{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3IJNHRWPKSFBF4ZD2BNOCG7T7Q","short_pith_number":"pith:3IJNHRWP","schema_version":"1.0","canonical_sha256":"da12d3c6cf548a12f323d05ae11bf3fc2d83ac4df3e9f30684b3048987259974","source":{"kind":"arxiv","id":"2102.13177","version":4},"attestation_state":"computed","paper":{"title":"Efficient and Interpretable Robot Manipulation with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Akshara Rai, Austin S. Wang, Eric Undersander, Yixin Lin","submitted_at":"2021-02-25T21:09:12Z","abstract_excerpt":"Manipulation tasks, like loading a dishwasher, can be seen as a sequence of spatial constraints and relationships between different objects. We aim to discover these rules from demonstrations by posing manipulation as a classification problem over a graph, whose nodes represent task-relevant entities like objects and goals, and present a graph neural network (GNN) policy architecture for solving this problem from demonstrations. In our experiments, a single GNN policy trained using imitation learning (IL) on 20 expert demos can solve blockstacking, rearrangement, and dishwasher loading tasks; "},"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":"2102.13177","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-02-25T21:09:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"427b645df11030ea423261c958a6560a598f6cb237f35dde70119cad1410abac","abstract_canon_sha256":"be103ff1b6c1317e8759d30caef036a4b95b45e93f8325f933d4cd676d41d9d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:51.457353Z","signature_b64":"EG65RM9Y5VVr+vOUwZeGYPXM9pIxU2hLQIg2nhGuxlOSzhtuK8XtzhImdNZSv1/9L2c9iCv+jqu4+TFZJNNmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da12d3c6cf548a12f323d05ae11bf3fc2d83ac4df3e9f30684b3048987259974","last_reissued_at":"2026-07-05T03:47:51.456884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:51.456884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Interpretable Robot Manipulation with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Akshara Rai, Austin S. Wang, Eric Undersander, Yixin Lin","submitted_at":"2021-02-25T21:09:12Z","abstract_excerpt":"Manipulation tasks, like loading a dishwasher, can be seen as a sequence of spatial constraints and relationships between different objects. We aim to discover these rules from demonstrations by posing manipulation as a classification problem over a graph, whose nodes represent task-relevant entities like objects and goals, and present a graph neural network (GNN) policy architecture for solving this problem from demonstrations. In our experiments, a single GNN policy trained using imitation learning (IL) on 20 expert demos can solve blockstacking, rearrangement, and dishwasher loading tasks; "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13177","kind":"arxiv","version":4},"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/2102.13177/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":"2102.13177","created_at":"2026-07-05T03:47:51.456941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.13177v4","created_at":"2026-07-05T03:47:51.456941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13177","created_at":"2026-07-05T03:47:51.456941+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IJNHRWPKSFB","created_at":"2026-07-05T03:47:51.456941+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IJNHRWPKSFBF4ZD","created_at":"2026-07-05T03:47:51.456941+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IJNHRWP","created_at":"2026-07-05T03:47:51.456941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q","json":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q.json","graph_json":"https://pith.science/api/pith-number/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/graph.json","events_json":"https://pith.science/api/pith-number/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/events.json","paper":"https://pith.science/paper/3IJNHRWP"},"agent_actions":{"view_html":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q","download_json":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q.json","view_paper":"https://pith.science/paper/3IJNHRWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.13177&json=true","fetch_graph":"https://pith.science/api/pith-number/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/action/storage_attestation","attest_author":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/action/author_attestation","sign_citation":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/action/citation_signature","submit_replication":"https://pith.science/pith/3IJNHRWPKSFBF4ZD2BNOCG7T7Q/action/replication_record"}},"created_at":"2026-07-05T03:47:51.456941+00:00","updated_at":"2026-07-05T03:47:51.456941+00:00"}