{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:5X7GN4FTZ7EMKOO5D7M26NA2FJ","short_pith_number":"pith:5X7GN4FT","canonical_record":{"source":{"id":"2211.11983","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T03:35:15Z","cross_cats_sorted":[],"title_canon_sha256":"18ded8b6b09ae10897732c3419a28ba46b93ff55d48a77ac6f8dd67040c2713f","abstract_canon_sha256":"f2435192054647c6a2589f718af092e691e4fd5ea1f44586b9047a4af9954882"},"schema_version":"1.0"},"canonical_sha256":"edfe66f0b3cfc8c539dd1fd9af341a2a51406a14ba52a82ab3208bcbeac4fef7","source":{"kind":"arxiv","id":"2211.11983","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11983","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11983v1","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11983","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"5X7GN4FTZ7EM","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"5X7GN4FTZ7EMKOO5","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"5X7GN4FT","created_at":"2026-07-05T05:18:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:5X7GN4FTZ7EMKOO5D7M26NA2FJ","target":"record","payload":{"canonical_record":{"source":{"id":"2211.11983","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T03:35:15Z","cross_cats_sorted":[],"title_canon_sha256":"18ded8b6b09ae10897732c3419a28ba46b93ff55d48a77ac6f8dd67040c2713f","abstract_canon_sha256":"f2435192054647c6a2589f718af092e691e4fd5ea1f44586b9047a4af9954882"},"schema_version":"1.0"},"canonical_sha256":"edfe66f0b3cfc8c539dd1fd9af341a2a51406a14ba52a82ab3208bcbeac4fef7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:11.521568Z","signature_b64":"LVoU+cWMcEeIYv1biIcvUxOjtbCcVDs4Cc3AAywl7g47L9FA96nrwYNFwYu6YBtSKV49U6dVvAXZVFTBvSXQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edfe66f0b3cfc8c539dd1fd9af341a2a51406a14ba52a82ab3208bcbeac4fef7","last_reissued_at":"2026-07-05T05:18:11.521095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:11.521095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.11983","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":"2026-07-05T05:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YUg+XXUlJyPWk5jB6plH3+9Tk5PMlV9GUVfRkq1onQvbHD+KtVWRqxds/OE91MWEgKM1jYsEDBDtedfap+foCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:03:30.776077Z"},"content_sha256":"073a3e8151de2ea1513ca74dd96e3b526c15e1e61bbc0489e852ef90422de1a5","schema_version":"1.0","event_id":"sha256:073a3e8151de2ea1513ca74dd96e3b526c15e1e61bbc0489e852ef90422de1a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:5X7GN4FTZ7EMKOO5D7M26NA2FJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongmei Fu, Jianlong Fu, Kai Qiu, Zhongwei Qiu","submitted_at":"2022-11-22T03:35:15Z","abstract_excerpt":"Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. However, existing 3D datasets lack diversity, which limits the performance of current methods and their generalization ability. Although existing methods utilize 2D pose annotations to help 3D pose estimation, they mainly focus on extracting 2D structural constraints from 2D poses, ignoring the 3D information hidden in the images. In this paper, we propose a novel method to extract weak 3D information directly from 2D images without 3D pose supervision. Firstly, we utilize 2D pose annotations and pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11983","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/2211.11983/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":"2026-07-05T05:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/hF3YvKIiV0ndKkMNO5P9VTs4+gIevfLsill7I3W8NKFOYzUg58hsTUQ5r1x7tbnT/ZLSTnpIzkZ4XASNyFCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:03:30.776658Z"},"content_sha256":"86600f74cdf0185219e5ca9b118fbaefca365ddc3c8b52dc1e781c89f0f3410d","schema_version":"1.0","event_id":"sha256:86600f74cdf0185219e5ca9b118fbaefca365ddc3c8b52dc1e781c89f0f3410d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ/bundle.json","state_url":"https://pith.science/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ/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":"2026-08-05T05:03:30Z","links":{"resolver":"https://pith.science/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ","bundle":"https://pith.science/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ/bundle.json","state":"https://pith.science/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5X7GN4FTZ7EMKOO5D7M26NA2FJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5X7GN4FTZ7EMKOO5D7M26NA2FJ","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":"f2435192054647c6a2589f718af092e691e4fd5ea1f44586b9047a4af9954882","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T03:35:15Z","title_canon_sha256":"18ded8b6b09ae10897732c3419a28ba46b93ff55d48a77ac6f8dd67040c2713f"},"schema_version":"1.0","source":{"id":"2211.11983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.11983","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2211.11983v1","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11983","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"5X7GN4FTZ7EM","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"5X7GN4FTZ7EMKOO5","created_at":"2026-07-05T05:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"5X7GN4FT","created_at":"2026-07-05T05:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:86600f74cdf0185219e5ca9b118fbaefca365ddc3c8b52dc1e781c89f0f3410d","target":"graph","created_at":"2026-07-05T05:18:11Z","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/2211.11983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. However, existing 3D datasets lack diversity, which limits the performance of current methods and their generalization ability. Although existing methods utilize 2D pose annotations to help 3D pose estimation, they mainly focus on extracting 2D structural constraints from 2D poses, ignoring the 3D information hidden in the images. In this paper, we propose a novel method to extract weak 3D information directly from 2D images without 3D pose supervision. Firstly, we utilize 2D pose annotations and pe","authors_text":"Dongmei Fu, Jianlong Fu, Kai Qiu, Zhongwei Qiu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T03:35:15Z","title":"Weakly-supervised Pre-training for 3D Human Pose Estimation via Perspective Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11983","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":"sha256:073a3e8151de2ea1513ca74dd96e3b526c15e1e61bbc0489e852ef90422de1a5","target":"record","created_at":"2026-07-05T05:18:11Z","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":"f2435192054647c6a2589f718af092e691e4fd5ea1f44586b9047a4af9954882","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-22T03:35:15Z","title_canon_sha256":"18ded8b6b09ae10897732c3419a28ba46b93ff55d48a77ac6f8dd67040c2713f"},"schema_version":"1.0","source":{"id":"2211.11983","kind":"arxiv","version":1}},"canonical_sha256":"edfe66f0b3cfc8c539dd1fd9af341a2a51406a14ba52a82ab3208bcbeac4fef7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edfe66f0b3cfc8c539dd1fd9af341a2a51406a14ba52a82ab3208bcbeac4fef7","first_computed_at":"2026-07-05T05:18:11.521095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:18:11.521095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVoU+cWMcEeIYv1biIcvUxOjtbCcVDs4Cc3AAywl7g47L9FA96nrwYNFwYu6YBtSKV49U6dVvAXZVFTBvSXQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:18:11.521568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.11983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:073a3e8151de2ea1513ca74dd96e3b526c15e1e61bbc0489e852ef90422de1a5","sha256:86600f74cdf0185219e5ca9b118fbaefca365ddc3c8b52dc1e781c89f0f3410d"],"state_sha256":"959df87d0c3c0ca7ac55f058c1a1c5fe2285983eda29e376975fd94838545f27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvETdh8oN9YR062mXkJr651ZqbN4LyEcZW99p4QzZ1lYqgmple6nEO8qi0mna4sqq5NTjyAJGJQX5lFWESJoCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:03:30.781838Z","bundle_sha256":"c99be454dbe63670784612056f696db8d87627d8a4919e29eac90817b4b9464e"}}