{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:JQJGFOQ5EJ2V3LNWSXSW2BTREQ","short_pith_number":"pith:JQJGFOQ5","canonical_record":{"source":{"id":"2306.01533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-02T13:36:34Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"60aab9a3d9e65ca0d7fc6b0ad378dc2948976fa710ca28432f2c594e4993c6f7","abstract_canon_sha256":"779ac13e27e0d63fe283f66501682573e0f9ff9a906854fc0ee672d834ab9942"},"schema_version":"1.0"},"canonical_sha256":"4c1262ba1d22755dadb695e56d0671243fe714b0e29f22c70d5bd9bf2977bf71","source":{"kind":"arxiv","id":"2306.01533","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01533","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01533v2","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01533","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"JQJGFOQ5EJ2V","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"JQJGFOQ5EJ2V3LNW","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"JQJGFOQ5","created_at":"2026-07-05T08:45:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:JQJGFOQ5EJ2V3LNWSXSW2BTREQ","target":"record","payload":{"canonical_record":{"source":{"id":"2306.01533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-02T13:36:34Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"60aab9a3d9e65ca0d7fc6b0ad378dc2948976fa710ca28432f2c594e4993c6f7","abstract_canon_sha256":"779ac13e27e0d63fe283f66501682573e0f9ff9a906854fc0ee672d834ab9942"},"schema_version":"1.0"},"canonical_sha256":"4c1262ba1d22755dadb695e56d0671243fe714b0e29f22c70d5bd9bf2977bf71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:20.835752Z","signature_b64":"9zdSSGImo/ti7TQiJC0+Kk76fLoFEClSrKQzBgU9Gu40QWAu0VVGP9pZX3i4K+qgk9OMfPT92Jc30jf8Ce9zCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c1262ba1d22755dadb695e56d0671243fe714b0e29f22c70d5bd9bf2977bf71","last_reissued_at":"2026-07-05T08:45:20.835226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:20.835226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.01533","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":"2026-07-05T08:45:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4mZhvgbPMpiYTDyT47crnfxx7aiWmTIdYfPtuqmnH0aAfZcNKjDQlsOIPjSyGEmKKdSyvNQ9O1BJRFfZCSMtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T20:12:58.485030Z"},"content_sha256":"1dadc5534dcebb3bab08326726a640bd8e1db84fa0fa62ff0d3bebcdda1a5848","schema_version":"1.0","event_id":"sha256:1dadc5534dcebb3bab08326726a640bd8e1db84fa0fa62ff0d3bebcdda1a5848"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:JQJGFOQ5EJ2V3LNWSXSW2BTREQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhance Temporal Relations in Audio Captioning with Sound Event Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Yu, Mengyue Wu, Xuenan Xu, Zeyu Xie","submitted_at":"2023-06-02T13:36:34Z","abstract_excerpt":"Automated audio captioning aims at generating natural language descriptions for given audio clips, not only detecting and classifying sounds, but also summarizing the relationships between audio events. Recent research advances in audio captioning have introduced additional guidance to improve the accuracy of audio events in generated sentences. However, temporal relations between audio events have received little attention while revealing complex relations is a key component in summarizing audio content. Therefore, this paper aims to better capture temporal relationships in caption generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01533","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/2306.01533/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":"2026-07-05T08:45:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OArrXrjVHQdkKmzu3h9761McUGrqqgFp9pJwhgDhSVk+XINb2v+iP48Gtczo9t/v2Dt9AvT3np6tz0bywqQhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T20:12:58.485438Z"},"content_sha256":"9aef09885c6eb53617fc472b0082fb6dcf3a285c85cdbe28f1c127abedf79bde","schema_version":"1.0","event_id":"sha256:9aef09885c6eb53617fc472b0082fb6dcf3a285c85cdbe28f1c127abedf79bde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ/bundle.json","state_url":"https://pith.science/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ/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":"2026-07-13T20:12:58Z","links":{"resolver":"https://pith.science/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ","bundle":"https://pith.science/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ/bundle.json","state":"https://pith.science/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQJGFOQ5EJ2V3LNWSXSW2BTREQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JQJGFOQ5EJ2V3LNWSXSW2BTREQ","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":"779ac13e27e0d63fe283f66501682573e0f9ff9a906854fc0ee672d834ab9942","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-02T13:36:34Z","title_canon_sha256":"60aab9a3d9e65ca0d7fc6b0ad378dc2948976fa710ca28432f2c594e4993c6f7"},"schema_version":"1.0","source":{"id":"2306.01533","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01533","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01533v2","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01533","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"pith_short_12","alias_value":"JQJGFOQ5EJ2V","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"pith_short_16","alias_value":"JQJGFOQ5EJ2V3LNW","created_at":"2026-07-05T08:45:20Z"},{"alias_kind":"pith_short_8","alias_value":"JQJGFOQ5","created_at":"2026-07-05T08:45:20Z"}],"graph_snapshots":[{"event_id":"sha256:9aef09885c6eb53617fc472b0082fb6dcf3a285c85cdbe28f1c127abedf79bde","target":"graph","created_at":"2026-07-05T08:45:20Z","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/2306.01533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated audio captioning aims at generating natural language descriptions for given audio clips, not only detecting and classifying sounds, but also summarizing the relationships between audio events. Recent research advances in audio captioning have introduced additional guidance to improve the accuracy of audio events in generated sentences. However, temporal relations between audio events have received little attention while revealing complex relations is a key component in summarizing audio content. Therefore, this paper aims to better capture temporal relationships in caption generation","authors_text":"Kai Yu, Mengyue Wu, Xuenan Xu, Zeyu Xie","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-02T13:36:34Z","title":"Enhance Temporal Relations in Audio Captioning with Sound Event Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01533","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":"sha256:1dadc5534dcebb3bab08326726a640bd8e1db84fa0fa62ff0d3bebcdda1a5848","target":"record","created_at":"2026-07-05T08:45:20Z","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":"779ac13e27e0d63fe283f66501682573e0f9ff9a906854fc0ee672d834ab9942","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-02T13:36:34Z","title_canon_sha256":"60aab9a3d9e65ca0d7fc6b0ad378dc2948976fa710ca28432f2c594e4993c6f7"},"schema_version":"1.0","source":{"id":"2306.01533","kind":"arxiv","version":2}},"canonical_sha256":"4c1262ba1d22755dadb695e56d0671243fe714b0e29f22c70d5bd9bf2977bf71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c1262ba1d22755dadb695e56d0671243fe714b0e29f22c70d5bd9bf2977bf71","first_computed_at":"2026-07-05T08:45:20.835226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:20.835226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9zdSSGImo/ti7TQiJC0+Kk76fLoFEClSrKQzBgU9Gu40QWAu0VVGP9pZX3i4K+qgk9OMfPT92Jc30jf8Ce9zCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:20.835752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01533","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dadc5534dcebb3bab08326726a640bd8e1db84fa0fa62ff0d3bebcdda1a5848","sha256:9aef09885c6eb53617fc472b0082fb6dcf3a285c85cdbe28f1c127abedf79bde"],"state_sha256":"6698ae893a243914381294c612e2c62c93e59cd35568b68f051b2c5d6fca8570"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g5Bk9NUjWYELkvB46aeHuQhnO7LlCwKfYugcAThJWXr7b0YHSMi+0NuQ+Mg4cbaBXY+JFMGJ7aroJNzA3C/6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T20:12:58.487577Z","bundle_sha256":"e223967098f1ce0eabf16eca6c94a03ceb4a1f726b6d92d816ffaa9dab53952e"}}