCTG6CA","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"5PZCARUT","created_at":"2026-07-05T04:15:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5PZCARUTPDCTG6CAXI4XB3LWWK","target":"record","payload":{"canonical_record":{"source":{"id":"2204.08409","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-18T17:07:31Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"e8adbfe0ab72db33b2f130ce616b1ce5f1958c87b5b268d71660c409b8b25e38","abstract_canon_sha256":"a2f15fde01a941d4319c5c90c462a8f835fc3fa9379308860076af5083ab8485"},"schema_version":"1.0"},"canonical_sha256":"ebf220469378c5337840ba3970ed76b2b178ddbc2e8cab219dd3d6281d1a02e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:25.703676Z","signature_b64":"Hf0vrCke9TtKv2HsV5H+gctErxQhZEJKHHokbZD+ZDQ+EaIFjnTxIG4XcMcHOR97s86bpHVhBzjvUqQ2B9+jBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf220469378c5337840ba3970ed76b2b178ddbc2e8cab219dd3d6281d1a02e2","last_reissued_at":"2026-07-05T04:15:25.703156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:25.703156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.08409","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":"2026-07-05T04:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ic64n4Pd/Sar1OMVj5aUTJ/Unp/Z9uyryF1ym7NtmHGdjcPP3+Azngq6l0JbqknVvMwVScF51ZET+RRWXfBYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:12:00.210925Z"},"content_sha256":"0161a73cbc8cf030105a254bbda4d995371925e2bb9b5ef36a32b54309a624a9","schema_version":"1.0","event_id":"sha256:0161a73cbc8cf030105a254bbda4d995371925e2bb9b5ef36a32b54309a624a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5PZCARUTPDCTG6CAXI4XB3LWWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Caption Feature Space Regularization for Audio Captioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hong Yu, Ruoyi Du, Yiming Zhang, Yuan Dong, Zhanyu Ma","submitted_at":"2022-04-18T17:07:31Z","abstract_excerpt":"Audio captioning aims at describing the content of audio clips with human language. Due to the ambiguity of audio, different people may perceive the same audio differently, resulting in caption disparities (i.e., one audio may correlate to several captions with diverse semantics). For that, general audio captioning models achieve the one-to-many training by randomly selecting a correlated caption as the ground truth for each audio. However, it leads to a significant variation in the optimization directions and weakens the model stability. To eliminate this negative effect, in this paper, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08409","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/2204.08409/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":"2026-07-05T04:15:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hjszZO4Ab0zxRKuGiMTLrvPNcHUxmPbDD8d1aOnE/B6C/L/tb/1dA4S/VrqlMekvKgphC0Uf6gGjDUyLOGaZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:12:00.212272Z"},"content_sha256":"9a47280e75a4d18808ca1b114f918252596199af405ac425f40addd7a06c6abc","schema_version":"1.0","event_id":"sha256:9a47280e75a4d18808ca1b114f918252596199af405ac425f40addd7a06c6abc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PZCARUTPDCTG6CAXI4XB3LWWK/bundle.json","state_url":"https://pith.science/pith/5PZCARUTPDCTG6CAXI4XB3LWWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PZCARUTPDCTG6CAXI4XB3LWWK/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":"2026-08-08T11:12:00Z","links":{"resolver":"https://pith.science/pith/5PZCARUTPDCTG6CAXI4XB3LWWK","bundle":"https://pith.science/pith/5PZCARUTPDCTG6CAXI4XB3LWWK/bundle.json","state":"https://pith.science/pith/5PZCARUTPDCTG6CAXI4XB3LWWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PZCARUTPDCTG6CAXI4XB3LWWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5PZCARUTPDCTG6CAXI4XB3LWWK","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":"a2f15fde01a941d4319c5c90c462a8f835fc3fa9379308860076af5083ab8485","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-18T17:07:31Z","title_canon_sha256":"e8adbfe0ab72db33b2f130ce616b1ce5f1958c87b5b268d71660c409b8b25e38"},"schema_version":"1.0","source":{"id":"2204.08409","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08409","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08409v1","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08409","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_12","alias_value":"5PZCARUTPDCT","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_16","alias_value":"5PZCARUTPDCTG6CA","created_at":"2026-07-05T04:15:25Z"},{"alias_kind":"pith_short_8","alias_value":"5PZCARUT","created_at":"2026-07-05T04:15:25Z"}],"graph_snapshots":[{"event_id":"sha256:9a47280e75a4d18808ca1b114f918252596199af405ac425f40addd7a06c6abc","target":"graph","created_at":"2026-07-05T04:15:25Z","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/2204.08409/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio captioning aims at describing the content of audio clips with human language. Due to the ambiguity of audio, different people may perceive the same audio differently, resulting in caption disparities (i.e., one audio may correlate to several captions with diverse semantics). For that, general audio captioning models achieve the one-to-many training by randomly selecting a correlated caption as the ground truth for each audio. However, it leads to a significant variation in the optimization directions and weakens the model stability. To eliminate this negative effect, in this paper, we pr","authors_text":"Hong Yu, Ruoyi Du, Yiming Zhang, Yuan Dong, Zhanyu Ma","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-18T17:07:31Z","title":"Caption Feature Space Regularization for Audio Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08409","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":"sha256:0161a73cbc8cf030105a254bbda4d995371925e2bb9b5ef36a32b54309a624a9","target":"record","created_at":"2026-07-05T04:15:25Z","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":"a2f15fde01a941d4319c5c90c462a8f835fc3fa9379308860076af5083ab8485","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-04-18T17:07:31Z","title_canon_sha256":"e8adbfe0ab72db33b2f130ce616b1ce5f1958c87b5b268d71660c409b8b25e38"},"schema_version":"1.0","source":{"id":"2204.08409","kind":"arxiv","version":1}},"canonical_sha256":"ebf220469378c5337840ba3970ed76b2b178ddbc2e8cab219dd3d6281d1a02e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf220469378c5337840ba3970ed76b2b178ddbc2e8cab219dd3d6281d1a02e2","first_computed_at":"2026-07-05T04:15:25.703156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:25.703156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hf0vrCke9TtKv2HsV5H+gctErxQhZEJKHHokbZD+ZDQ+EaIFjnTxIG4XcMcHOR97s86bpHVhBzjvUqQ2B9+jBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:25.703676Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08409","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0161a73cbc8cf030105a254bbda4d995371925e2bb9b5ef36a32b54309a624a9","sha256:9a47280e75a4d18808ca1b114f918252596199af405ac425f40addd7a06c6abc"],"state_sha256":"05209b2995108d88dfd6315bd89bd7175dc10284d2031de9af9488b89e44335e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WY2UT80XkCY1ygj8z0s/ERxaYcspn/Mqc8qJfJn5cunrb2miCwxRI7LL4lOALJ5uBoHdh5YHJpAJPMpGOmlrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:12:00.217852Z","bundle_sha256":"7d80cec469b5c117a5aa4c68b73ccb3bb7e052ca04f2534d5d7f554b1b5e9486"}}