{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VV4PQKYL3R2MR2N44EBPEUOR53","short_pith_number":"pith:VV4PQKYL","schema_version":"1.0","canonical_sha256":"ad78f82b0bdc74c8e9bce102f251d1eec6da33396402272a96fe2068c548b76d","source":{"kind":"arxiv","id":"2405.19758","version":1},"attestation_state":"computed","paper":{"title":"InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Muzhi Han, Song-Chun Zhu, Yifeng Zhu, Ying Nian Wu, Yuke Zhu","submitted_at":"2024-05-30T07:08:40Z","abstract_excerpt":"Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during embodied interaction. The learned predicates provide relational abstractions of the environment state, facilitating the learning of symbolic operators that capture action preconditions and effects. By compiling the learned predicates and operators into a PDDL domain on-the-fly, InterPreT allows effective planning toward arbitrary in-domain goals using a PDDL pla"},"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":"2405.19758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-30T07:08:40Z","cross_cats_sorted":[],"title_canon_sha256":"0d3b6466c57dbdcd660d85516c30ccd0a29cd57faa7d563bb2fc4422bb8f2b78","abstract_canon_sha256":"5684615e516fd05838c93931a22413704e3c0418d6603416a0c8497c23b4ac60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:12.019891Z","signature_b64":"ct49S9WUanDdXqhwAdLbsm0QRWauN+NyrjjFcJNl4SsT1eizP5lcKTeXDzEYiMtW9imRZoo4aIvumDv+l4IkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad78f82b0bdc74c8e9bce102f251d1eec6da33396402272a96fe2068c548b76d","last_reissued_at":"2026-07-05T08:25:12.019485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:12.019485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterPreT: Interactive Predicate Learning from Language Feedback for Generalizable Task Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Muzhi Han, Song-Chun Zhu, Yifeng Zhu, Ying Nian Wu, Yuke Zhu","submitted_at":"2024-05-30T07:08:40Z","abstract_excerpt":"Learning abstract state representations and knowledge is crucial for long-horizon robot planning. We present InterPreT, an LLM-powered framework for robots to learn symbolic predicates from language feedback of human non-experts during embodied interaction. The learned predicates provide relational abstractions of the environment state, facilitating the learning of symbolic operators that capture action preconditions and effects. By compiling the learned predicates and operators into a PDDL domain on-the-fly, InterPreT allows effective planning toward arbitrary in-domain goals using a PDDL pla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19758","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/2405.19758/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":"2405.19758","created_at":"2026-07-05T08:25:12.019541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19758v1","created_at":"2026-07-05T08:25:12.019541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19758","created_at":"2026-07-05T08:25:12.019541+00:00"},{"alias_kind":"pith_short_12","alias_value":"VV4PQKYL3R2M","created_at":"2026-07-05T08:25:12.019541+00:00"},{"alias_kind":"pith_short_16","alias_value":"VV4PQKYL3R2MR2N4","created_at":"2026-07-05T08:25:12.019541+00:00"},{"alias_kind":"pith_short_8","alias_value":"VV4PQKYL","created_at":"2026-07-05T08:25:12.019541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.21545","citing_title":"UniDomain: Pretraining a Unified PDDL Domain from Real-World Demonstrations for Generalizable Robot Task Planning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09487","citing_title":"Kintsugi: Learning Policies by Repairing Executable Knowledge Bases","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53","json":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53.json","graph_json":"https://pith.science/api/pith-number/VV4PQKYL3R2MR2N44EBPEUOR53/graph.json","events_json":"https://pith.science/api/pith-number/VV4PQKYL3R2MR2N44EBPEUOR53/events.json","paper":"https://pith.science/paper/VV4PQKYL"},"agent_actions":{"view_html":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53","download_json":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53.json","view_paper":"https://pith.science/paper/VV4PQKYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19758&json=true","fetch_graph":"https://pith.science/api/pith-number/VV4PQKYL3R2MR2N44EBPEUOR53/graph.json","fetch_events":"https://pith.science/api/pith-number/VV4PQKYL3R2MR2N44EBPEUOR53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53/action/storage_attestation","attest_author":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53/action/author_attestation","sign_citation":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53/action/citation_signature","submit_replication":"https://pith.science/pith/VV4PQKYL3R2MR2N44EBPEUOR53/action/replication_record"}},"created_at":"2026-07-05T08:25:12.019541+00:00","updated_at":"2026-07-05T08:25:12.019541+00:00"}