{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JW3LT437NLVHEDYLKFT6WURUSX","short_pith_number":"pith:JW3LT437","canonical_record":{"source":{"id":"2102.11474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T03:44:14Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e84087c505e3a122f9b32f9fd0b96a44880c6a1d1eafdc0deff0f9f1cdfa46f5","abstract_canon_sha256":"17ce4fab4248b9920aed46e58351c2567b2537bd7dc14d044cf2555175e22fa8"},"schema_version":"1.0"},"canonical_sha256":"4db6b9f37f6aea720f0b5167eb523495e97dda04dbee03b65b799433ddbb66bf","source":{"kind":"arxiv","id":"2102.11474","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11474","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11474v1","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11474","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"JW3LT437NLVH","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"JW3LT437NLVHEDYL","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"JW3LT437","created_at":"2026-07-05T02:17:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JW3LT437NLVHEDYLKFT6WURUSX","target":"record","payload":{"canonical_record":{"source":{"id":"2102.11474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T03:44:14Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"e84087c505e3a122f9b32f9fd0b96a44880c6a1d1eafdc0deff0f9f1cdfa46f5","abstract_canon_sha256":"17ce4fab4248b9920aed46e58351c2567b2537bd7dc14d044cf2555175e22fa8"},"schema_version":"1.0"},"canonical_sha256":"4db6b9f37f6aea720f0b5167eb523495e97dda04dbee03b65b799433ddbb66bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:11.903527Z","signature_b64":"1rhnvcKsNsNUU+og7LnHbTZVfS+Cl/+OwYqQljGnS2N8XN+DiOza4klF4ub0+4LDuIa67x1pBedTn9wDskNnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4db6b9f37f6aea720f0b5167eb523495e97dda04dbee03b65b799433ddbb66bf","last_reissued_at":"2026-07-05T02:17:11.903106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:11.903106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.11474","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":"2026-07-05T02:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fGF1JXOcTcBP9oOD1HIon/VXlUzVsPJ+sooPfO2KIy5USyUxPSOA75aLrwNTqJ5hjC1KVdsmRgEk8XROynhfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:07:41.796928Z"},"content_sha256":"24166fd6f91dec12d8518ef96712348e3e0dc39dc6933ef8b7a34db6844b30c9","schema_version":"1.0","event_id":"sha256:24166fd6f91dec12d8518ef96712348e3e0dc39dc6933ef8b7a34db6844b30c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JW3LT437NLVHEDYLKFT6WURUSX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Xuenan Xu","submitted_at":"2021-02-23T03:44:14Z","abstract_excerpt":"Automated Audio Captioning is a cross-modal task, generating natural language descriptions to summarize the audio clips' sound events. However, grounding the actual sound events in the given audio based on its corresponding caption has not been investigated. This paper contributes an AudioGrounding dataset, which provides the correspondence between sound events and the captions provided in Audiocaps, along with the location (timestamps) of each present sound event. Based on such, we propose the text-to-audio grounding (TAG) task, which interactively considers the relationship between audio pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11474","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/2102.11474/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":"2026-07-05T02:17:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e+7OkGQOfDfMf5aeS/cHPI3BayXqpWzKpOkHAw6GsGNSojcrNskbt6LZEvUEdoUl71yK7Nx0H+O6pG/vDNuTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:07:41.797265Z"},"content_sha256":"125d93b39d7b3ac5e1c61c5de857952b9594a9031719c3297f38b38de422fb05","schema_version":"1.0","event_id":"sha256:125d93b39d7b3ac5e1c61c5de857952b9594a9031719c3297f38b38de422fb05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JW3LT437NLVHEDYLKFT6WURUSX/bundle.json","state_url":"https://pith.science/pith/JW3LT437NLVHEDYLKFT6WURUSX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JW3LT437NLVHEDYLKFT6WURUSX/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":"2026-08-20T02:07:41Z","links":{"resolver":"https://pith.science/pith/JW3LT437NLVHEDYLKFT6WURUSX","bundle":"https://pith.science/pith/JW3LT437NLVHEDYLKFT6WURUSX/bundle.json","state":"https://pith.science/pith/JW3LT437NLVHEDYLKFT6WURUSX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JW3LT437NLVHEDYLKFT6WURUSX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JW3LT437NLVHEDYLKFT6WURUSX","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":"17ce4fab4248b9920aed46e58351c2567b2537bd7dc14d044cf2555175e22fa8","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T03:44:14Z","title_canon_sha256":"e84087c505e3a122f9b32f9fd0b96a44880c6a1d1eafdc0deff0f9f1cdfa46f5"},"schema_version":"1.0","source":{"id":"2102.11474","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11474","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11474v1","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11474","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_12","alias_value":"JW3LT437NLVH","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_16","alias_value":"JW3LT437NLVHEDYL","created_at":"2026-07-05T02:17:11Z"},{"alias_kind":"pith_short_8","alias_value":"JW3LT437","created_at":"2026-07-05T02:17:11Z"}],"graph_snapshots":[{"event_id":"sha256:125d93b39d7b3ac5e1c61c5de857952b9594a9031719c3297f38b38de422fb05","target":"graph","created_at":"2026-07-05T02:17:11Z","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/2102.11474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automated Audio Captioning is a cross-modal task, generating natural language descriptions to summarize the audio clips' sound events. However, grounding the actual sound events in the given audio based on its corresponding caption has not been investigated. This paper contributes an AudioGrounding dataset, which provides the correspondence between sound events and the captions provided in Audiocaps, along with the location (timestamps) of each present sound event. Based on such, we propose the text-to-audio grounding (TAG) task, which interactively considers the relationship between audio pro","authors_text":"Heinrich Dinkel, Kai Yu, Mengyue Wu, Xuenan Xu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T03:44:14Z","title":"Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11474","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":"sha256:24166fd6f91dec12d8518ef96712348e3e0dc39dc6933ef8b7a34db6844b30c9","target":"record","created_at":"2026-07-05T02:17:11Z","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":"17ce4fab4248b9920aed46e58351c2567b2537bd7dc14d044cf2555175e22fa8","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-02-23T03:44:14Z","title_canon_sha256":"e84087c505e3a122f9b32f9fd0b96a44880c6a1d1eafdc0deff0f9f1cdfa46f5"},"schema_version":"1.0","source":{"id":"2102.11474","kind":"arxiv","version":1}},"canonical_sha256":"4db6b9f37f6aea720f0b5167eb523495e97dda04dbee03b65b799433ddbb66bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4db6b9f37f6aea720f0b5167eb523495e97dda04dbee03b65b799433ddbb66bf","first_computed_at":"2026-07-05T02:17:11.903106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:11.903106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1rhnvcKsNsNUU+og7LnHbTZVfS+Cl/+OwYqQljGnS2N8XN+DiOza4klF4ub0+4LDuIa67x1pBedTn9wDskNnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:11.903527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.11474","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24166fd6f91dec12d8518ef96712348e3e0dc39dc6933ef8b7a34db6844b30c9","sha256:125d93b39d7b3ac5e1c61c5de857952b9594a9031719c3297f38b38de422fb05"],"state_sha256":"89a2b2c578076a7e8717e99599d23ca1c768c7fbe97c26a0f1f563f7761b8f18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SM/cxTwxq3Xjqwylg4l/c/HWVQmLPM8E8UgWvgNMlAItzMLGs4C7gQvyxip6vfAa1ZxIm4g/8EoOtxtMJXxWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T02:07:41.800458Z","bundle_sha256":"d2feb53796ed30ff6f7bc39983c519f746a0f51777e8f5e76d51711207b066c6"}}