{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ETDH4Q674DPG6DQEYFJ6SWAD2I","short_pith_number":"pith:ETDH4Q67","canonical_record":{"source":{"id":"2309.11500","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-20T17:59:32Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"a521e70c677a80adb41b542a0f3ad94811a57793c707a1488835da0ace3cc69a","abstract_canon_sha256":"98126eadfcc095a577efe1da9144b73298c51fdf3c393770025de7d378115c40"},"schema_version":"1.0"},"canonical_sha256":"24c67e43dfe0de6f0e04c153e95803d23aca07964481cc5e8e96d96480992012","source":{"kind":"arxiv","id":"2309.11500","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11500","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11500v4","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11500","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"ETDH4Q674DPG","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"ETDH4Q674DPG6DQE","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"ETDH4Q67","created_at":"2026-07-05T09:04:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ETDH4Q674DPG6DQEYFJ6SWAD2I","target":"record","payload":{"canonical_record":{"source":{"id":"2309.11500","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-20T17:59:32Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"a521e70c677a80adb41b542a0f3ad94811a57793c707a1488835da0ace3cc69a","abstract_canon_sha256":"98126eadfcc095a577efe1da9144b73298c51fdf3c393770025de7d378115c40"},"schema_version":"1.0"},"canonical_sha256":"24c67e43dfe0de6f0e04c153e95803d23aca07964481cc5e8e96d96480992012","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:29.458126Z","signature_b64":"Th9E31N7Eh1E/78FqBQAq1n1rFyu3ZudVuDZo93n7mTWQajlQg2Q+cjNp4xyROi8yqXWZX7EEm7q0gMVAqIaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24c67e43dfe0de6f0e04c153e95803d23aca07964481cc5e8e96d96480992012","last_reissued_at":"2026-07-05T09:04:29.457661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:29.457661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.11500","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cQAc7esEYZB4AJycA4Bt0bfPOoWRiHd3E4th2b4VL0Lzr/RO39WHxI42euFIsI8+psPVvkitUoITS7aX42MgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T01:42:05.246998Z"},"content_sha256":"f8b276ae6b19e63355b89a21c39bf048c64aceda538acd3ff9afdbcfa212cae0","schema_version":"1.0","event_id":"sha256:f8b276ae6b19e63355b89a21c39bf048c64aceda538acd3ff9afdbcfa212cae0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ETDH4Q674DPG6DQEYFJ6SWAD2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Luoyi Sun, Mengyue Wu, Weidi Xie, Xuenan Xu","submitted_at":"2023-09-20T17:59:32Z","abstract_excerpt":"Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learning, existing datasets suffer from limitations in the following aspects: insufficient volume, simplistic content, and arduous collection procedures. To establish an audio dataset with high-quality captions, we propose an innovative, automatic approach leveraging multimodal inputs, such as video frames, audio streams. Specifically, we construct a large-scale, high-quality, audio-language dataset, named as Auto-ACD, co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11500","kind":"arxiv","version":4},"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/2309.11500/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":"2026-07-05T09:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8hu/Irrd5yHKYAz73x+PsrXqob1C8czQdR2Z4JkKh4tA6zH8ZcNPOa3SB7HZTY7MWF0QNqXD7fjuQo1+L7UECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T01:42:05.247428Z"},"content_sha256":"d28167221602555505caa1b86d36234a0b0c8dfb4ab588f16eafdf118afa4d54","schema_version":"1.0","event_id":"sha256:d28167221602555505caa1b86d36234a0b0c8dfb4ab588f16eafdf118afa4d54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I/bundle.json","state_url":"https://pith.science/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I/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":"2026-07-10T01:42:05Z","links":{"resolver":"https://pith.science/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I","bundle":"https://pith.science/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I/bundle.json","state":"https://pith.science/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETDH4Q674DPG6DQEYFJ6SWAD2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ETDH4Q674DPG6DQEYFJ6SWAD2I","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":"98126eadfcc095a577efe1da9144b73298c51fdf3c393770025de7d378115c40","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-20T17:59:32Z","title_canon_sha256":"a521e70c677a80adb41b542a0f3ad94811a57793c707a1488835da0ace3cc69a"},"schema_version":"1.0","source":{"id":"2309.11500","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11500","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11500v4","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11500","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"ETDH4Q674DPG","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"ETDH4Q674DPG6DQE","created_at":"2026-07-05T09:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"ETDH4Q67","created_at":"2026-07-05T09:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:d28167221602555505caa1b86d36234a0b0c8dfb4ab588f16eafdf118afa4d54","target":"graph","created_at":"2026-07-05T09:04:29Z","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/2309.11500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learning, existing datasets suffer from limitations in the following aspects: insufficient volume, simplistic content, and arduous collection procedures. To establish an audio dataset with high-quality captions, we propose an innovative, automatic approach leveraging multimodal inputs, such as video frames, audio streams. Specifically, we construct a large-scale, high-quality, audio-language dataset, named as Auto-ACD, co","authors_text":"Luoyi Sun, Mengyue Wu, Weidi Xie, Xuenan Xu","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-20T17:59:32Z","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11500","kind":"arxiv","version":4},"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:f8b276ae6b19e63355b89a21c39bf048c64aceda538acd3ff9afdbcfa212cae0","target":"record","created_at":"2026-07-05T09:04:29Z","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":"98126eadfcc095a577efe1da9144b73298c51fdf3c393770025de7d378115c40","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-09-20T17:59:32Z","title_canon_sha256":"a521e70c677a80adb41b542a0f3ad94811a57793c707a1488835da0ace3cc69a"},"schema_version":"1.0","source":{"id":"2309.11500","kind":"arxiv","version":4}},"canonical_sha256":"24c67e43dfe0de6f0e04c153e95803d23aca07964481cc5e8e96d96480992012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24c67e43dfe0de6f0e04c153e95803d23aca07964481cc5e8e96d96480992012","first_computed_at":"2026-07-05T09:04:29.457661Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:29.457661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Th9E31N7Eh1E/78FqBQAq1n1rFyu3ZudVuDZo93n7mTWQajlQg2Q+cjNp4xyROi8yqXWZX7EEm7q0gMVAqIaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:29.458126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11500","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8b276ae6b19e63355b89a21c39bf048c64aceda538acd3ff9afdbcfa212cae0","sha256:d28167221602555505caa1b86d36234a0b0c8dfb4ab588f16eafdf118afa4d54"],"state_sha256":"f7d40dc374974004fb190cdcb539010a13ad680c243b9715f02458deb22f5963"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZLs6xPzsQCEblp+2UlZn7/BayBfpei3x+oMb4/PmVuIPuA4fZORa68b6qa1Xpl9Jtl2utaSfzCFtb1dnDw7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T01:42:05.249492Z","bundle_sha256":"cb2b675eb396c4879a628b44499ab740b109c447941a421d8a32281bf4376f1b"}}