{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XG6EDZST7YRUV7MIWVZAMLAZGM","short_pith_number":"pith:XG6EDZST","canonical_record":{"source":{"id":"2404.17806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-27T07:05:48Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"9c1ce455e72904fdada42586c198e757215d496404c711abc50d8699d86a512d","abstract_canon_sha256":"f7929be12dc0ae7d191a00cced180d848ce81eea847ac95e71072be35d3616d1"},"schema_version":"1.0"},"canonical_sha256":"b9bc41e653fe234afd88b572062c1933354509a1a8495f320d57c18575db6d62","source":{"kind":"arxiv","id":"2404.17806","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17806","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17806v1","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17806","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"XG6EDZST7YRU","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"XG6EDZST7YRUV7MI","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"XG6EDZST","created_at":"2026-07-05T08:13:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XG6EDZST7YRUV7MIWVZAMLAZGM","target":"record","payload":{"canonical_record":{"source":{"id":"2404.17806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-27T07:05:48Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"title_canon_sha256":"9c1ce455e72904fdada42586c198e757215d496404c711abc50d8699d86a512d","abstract_canon_sha256":"f7929be12dc0ae7d191a00cced180d848ce81eea847ac95e71072be35d3616d1"},"schema_version":"1.0"},"canonical_sha256":"b9bc41e653fe234afd88b572062c1933354509a1a8495f320d57c18575db6d62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:14.664401Z","signature_b64":"xt57X9mmJOsPi4KkVYPNhRqpPlzQ+luPkfzXpbYjLqhdOENzpsNoWhrFIHe7VuM2dGKLv/LDHgfEIeexBVR3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9bc41e653fe234afd88b572062c1933354509a1a8495f320d57c18575db6d62","last_reissued_at":"2026-07-05T08:13:14.664003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:14.664003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.17806","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":"2026-07-05T08:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wn7wfefbEY90/y7IzN3XJeKZSHcSyDkU048i+QRCH5y+mVIcffvzAaqK6xEsULYZs1UILseva0jnN14Nx0xGCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:56:41.082267Z"},"content_sha256":"f4daf8d394120efd6582ab78cb7a0359c735100a23360becfcb26237df26f008","schema_version":"1.0","event_id":"sha256:f4daf8d394120efd6582ab78cb7a0359c735100a23360becfcb26237df26f008"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XG6EDZST7YRUV7MIWVZAMLAZGM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dongya Jia, Haohe Liu, Mark D. Plumbley, Wenwu Wang, Xubo Liu, Xuenan Xu, Yi Yuan, Yuanzhe Chen, Zhuo Chen","submitted_at":"2024-04-27T07:05:48Z","abstract_excerpt":"Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal information within audio and text features, presenting substantial limitations for tasks such as audio retrieval and generation. To address this gap, we introduce T-CLAP, a temporal-enhanced CLAP model. We use Large Language Models~(LLMs) and mixed-up strategies to generate temporal-contrastive captions for audio clips from extensive audio-text datasets. Su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17806","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/2404.17806/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":"2026-07-05T08:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yp//wdwjLw8Wf1oXQBxe7MfMZ6KSbw95qXZGGvQYJyUQtrigwFbdhL+/p8k8vjbdJ6Nen0GDL34mNHL1qfs8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:56:41.082672Z"},"content_sha256":"1ac8a4228344ef2f9c1dba293f300d682bef126114cbe159cc20996d92831e62","schema_version":"1.0","event_id":"sha256:1ac8a4228344ef2f9c1dba293f300d682bef126114cbe159cc20996d92831e62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XG6EDZST7YRUV7MIWVZAMLAZGM/bundle.json","state_url":"https://pith.science/pith/XG6EDZST7YRUV7MIWVZAMLAZGM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XG6EDZST7YRUV7MIWVZAMLAZGM/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":"2026-07-07T14:56:41Z","links":{"resolver":"https://pith.science/pith/XG6EDZST7YRUV7MIWVZAMLAZGM","bundle":"https://pith.science/pith/XG6EDZST7YRUV7MIWVZAMLAZGM/bundle.json","state":"https://pith.science/pith/XG6EDZST7YRUV7MIWVZAMLAZGM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XG6EDZST7YRUV7MIWVZAMLAZGM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XG6EDZST7YRUV7MIWVZAMLAZGM","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":"f7929be12dc0ae7d191a00cced180d848ce81eea847ac95e71072be35d3616d1","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-27T07:05:48Z","title_canon_sha256":"9c1ce455e72904fdada42586c198e757215d496404c711abc50d8699d86a512d"},"schema_version":"1.0","source":{"id":"2404.17806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17806","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17806v1","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17806","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"XG6EDZST7YRU","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"pith_short_16","alias_value":"XG6EDZST7YRUV7MI","created_at":"2026-07-05T08:13:14Z"},{"alias_kind":"pith_short_8","alias_value":"XG6EDZST","created_at":"2026-07-05T08:13:14Z"}],"graph_snapshots":[{"event_id":"sha256:1ac8a4228344ef2f9c1dba293f300d682bef126114cbe159cc20996d92831e62","target":"graph","created_at":"2026-07-05T08:13:14Z","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/2404.17806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive language-audio pretraining~(CLAP) has been developed to align the representations of audio and language, achieving remarkable performance in retrieval and classification tasks. However, current CLAP struggles to capture temporal information within audio and text features, presenting substantial limitations for tasks such as audio retrieval and generation. To address this gap, we introduce T-CLAP, a temporal-enhanced CLAP model. We use Large Language Models~(LLMs) and mixed-up strategies to generate temporal-contrastive captions for audio clips from extensive audio-text datasets. Su","authors_text":"Dongya Jia, Haohe Liu, Mark D. Plumbley, Wenwu Wang, Xubo Liu, Xuenan Xu, Yi Yuan, Yuanzhe Chen, Zhuo Chen","cross_cats":["cs.CL","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-27T07:05:48Z","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17806","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:f4daf8d394120efd6582ab78cb7a0359c735100a23360becfcb26237df26f008","target":"record","created_at":"2026-07-05T08:13:14Z","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":"f7929be12dc0ae7d191a00cced180d848ce81eea847ac95e71072be35d3616d1","cross_cats_sorted":["cs.CL","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-04-27T07:05:48Z","title_canon_sha256":"9c1ce455e72904fdada42586c198e757215d496404c711abc50d8699d86a512d"},"schema_version":"1.0","source":{"id":"2404.17806","kind":"arxiv","version":1}},"canonical_sha256":"b9bc41e653fe234afd88b572062c1933354509a1a8495f320d57c18575db6d62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9bc41e653fe234afd88b572062c1933354509a1a8495f320d57c18575db6d62","first_computed_at":"2026-07-05T08:13:14.664003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:14.664003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xt57X9mmJOsPi4KkVYPNhRqpPlzQ+luPkfzXpbYjLqhdOENzpsNoWhrFIHe7VuM2dGKLv/LDHgfEIeexBVR3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:14.664401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4daf8d394120efd6582ab78cb7a0359c735100a23360becfcb26237df26f008","sha256:1ac8a4228344ef2f9c1dba293f300d682bef126114cbe159cc20996d92831e62"],"state_sha256":"9db2ae3fa2147b646d555f63705795421929111cdd5d108bd9bec2dbead81656"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nu72P7gKW5N7Tz9E14H62bzyucsA2+W2wUgcPZRRpwpuht8ZeycvAbIACTPiA+HHMzJlC6IZRpJuIdEvS0VSDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:56:41.084562Z","bundle_sha256":"19df85b62e41b75d20eb9dd08c668d5101925396142d1944501674a094aa8038"}}