{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TP4LRL7CAPL3ZIXLDRY4YYZVEZ","short_pith_number":"pith:TP4LRL7C","schema_version":"1.0","canonical_sha256":"9bf8b8afe203d7bca2eb1c71cc633526718a7bfe3f153b1090d9e11a5bd37eed","source":{"kind":"arxiv","id":"2410.23156","version":2},"attestation_state":"computed","paper":{"title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Adrian Weller, Hao Tang, Jo\\~ao F. Henriques, Joshua B. Tenenbaum, Kevin Ellis, Nishanth Kumar, Tom Silver, Yichao Liang","submitted_at":"2024-10-30T16:11:05Z","abstract_excerpt":"Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on b"},"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":"2410.23156","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-30T16:11:05Z","cross_cats_sorted":["cs.CV","cs.LG","cs.RO"],"title_canon_sha256":"6123cfa5df1a92cf68714f88de3c1399b7b5c39c36f1f7d59158277d438e4b0e","abstract_canon_sha256":"a9bafda631f8d4dbb8e1154809f30f9cf70f4a1d52b059001659cd4caa651c5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:08.945253Z","signature_b64":"CS4LAtA5+9TuLoIYWe7cDpXta14ZmGx6Y1NHwj8odK+vMnNvi98zrB28AIZcygGvKY3hW4pXfdv6fzQ0/fpCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bf8b8afe203d7bca2eb1c71cc633526718a7bfe3f153b1090d9e11a5bd37eed","last_reissued_at":"2026-07-05T10:22:08.944705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:08.944705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Adrian Weller, Hao Tang, Jo\\~ao F. Henriques, Joshua B. Tenenbaum, Kevin Ellis, Nishanth Kumar, Tom Silver, Yichao Liang","submitted_at":"2024-10-30T16:11:05Z","abstract_excerpt":"Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a first-order abstraction language that combines the strengths of symbolic and neural knowledge representations. We outline an online algorithm for inventing such predicates and learning abstract world models. We compare our approach to hierarchical reinforcement learning, vision-language model planning, and symbolic predicate invention approaches, on b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23156","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/2410.23156/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":"2410.23156","created_at":"2026-07-05T10:22:08.944763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23156v2","created_at":"2026-07-05T10:22:08.944763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23156","created_at":"2026-07-05T10:22:08.944763+00:00"},{"alias_kind":"pith_short_12","alias_value":"TP4LRL7CAPL3","created_at":"2026-07-05T10:22:08.944763+00:00"},{"alias_kind":"pith_short_16","alias_value":"TP4LRL7CAPL3ZIXL","created_at":"2026-07-05T10:22:08.944763+00:00"},{"alias_kind":"pith_short_8","alias_value":"TP4LRL7C","created_at":"2026-07-05T10:22:08.944763+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.12870","citing_title":"Physically Interpretable World Models via Weakly Supervised Representation Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21543","citing_title":"Self-CriTeach: LLM Self-Teaching and Self-Critiquing for Improving Robotic Planning via Automated Domain Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26689","citing_title":"Atomic-Probe Governance for Skill Updates in Compositional Robot Policies","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ","json":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ.json","graph_json":"https://pith.science/api/pith-number/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/graph.json","events_json":"https://pith.science/api/pith-number/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/events.json","paper":"https://pith.science/paper/TP4LRL7C"},"agent_actions":{"view_html":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ","download_json":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ.json","view_paper":"https://pith.science/paper/TP4LRL7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23156&json=true","fetch_graph":"https://pith.science/api/pith-number/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/action/storage_attestation","attest_author":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/action/author_attestation","sign_citation":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/action/citation_signature","submit_replication":"https://pith.science/pith/TP4LRL7CAPL3ZIXLDRY4YYZVEZ/action/replication_record"}},"created_at":"2026-07-05T10:22:08.944763+00:00","updated_at":"2026-07-05T10:22:08.944763+00:00"}