{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WP2RZHSEJAVFDK6WTHLRD3LXOQ","short_pith_number":"pith:WP2RZHSE","schema_version":"1.0","canonical_sha256":"b3f51c9e44482a51abd699d711ed77742fc44f97fb156a8f2ab5e9158df72715","source":{"kind":"arxiv","id":"2506.09284","version":2},"attestation_state":"computed","paper":{"title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengshu Li, Jiajun Wu, Li Fei-Fei, Roy Yuan, Ruohan Zhang, Wenlong Huang, Yihe Tang, Yingke Wang","submitted_at":"2025-06-10T22:47:16Z","abstract_excerpt":"Understanding fine-grained object affordances is imperative for robots to manipulate objects in unstructured environments given open-ended task instructions. However, existing methods of visual affordance predictions often rely on manually annotated data or conditions only on a predefined set of tasks. We introduce UAD (Unsupervised Affordance Distillation), a method for distilling affordance knowledge from foundation models into a task-conditioned affordance model without any manual annotations. By leveraging the complementary strengths of large vision models and vision-language models, UAD a"},"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":"2506.09284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-10T22:47:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"64215b8f1c5468c23e063e4cdc030250ace504cb3cb70cc3db6bbb5659a59819","abstract_canon_sha256":"64975cd62e5984df96678449228387638dc06933c57cdbd712dbdf83c0065dc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:15.646650Z","signature_b64":"lGhX/BhsPzlkrUav+z5nOeKohZgznxUjDnGXUI78emtWuOWB/+2wtfyqkheEoX2eF12wbDV5LN9B1P0UcXTlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3f51c9e44482a51abd699d711ed77742fc44f97fb156a8f2ab5e9158df72715","last_reissued_at":"2026-07-05T11:59:15.646034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:15.646034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UAD: Unsupervised Affordance Distillation for Generalization in Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chengshu Li, Jiajun Wu, Li Fei-Fei, Roy Yuan, Ruohan Zhang, Wenlong Huang, Yihe Tang, Yingke Wang","submitted_at":"2025-06-10T22:47:16Z","abstract_excerpt":"Understanding fine-grained object affordances is imperative for robots to manipulate objects in unstructured environments given open-ended task instructions. However, existing methods of visual affordance predictions often rely on manually annotated data or conditions only on a predefined set of tasks. We introduce UAD (Unsupervised Affordance Distillation), a method for distilling affordance knowledge from foundation models into a task-conditioned affordance model without any manual annotations. By leveraging the complementary strengths of large vision models and vision-language models, UAD a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09284","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/2506.09284/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":"2506.09284","created_at":"2026-07-05T11:59:15.646105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09284v2","created_at":"2026-07-05T11:59:15.646105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09284","created_at":"2026-07-05T11:59:15.646105+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP2RZHSEJAVF","created_at":"2026-07-05T11:59:15.646105+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP2RZHSEJAVFDK6W","created_at":"2026-07-05T11:59:15.646105+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP2RZHSE","created_at":"2026-07-05T11:59:15.646105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27036","citing_title":"RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08655","citing_title":"PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.19102","citing_title":"FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01433","citing_title":"AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ","json":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ.json","graph_json":"https://pith.science/api/pith-number/WP2RZHSEJAVFDK6WTHLRD3LXOQ/graph.json","events_json":"https://pith.science/api/pith-number/WP2RZHSEJAVFDK6WTHLRD3LXOQ/events.json","paper":"https://pith.science/paper/WP2RZHSE"},"agent_actions":{"view_html":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ","download_json":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ.json","view_paper":"https://pith.science/paper/WP2RZHSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09284&json=true","fetch_graph":"https://pith.science/api/pith-number/WP2RZHSEJAVFDK6WTHLRD3LXOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WP2RZHSEJAVFDK6WTHLRD3LXOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ/action/storage_attestation","attest_author":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ/action/author_attestation","sign_citation":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ/action/citation_signature","submit_replication":"https://pith.science/pith/WP2RZHSEJAVFDK6WTHLRD3LXOQ/action/replication_record"}},"created_at":"2026-07-05T11:59:15.646105+00:00","updated_at":"2026-07-05T11:59:15.646105+00:00"}