{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6LYCMLVYK3LSBWO5HLCQXC26WZ","short_pith_number":"pith:6LYCMLVY","schema_version":"1.0","canonical_sha256":"f2f0262eb856d720d9dd3ac50b8b5eb655ed5fd530a779dc3dbe5c5cb50b1a63","source":{"kind":"arxiv","id":"2506.14596","version":1},"attestation_state":"computed","paper":{"title":"PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ming Xu, Xu Zhang","submitted_at":"2025-06-17T14:59:56Z","abstract_excerpt":"Existing monocular 3D pose estimation methods primarily rely on joint positional features, while overlooking intrinsic directional and angular correlations within the skeleton. As a result, they often produce implausible poses under joint occlusions or rapid motion changes. To address these challenges, we propose the PoseGRAF framework. We first construct a dual graph convolutional structure that separately processes joint and bone graphs, effectively capturing their local dependencies. A Cross-Attention module is then introduced to model interdependencies between bone directions and joint fea"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.14596","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-17T14:59:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7078242ebc3d0dc144faa6862e2308ef72c9660228f5da0d56aa7c8aa4c8064c","abstract_canon_sha256":"9daf9bb82987a4d422c2ea1bca03b8c60d9dcc7ae6047621a88a06ec0a61a3e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:59.459226Z","signature_b64":"BIGnOcRxRINWBKnFl/1Od45xZl7CX8guCCKeOlJcmLGPqoSQV4IC4AGp2KzGq4NaKnEq/M/VIudddm0OT3DBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2f0262eb856d720d9dd3ac50b8b5eb655ed5fd530a779dc3dbe5c5cb50b1a63","last_reissued_at":"2026-07-05T11:22:59.458741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:59.458741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PoseGRAF: Geometric-Reinforced Adaptive Fusion for Monocular 3D Human Pose Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ming Xu, Xu Zhang","submitted_at":"2025-06-17T14:59:56Z","abstract_excerpt":"Existing monocular 3D pose estimation methods primarily rely on joint positional features, while overlooking intrinsic directional and angular correlations within the skeleton. As a result, they often produce implausible poses under joint occlusions or rapid motion changes. To address these challenges, we propose the PoseGRAF framework. We first construct a dual graph convolutional structure that separately processes joint and bone graphs, effectively capturing their local dependencies. A Cross-Attention module is then introduced to model interdependencies between bone directions and joint fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14596","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/2506.14596/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.14596","created_at":"2026-07-05T11:22:59.458799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14596v1","created_at":"2026-07-05T11:22:59.458799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14596","created_at":"2026-07-05T11:22:59.458799+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LYCMLVYK3LS","created_at":"2026-07-05T11:22:59.458799+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LYCMLVYK3LSBWO5","created_at":"2026-07-05T11:22:59.458799+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LYCMLVY","created_at":"2026-07-05T11:22:59.458799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13233","citing_title":"Doppler Prompting for Stable mmWave-based Human Pose Estimation","ref_index":285,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ","json":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ.json","graph_json":"https://pith.science/api/pith-number/6LYCMLVYK3LSBWO5HLCQXC26WZ/graph.json","events_json":"https://pith.science/api/pith-number/6LYCMLVYK3LSBWO5HLCQXC26WZ/events.json","paper":"https://pith.science/paper/6LYCMLVY"},"agent_actions":{"view_html":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ","download_json":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ.json","view_paper":"https://pith.science/paper/6LYCMLVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14596&json=true","fetch_graph":"https://pith.science/api/pith-number/6LYCMLVYK3LSBWO5HLCQXC26WZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6LYCMLVYK3LSBWO5HLCQXC26WZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ/action/storage_attestation","attest_author":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ/action/author_attestation","sign_citation":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ/action/citation_signature","submit_replication":"https://pith.science/pith/6LYCMLVYK3LSBWO5HLCQXC26WZ/action/replication_record"}},"created_at":"2026-07-05T11:22:59.458799+00:00","updated_at":"2026-07-05T11:22:59.458799+00:00"}