{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LBQAMYYIRMMQFVXPDBRMGXDNNY","short_pith_number":"pith:LBQAMYYI","schema_version":"1.0","canonical_sha256":"58600663088b1902d6ef1862c35c6d6e1ad4de05754932df08864b341438d069","source":{"kind":"arxiv","id":"2201.13388","version":1},"attestation_state":"computed","paper":{"title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Bernhard Sch\\\"olkopf, Davide Mambelli, Francesco Locatello, Frederik Tr\\\"auble, Stefan Bauer","submitted_at":"2022-01-31T17:53:30Z","abstract_excerpt":"Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge. In this paper, we focus on models that can learn manipulation tasks in fixed multi-object settings and extrapolate this skill zero-shot without any drop in performance when the number of objects changes. We consider the generic task of bringing a specific cube out of a set to a goal position. We find that previous approaches, which primarily leverage attention and graph neural network-based architectures, do not gener"},"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":"2201.13388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-01-31T17:53:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"afd868b768e5f0bc0de5e58ad2bcfcd18423ef9fbf59e9a1f008bad8e3c80151","abstract_canon_sha256":"2503ad732adfa759b0bfc80f9034a39106272182fb47dc722658f6858216d4bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:52:51.535823Z","signature_b64":"wGjzZNzoz3xkl4SnceypOuzVc250v6W5UuLcJsyT3kbd/PvZqDt1RNYmIDjgK1ZPfFahKoqJKMLx+7xRmRaPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58600663088b1902d6ef1862c35c6d6e1ad4de05754932df08864b341438d069","last_reissued_at":"2026-07-05T03:52:51.535354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:52:51.535354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Bernhard Sch\\\"olkopf, Davide Mambelli, Francesco Locatello, Frederik Tr\\\"auble, Stefan Bauer","submitted_at":"2022-01-31T17:53:30Z","abstract_excerpt":"Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge. In this paper, we focus on models that can learn manipulation tasks in fixed multi-object settings and extrapolate this skill zero-shot without any drop in performance when the number of objects changes. We consider the generic task of bringing a specific cube out of a set to a goal position. We find that previous approaches, which primarily leverage attention and graph neural network-based architectures, do not gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.13388","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/2201.13388/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":"2201.13388","created_at":"2026-07-05T03:52:51.535410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.13388v1","created_at":"2026-07-05T03:52:51.535410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.13388","created_at":"2026-07-05T03:52:51.535410+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBQAMYYIRMMQ","created_at":"2026-07-05T03:52:51.535410+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBQAMYYIRMMQFVXP","created_at":"2026-07-05T03:52:51.535410+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBQAMYYI","created_at":"2026-07-05T03:52:51.535410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14937","citing_title":"Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY","json":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY.json","graph_json":"https://pith.science/api/pith-number/LBQAMYYIRMMQFVXPDBRMGXDNNY/graph.json","events_json":"https://pith.science/api/pith-number/LBQAMYYIRMMQFVXPDBRMGXDNNY/events.json","paper":"https://pith.science/paper/LBQAMYYI"},"agent_actions":{"view_html":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY","download_json":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY.json","view_paper":"https://pith.science/paper/LBQAMYYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.13388&json=true","fetch_graph":"https://pith.science/api/pith-number/LBQAMYYIRMMQFVXPDBRMGXDNNY/graph.json","fetch_events":"https://pith.science/api/pith-number/LBQAMYYIRMMQFVXPDBRMGXDNNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY/action/storage_attestation","attest_author":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY/action/author_attestation","sign_citation":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY/action/citation_signature","submit_replication":"https://pith.science/pith/LBQAMYYIRMMQFVXPDBRMGXDNNY/action/replication_record"}},"created_at":"2026-07-05T03:52:51.535410+00:00","updated_at":"2026-07-05T03:52:51.535410+00:00"}