{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WTN2OJ54UMPAH52TPEE4SDWDFI","short_pith_number":"pith:WTN2OJ54","schema_version":"1.0","canonical_sha256":"b4dba727bca31e03f7537909c90ec32a17e5dd7529759a81bc5ba684b6b6e318","source":{"kind":"arxiv","id":"1812.07768","version":1},"attestation_state":"computed","paper":{"title":"Modular meta-learning in abstract graph networks for combinatorial generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Rodriguez, Ferran Alet, Leslie P. Kaelbling, Maria Bauza, Tomas Lozano-Perez","submitted_at":"2018-12-19T06:07:51Z","abstract_excerpt":"Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways. In this work we propose abstract graph networks: using graphs as abstractions of a system's subparts without a fixed assignment of nodes to system subparts, for which we would need supervision. We combine this idea with modular meta-learning to get a flexible framework with combinatorial generalization to new tasks built in. We then use it to model the pushing of arbitrarily shaped objects from little or no training data."},"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":"1812.07768","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T06:07:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"460e6b6e6152b7f968511bbb260f9c55d976d2f0686beb481b07354336d29a09","abstract_canon_sha256":"4858bbcb32340ac6d8b7c83de03665e3ee3dc04cc4af9b2a0e10e612b4b40513"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:56.052432Z","signature_b64":"aqYjKeNdpKXMH3nfPGEG4YoAcGYlKEq4Wa27iGECD81S7ZurF1k3Iw+kitcFV8SQAaQ22sNpaUlbazH4seBfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4dba727bca31e03f7537909c90ec32a17e5dd7529759a81bc5ba684b6b6e318","last_reissued_at":"2026-05-17T23:57:56.051901Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:56.051901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modular meta-learning in abstract graph networks for combinatorial generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Rodriguez, Ferran Alet, Leslie P. Kaelbling, Maria Bauza, Tomas Lozano-Perez","submitted_at":"2018-12-19T06:07:51Z","abstract_excerpt":"Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways. In this work we propose abstract graph networks: using graphs as abstractions of a system's subparts without a fixed assignment of nodes to system subparts, for which we would need supervision. We combine this idea with modular meta-learning to get a flexible framework with combinatorial generalization to new tasks built in. We then use it to model the pushing of arbitrarily shaped objects from little or no training data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07768","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":""},"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":"1812.07768","created_at":"2026-05-17T23:57:56.051983+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.07768v1","created_at":"2026-05-17T23:57:56.051983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07768","created_at":"2026-05-17T23:57:56.051983+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTN2OJ54UMPA","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTN2OJ54UMPAH52T","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTN2OJ54","created_at":"2026-05-18T12:33:01.666342+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/WTN2OJ54UMPAH52TPEE4SDWDFI","json":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI.json","graph_json":"https://pith.science/api/pith-number/WTN2OJ54UMPAH52TPEE4SDWDFI/graph.json","events_json":"https://pith.science/api/pith-number/WTN2OJ54UMPAH52TPEE4SDWDFI/events.json","paper":"https://pith.science/paper/WTN2OJ54"},"agent_actions":{"view_html":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI","download_json":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI.json","view_paper":"https://pith.science/paper/WTN2OJ54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.07768&json=true","fetch_graph":"https://pith.science/api/pith-number/WTN2OJ54UMPAH52TPEE4SDWDFI/graph.json","fetch_events":"https://pith.science/api/pith-number/WTN2OJ54UMPAH52TPEE4SDWDFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI/action/storage_attestation","attest_author":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI/action/author_attestation","sign_citation":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI/action/citation_signature","submit_replication":"https://pith.science/pith/WTN2OJ54UMPAH52TPEE4SDWDFI/action/replication_record"}},"created_at":"2026-05-17T23:57:56.051983+00:00","updated_at":"2026-05-17T23:57:56.051983+00:00"}