{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DWI7DCECSTUTJL7JZW26DTZMBO","short_pith_number":"pith:DWI7DCEC","canonical_record":{"source":{"id":"2202.00182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-01T02:06:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e213be023058eb0e9acdb606a1736d86ae77ee6c79adbc2f010cf935aa5c06d0","abstract_canon_sha256":"cd7bab981a880aae4c8f32ab640846ae3fd9b17c7fe42299ab8157b24ed943db"},"schema_version":"1.0"},"canonical_sha256":"1d91f1888294e934afe9cdb5e1cf2c0b83cb7da784d3e2db72ab62b5fb28ed82","source":{"kind":"arxiv","id":"2202.00182","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00182","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00182v3","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00182","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"DWI7DCECSTUT","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"DWI7DCECSTUTJL7J","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"DWI7DCEC","created_at":"2026-07-05T05:48:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DWI7DCECSTUTJL7JZW26DTZMBO","target":"record","payload":{"canonical_record":{"source":{"id":"2202.00182","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-01T02:06:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e213be023058eb0e9acdb606a1736d86ae77ee6c79adbc2f010cf935aa5c06d0","abstract_canon_sha256":"cd7bab981a880aae4c8f32ab640846ae3fd9b17c7fe42299ab8157b24ed943db"},"schema_version":"1.0"},"canonical_sha256":"1d91f1888294e934afe9cdb5e1cf2c0b83cb7da784d3e2db72ab62b5fb28ed82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:32.180404Z","signature_b64":"PsC8eI6HzNHqOWk3EWa6bN55gBjEF+l9cM6mgteXGzLOwW8lH2IZhk4AVgmiWbtntJ/NxfXsqcl/KeP46sGTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d91f1888294e934afe9cdb5e1cf2c0b83cb7da784d3e2db72ab62b5fb28ed82","last_reissued_at":"2026-07-05T05:48:32.179964Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:32.179964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.00182","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/De5TcQG6NVCycIq7OVgEeADEX+q/T7N3Yey+I/n3sD2nKwQUGWmLrG0iVOunAhcM9s3R1WJbz1G/MX5JSGzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:13:40.630935Z"},"content_sha256":"40091ee77f562da5f78dcea182ba9bfe84d3eccef3e7eacae10dec3024a1f606","schema_version":"1.0","event_id":"sha256:40091ee77f562da5f78dcea182ba9bfe84d3eccef3e7eacae10dec3024a1f606"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DWI7DCECSTUTJL7JZW26DTZMBO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised 3D Object Detection via Temporal Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"David Held, Haiming Gang, Jianren Wang, Siddharth Ancha, Yi-Ting Chen","submitted_at":"2022-02-01T02:06:54Z","abstract_excerpt":"3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks. Our insight is that temporal smoothing can create more accurate detection results on unlabeled data, and these smoothed detections can then be used to retrain the detector. We learn to perform this tempo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00182","kind":"arxiv","version":3},"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/2202.00182/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":"2026-07-05T05:48:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ClGP4twg3QsUvJz0FItqa6kbkpAZ6tw+dKz+53G3ndkMoVXobXmmfR+n137odUElb2nl4kOQkgz++BTd8qwdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:13:40.631308Z"},"content_sha256":"0b4cd3db8c4d1cae02a0c41d15a2c425c53c5e348e5c379dad2e972b083ed31c","schema_version":"1.0","event_id":"sha256:0b4cd3db8c4d1cae02a0c41d15a2c425c53c5e348e5c379dad2e972b083ed31c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DWI7DCECSTUTJL7JZW26DTZMBO/bundle.json","state_url":"https://pith.science/pith/DWI7DCECSTUTJL7JZW26DTZMBO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DWI7DCECSTUTJL7JZW26DTZMBO/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":"2026-07-06T16:13:40Z","links":{"resolver":"https://pith.science/pith/DWI7DCECSTUTJL7JZW26DTZMBO","bundle":"https://pith.science/pith/DWI7DCECSTUTJL7JZW26DTZMBO/bundle.json","state":"https://pith.science/pith/DWI7DCECSTUTJL7JZW26DTZMBO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DWI7DCECSTUTJL7JZW26DTZMBO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DWI7DCECSTUTJL7JZW26DTZMBO","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":"cd7bab981a880aae4c8f32ab640846ae3fd9b17c7fe42299ab8157b24ed943db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-01T02:06:54Z","title_canon_sha256":"e213be023058eb0e9acdb606a1736d86ae77ee6c79adbc2f010cf935aa5c06d0"},"schema_version":"1.0","source":{"id":"2202.00182","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00182","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00182v3","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00182","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"pith_short_12","alias_value":"DWI7DCECSTUT","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"pith_short_16","alias_value":"DWI7DCECSTUTJL7J","created_at":"2026-07-05T05:48:32Z"},{"alias_kind":"pith_short_8","alias_value":"DWI7DCEC","created_at":"2026-07-05T05:48:32Z"}],"graph_snapshots":[{"event_id":"sha256:0b4cd3db8c4d1cae02a0c41d15a2c425c53c5e348e5c379dad2e972b083ed31c","target":"graph","created_at":"2026-07-05T05:48:32Z","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/2202.00182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"3D object detection plays an important role in autonomous driving and other robotics applications. However, these detectors usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging large amounts of unlabeled point cloud videos by semi-supervised learning of 3D object detectors via temporal graph neural networks. Our insight is that temporal smoothing can create more accurate detection results on unlabeled data, and these smoothed detections can then be used to retrain the detector. We learn to perform this tempo","authors_text":"David Held, Haiming Gang, Jianren Wang, Siddharth Ancha, Yi-Ting Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-01T02:06:54Z","title":"Semi-supervised 3D Object Detection via Temporal Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00182","kind":"arxiv","version":3},"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":"sha256:40091ee77f562da5f78dcea182ba9bfe84d3eccef3e7eacae10dec3024a1f606","target":"record","created_at":"2026-07-05T05:48:32Z","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":"cd7bab981a880aae4c8f32ab640846ae3fd9b17c7fe42299ab8157b24ed943db","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-01T02:06:54Z","title_canon_sha256":"e213be023058eb0e9acdb606a1736d86ae77ee6c79adbc2f010cf935aa5c06d0"},"schema_version":"1.0","source":{"id":"2202.00182","kind":"arxiv","version":3}},"canonical_sha256":"1d91f1888294e934afe9cdb5e1cf2c0b83cb7da784d3e2db72ab62b5fb28ed82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d91f1888294e934afe9cdb5e1cf2c0b83cb7da784d3e2db72ab62b5fb28ed82","first_computed_at":"2026-07-05T05:48:32.179964Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:32.179964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PsC8eI6HzNHqOWk3EWa6bN55gBjEF+l9cM6mgteXGzLOwW8lH2IZhk4AVgmiWbtntJ/NxfXsqcl/KeP46sGTCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:32.180404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00182","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40091ee77f562da5f78dcea182ba9bfe84d3eccef3e7eacae10dec3024a1f606","sha256:0b4cd3db8c4d1cae02a0c41d15a2c425c53c5e348e5c379dad2e972b083ed31c"],"state_sha256":"edb36ea91752d9911693260f6c27539b963c507b224a4d688f3a06d1c1fa0bdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcK7ExRVIsb48dExGuMUziDIce+c3LS2yxsAF8n3IyheZPV3mEjFfbFAIjNTlzy1FcmB3gZaqnJNBc0LtmZTCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:13:40.633195Z","bundle_sha256":"d24af5da150fce2d64789501f7e1288f7c0b357d5d326b00c86a1a48f24a186a"}}