{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OM3MQJRW7BVWGSI7AGLB3TCJ4A","short_pith_number":"pith:OM3MQJRW","schema_version":"1.0","canonical_sha256":"7336c82636f86b63491f01961dcc49e02ae4095562b47b83eb602ab194250a2e","source":{"kind":"arxiv","id":"2211.05272","version":2},"attestation_state":"computed","paper":{"title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chengyang Zhao, Haoran Geng, Helin Xu, He Wang, Li Yi, Siyuan Huang","submitted_at":"2022-11-10T00:30:22Z","abstract_excerpt":"For years, researchers have been devoted to generalizable object perception and manipulation, where cross-category generalizability is highly desired yet underexplored. In this work, we propose to learn such cross-category skills via Generalizable and Actionable Parts (GAParts). By identifying and defining 9 GAPart classes (lids, handles, etc.) in 27 object categories, we construct a large-scale part-centric interactive dataset, GAPartNet, where we provide rich, part-level annotations (semantics, poses) for 8,489 part instances on 1,166 objects. Based on GAPartNet, we investigate three cross-c"},"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":"2211.05272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-10T00:30:22Z","cross_cats_sorted":[],"title_canon_sha256":"fca20a3764878b9669bb834fed8c27b6ef2ab43e81c8194906c3422e7609cb77","abstract_canon_sha256":"fc5c8f50328c2a3f537fa18d11dd56d30be138233aaecafe17484556915e2307"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:32.755164Z","signature_b64":"PfdOGCQuEmwddPWTf7JPNAnxmlvL58Xo5CACGH0CZ7HBVEwtGAi7nlIxHHy6oZxM29soBNYABOfMSIURfteGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7336c82636f86b63491f01961dcc49e02ae4095562b47b83eb602ab194250a2e","last_reissued_at":"2026-07-05T05:54:32.754552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:32.754552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Xu, Chengyang Zhao, Haoran Geng, Helin Xu, He Wang, Li Yi, Siyuan Huang","submitted_at":"2022-11-10T00:30:22Z","abstract_excerpt":"For years, researchers have been devoted to generalizable object perception and manipulation, where cross-category generalizability is highly desired yet underexplored. In this work, we propose to learn such cross-category skills via Generalizable and Actionable Parts (GAParts). By identifying and defining 9 GAPart classes (lids, handles, etc.) in 27 object categories, we construct a large-scale part-centric interactive dataset, GAPartNet, where we provide rich, part-level annotations (semantics, poses) for 8,489 part instances on 1,166 objects. Based on GAPartNet, we investigate three cross-c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05272","kind":"arxiv","version":2},"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/2211.05272/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":"2211.05272","created_at":"2026-07-05T05:54:32.754634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05272v2","created_at":"2026-07-05T05:54:32.754634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05272","created_at":"2026-07-05T05:54:32.754634+00:00"},{"alias_kind":"pith_short_12","alias_value":"OM3MQJRW7BVW","created_at":"2026-07-05T05:54:32.754634+00:00"},{"alias_kind":"pith_short_16","alias_value":"OM3MQJRW7BVWGSI7","created_at":"2026-07-05T05:54:32.754634+00:00"},{"alias_kind":"pith_short_8","alias_value":"OM3MQJRW","created_at":"2026-07-05T05:54:32.754634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24628","citing_title":"ArtiTwinSplat: Interactable Digital Twin Reconstruction via Gaussian Splatting from RGB-D videos","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16582","citing_title":"ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19136","citing_title":"Automatically Improving Simulation Physics for Articulated Objects","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15953","citing_title":"ViTacFormer: Learning Cross-Modal Representation for Visuo-Tactile Dexterous Manipulation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22551","citing_title":"QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A","json":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A.json","graph_json":"https://pith.science/api/pith-number/OM3MQJRW7BVWGSI7AGLB3TCJ4A/graph.json","events_json":"https://pith.science/api/pith-number/OM3MQJRW7BVWGSI7AGLB3TCJ4A/events.json","paper":"https://pith.science/paper/OM3MQJRW"},"agent_actions":{"view_html":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A","download_json":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A.json","view_paper":"https://pith.science/paper/OM3MQJRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05272&json=true","fetch_graph":"https://pith.science/api/pith-number/OM3MQJRW7BVWGSI7AGLB3TCJ4A/graph.json","fetch_events":"https://pith.science/api/pith-number/OM3MQJRW7BVWGSI7AGLB3TCJ4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A/action/storage_attestation","attest_author":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A/action/author_attestation","sign_citation":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A/action/citation_signature","submit_replication":"https://pith.science/pith/OM3MQJRW7BVWGSI7AGLB3TCJ4A/action/replication_record"}},"created_at":"2026-07-05T05:54:32.754634+00:00","updated_at":"2026-07-05T05:54:32.754634+00:00"}