{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KDGDB63LVQSSYBMXVCG7YBXAZJ","short_pith_number":"pith:KDGDB63L","schema_version":"1.0","canonical_sha256":"50cc30fb6bac252c0597a88dfc06e0ca4268e874922de250453fa4f3521e6b0e","source":{"kind":"arxiv","id":"2605.26828","version":1},"attestation_state":"computed","paper":{"title":"Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Karla Stepanova, Oleh Borys","submitted_at":"2026-05-26T10:45:29Z","abstract_excerpt":"Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representations must be inspectable, reusable, and human-interpretable. To address this, we study how to represent and learn robotic tasks with inductive logic programming~(ILP) by decomposing a complex task into a series of simpler learning objectives at different abstraction (ontological) levels. The system infers symbolic rules from demonstrations and prior (domain) knowledge, and reuses "},"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":"2605.26828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-26T10:45:29Z","cross_cats_sorted":[],"title_canon_sha256":"503e32efab88b426284cacaf8effc7d94690a3ab536c2b673156fea30b4ff3aa","abstract_canon_sha256":"2f8a7ece665bc4b7a2f96fac4a3a3d0f33cf92fc404b0041f0ce18e0a9d37c7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:14.625506Z","signature_b64":"W+VApBsKtlKp0pUY+2IZD94A4F5AO0Ci+DlrkDP/Zi66ncNdxs8J0uAFWhxNP7GW1mhVwvVCzoAR5Td47JG0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50cc30fb6bac252c0597a88dfc06e0ca4268e874922de250453fa4f3521e6b0e","last_reissued_at":"2026-05-27T01:06:14.623430Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:14.623430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Karla Stepanova, Oleh Borys","submitted_at":"2026-05-26T10:45:29Z","abstract_excerpt":"Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representations must be inspectable, reusable, and human-interpretable. To address this, we study how to represent and learn robotic tasks with inductive logic programming~(ILP) by decomposing a complex task into a series of simpler learning objectives at different abstraction (ontological) levels. The system infers symbolic rules from demonstrations and prior (domain) knowledge, and reuses "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26828","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/2605.26828/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":"2605.26828","created_at":"2026-05-27T01:06:14.623566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26828v1","created_at":"2026-05-27T01:06:14.623566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26828","created_at":"2026-05-27T01:06:14.623566+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDGDB63LVQSS","created_at":"2026-05-27T01:06:14.623566+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDGDB63LVQSSYBMX","created_at":"2026-05-27T01:06:14.623566+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDGDB63L","created_at":"2026-05-27T01:06:14.623566+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/KDGDB63LVQSSYBMXVCG7YBXAZJ","json":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ.json","graph_json":"https://pith.science/api/pith-number/KDGDB63LVQSSYBMXVCG7YBXAZJ/graph.json","events_json":"https://pith.science/api/pith-number/KDGDB63LVQSSYBMXVCG7YBXAZJ/events.json","paper":"https://pith.science/paper/KDGDB63L"},"agent_actions":{"view_html":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ","download_json":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ.json","view_paper":"https://pith.science/paper/KDGDB63L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26828&json=true","fetch_graph":"https://pith.science/api/pith-number/KDGDB63LVQSSYBMXVCG7YBXAZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KDGDB63LVQSSYBMXVCG7YBXAZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ/action/storage_attestation","attest_author":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ/action/author_attestation","sign_citation":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ/action/citation_signature","submit_replication":"https://pith.science/pith/KDGDB63LVQSSYBMXVCG7YBXAZJ/action/replication_record"}},"created_at":"2026-05-27T01:06:14.623566+00:00","updated_at":"2026-05-27T01:06:14.623566+00:00"}