{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HGVMQSWGVCBY3D4OLG7KP5IWFH","short_pith_number":"pith:HGVMQSWG","canonical_record":{"source":{"id":"2307.15167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-07-27T19:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"26820a375af54b0f898defd622697c5cce7551b67344a14bf59eb700690a3c60","abstract_canon_sha256":"9a152e185eb8e87cc5bdfab82433a59cab8c3b3ee6b581e3ccb24f64d79134c8"},"schema_version":"1.0"},"canonical_sha256":"39aac84ac6a8838d8f8e59bea7f51629c94284493c340fb9ba8ba6ab069130f7","source":{"kind":"arxiv","id":"2307.15167","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15167","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15167v1","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15167","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"pith_short_12","alias_value":"HGVMQSWGVCBY","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"pith_short_16","alias_value":"HGVMQSWGVCBY3D4O","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"pith_short_8","alias_value":"HGVMQSWG","created_at":"2026-07-05T06:35:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HGVMQSWGVCBY3D4OLG7KP5IWFH","target":"record","payload":{"canonical_record":{"source":{"id":"2307.15167","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-07-27T19:56:02Z","cross_cats_sorted":[],"title_canon_sha256":"26820a375af54b0f898defd622697c5cce7551b67344a14bf59eb700690a3c60","abstract_canon_sha256":"9a152e185eb8e87cc5bdfab82433a59cab8c3b3ee6b581e3ccb24f64d79134c8"},"schema_version":"1.0"},"canonical_sha256":"39aac84ac6a8838d8f8e59bea7f51629c94284493c340fb9ba8ba6ab069130f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:31.192371Z","signature_b64":"0OO8qBMUkPGU8wR2RTNJ8R4lsYjERYVlJ6wRilpsYhklKv4Q68JE9GwsoGYL6WmSUi9xLyaBeZlexXu/PM90BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39aac84ac6a8838d8f8e59bea7f51629c94284493c340fb9ba8ba6ab069130f7","last_reissued_at":"2026-07-05T06:35:31.191763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:31.191763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.15167","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":"2026-07-05T06:35:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZSxqNd7HXUdcKM6r71YCxPcNsvy4eaOv2hCFDHpii/Tt2kZhnR4LwNvWrPI0QukNsD2Vw43OUuXPYErfkGh0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:21:09.107011Z"},"content_sha256":"81734ae090e74c3faf4c9b38af0f7abefc4c592a40374b15d33840ca2a25037d","schema_version":"1.0","event_id":"sha256:81734ae090e74c3faf4c9b38af0f7abefc4c592a40374b15d33840ca2a25037d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HGVMQSWGVCBY3D4OLG7KP5IWFH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PEANUT: A Human-AI Collaborative Tool for Annotating Audio-Visual Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Chenliang Xu, Toby Jia-Jun Li, Yapeng Tian, Zheng Ning, Zheng Zhang","submitted_at":"2023-07-27T19:56:02Z","abstract_excerpt":"Audio-visual learning seeks to enhance the computer's multi-modal perception leveraging the correlation between the auditory and visual modalities. Despite their many useful downstream tasks, such as video retrieval, AR/VR, and accessibility, the performance and adoption of existing audio-visual models have been impeded by the availability of high-quality datasets. Annotating audio-visual datasets is laborious, expensive, and time-consuming. To address this challenge, we designed and developed an efficient audio-visual annotation tool called Peanut. Peanut's human-AI collaborative pipeline sep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15167","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/2307.15167/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":"2026-07-05T06:35:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NosBPop52HNXL39Pv3OmnCVrOum2jTd7uNlzE4+0Ibnbv2qgRKCOQ2SKiRu3P7bTfqYbF7bz2sSLIOwkC5JPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T19:21:09.107518Z"},"content_sha256":"4760f22d6f52082a1b47b46e0f025339d2a69c60c10dd56618bf3341ee1903ab","schema_version":"1.0","event_id":"sha256:4760f22d6f52082a1b47b46e0f025339d2a69c60c10dd56618bf3341ee1903ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH/bundle.json","state_url":"https://pith.science/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH/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":"2026-08-04T19:21:09Z","links":{"resolver":"https://pith.science/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH","bundle":"https://pith.science/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH/bundle.json","state":"https://pith.science/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HGVMQSWGVCBY3D4OLG7KP5IWFH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HGVMQSWGVCBY3D4OLG7KP5IWFH","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":"9a152e185eb8e87cc5bdfab82433a59cab8c3b3ee6b581e3ccb24f64d79134c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-07-27T19:56:02Z","title_canon_sha256":"26820a375af54b0f898defd622697c5cce7551b67344a14bf59eb700690a3c60"},"schema_version":"1.0","source":{"id":"2307.15167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15167","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15167v1","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15167","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"pith_short_12","alias_value":"HGVMQSWGVCBY","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"pith_short_16","alias_value":"HGVMQSWGVCBY3D4O","created_at":"2026-07-05T06:35:31Z"},{"alias_kind":"pith_short_8","alias_value":"HGVMQSWG","created_at":"2026-07-05T06:35:31Z"}],"graph_snapshots":[{"event_id":"sha256:4760f22d6f52082a1b47b46e0f025339d2a69c60c10dd56618bf3341ee1903ab","target":"graph","created_at":"2026-07-05T06:35:31Z","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/2307.15167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual learning seeks to enhance the computer's multi-modal perception leveraging the correlation between the auditory and visual modalities. Despite their many useful downstream tasks, such as video retrieval, AR/VR, and accessibility, the performance and adoption of existing audio-visual models have been impeded by the availability of high-quality datasets. Annotating audio-visual datasets is laborious, expensive, and time-consuming. To address this challenge, we designed and developed an efficient audio-visual annotation tool called Peanut. Peanut's human-AI collaborative pipeline sep","authors_text":"Chenliang Xu, Toby Jia-Jun Li, Yapeng Tian, Zheng Ning, Zheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-07-27T19:56:02Z","title":"PEANUT: A Human-AI Collaborative Tool for Annotating Audio-Visual Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15167","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":"sha256:81734ae090e74c3faf4c9b38af0f7abefc4c592a40374b15d33840ca2a25037d","target":"record","created_at":"2026-07-05T06:35:31Z","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":"9a152e185eb8e87cc5bdfab82433a59cab8c3b3ee6b581e3ccb24f64d79134c8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2023-07-27T19:56:02Z","title_canon_sha256":"26820a375af54b0f898defd622697c5cce7551b67344a14bf59eb700690a3c60"},"schema_version":"1.0","source":{"id":"2307.15167","kind":"arxiv","version":1}},"canonical_sha256":"39aac84ac6a8838d8f8e59bea7f51629c94284493c340fb9ba8ba6ab069130f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39aac84ac6a8838d8f8e59bea7f51629c94284493c340fb9ba8ba6ab069130f7","first_computed_at":"2026-07-05T06:35:31.191763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:31.191763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0OO8qBMUkPGU8wR2RTNJ8R4lsYjERYVlJ6wRilpsYhklKv4Q68JE9GwsoGYL6WmSUi9xLyaBeZlexXu/PM90BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:31.192371Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81734ae090e74c3faf4c9b38af0f7abefc4c592a40374b15d33840ca2a25037d","sha256:4760f22d6f52082a1b47b46e0f025339d2a69c60c10dd56618bf3341ee1903ab"],"state_sha256":"d15b7ad3e9cef50ed79e80ab52b96dcbd1891f0a8fe53f7b5f8693407ccaee01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvDFFQjC5jvMJDPtkqbNMDVaMCFxFYJnP7dPGyh8SIeIaWD15oPz86omfuKgITeZQCHQgbl9+AfzMSS4WG9NBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T19:21:09.112276Z","bundle_sha256":"413ce7f70d9e6fbd994f187f486b332d1fc81a66786aa0e6efb02051fae608e3"}}