{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GILM5GLK6YYEXIIU4MFU5B53GW","short_pith_number":"pith:GILM5GLK","schema_version":"1.0","canonical_sha256":"3216ce996af6304ba114e30b4e87bb358f85f8a9657dae9a19495fafade8e381","source":{"kind":"arxiv","id":"2401.07487","version":1},"attestation_state":"computed","paper":{"title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Guowei Zhang, Gu Zhang, Huazhe Xu, Kaizhe Hu, Mingrun Jiang, Yuanchen Ju","submitted_at":"2024-01-15T06:02:30Z","abstract_excerpt":"Enabling robotic manipulation that generalizes to out-of-distribution scenes is a crucial step toward open-world embodied intelligence. For human beings, this ability is rooted in the understanding of semantic correspondence among objects, which naturally transfers the interaction experience of familiar objects to novel ones. Although robots lack such a reservoir of interaction experience, the vast availability of human videos on the Internet may serve as a valuable resource, from which we extract an affordance memory including the contact points. Inspired by the natural way humans think, we p"},"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":"2401.07487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-01-15T06:02:30Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"50a8a7df822e6940aa34028cbd693778aa690edf346419f5c3a73a68e1e2da0f","abstract_canon_sha256":"d6266d1f6d74e9f38d9cf2d2a8a7a886cbf422270dffd1bc49460ea63c37ccee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:37.936097Z","signature_b64":"CvRoZ9T7MCA80W20svK5Vn8B7Xx0pbI4lHX49ISu5TGCLUXTKERAV2XvEEpNfIhbf9BmoY7+tgLlyea8BEuTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3216ce996af6304ba114e30b4e87bb358f85f8a9657dae9a19495fafade8e381","last_reissued_at":"2026-07-05T07:33:37.935625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:37.935625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Guowei Zhang, Gu Zhang, Huazhe Xu, Kaizhe Hu, Mingrun Jiang, Yuanchen Ju","submitted_at":"2024-01-15T06:02:30Z","abstract_excerpt":"Enabling robotic manipulation that generalizes to out-of-distribution scenes is a crucial step toward open-world embodied intelligence. For human beings, this ability is rooted in the understanding of semantic correspondence among objects, which naturally transfers the interaction experience of familiar objects to novel ones. Although robots lack such a reservoir of interaction experience, the vast availability of human videos on the Internet may serve as a valuable resource, from which we extract an affordance memory including the contact points. Inspired by the natural way humans think, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07487","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/2401.07487/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":"2401.07487","created_at":"2026-07-05T07:33:37.935681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07487v1","created_at":"2026-07-05T07:33:37.935681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07487","created_at":"2026-07-05T07:33:37.935681+00:00"},{"alias_kind":"pith_short_12","alias_value":"GILM5GLK6YYE","created_at":"2026-07-05T07:33:37.935681+00:00"},{"alias_kind":"pith_short_16","alias_value":"GILM5GLK6YYEXIIU","created_at":"2026-07-05T07:33:37.935681+00:00"},{"alias_kind":"pith_short_8","alias_value":"GILM5GLK","created_at":"2026-07-05T07:33:37.935681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26800","citing_title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06155","citing_title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26800","citing_title":"SSI-Policy: Learning Structured Scene Interfaces for Vision-Language Robotic Manipulation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW","json":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW.json","graph_json":"https://pith.science/api/pith-number/GILM5GLK6YYEXIIU4MFU5B53GW/graph.json","events_json":"https://pith.science/api/pith-number/GILM5GLK6YYEXIIU4MFU5B53GW/events.json","paper":"https://pith.science/paper/GILM5GLK"},"agent_actions":{"view_html":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW","download_json":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW.json","view_paper":"https://pith.science/paper/GILM5GLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07487&json=true","fetch_graph":"https://pith.science/api/pith-number/GILM5GLK6YYEXIIU4MFU5B53GW/graph.json","fetch_events":"https://pith.science/api/pith-number/GILM5GLK6YYEXIIU4MFU5B53GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW/action/storage_attestation","attest_author":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW/action/author_attestation","sign_citation":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW/action/citation_signature","submit_replication":"https://pith.science/pith/GILM5GLK6YYEXIIU4MFU5B53GW/action/replication_record"}},"created_at":"2026-07-05T07:33:37.935681+00:00","updated_at":"2026-07-05T07:33:37.935681+00:00"}