{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:A6JSA3UM5NTLX64K3PKUJCU6WX","short_pith_number":"pith:A6JSA3UM","schema_version":"1.0","canonical_sha256":"0793206e8ceb66bbfb8adbd5448a9eb5d27117d248eeec92394c07acc0ea2a8d","source":{"kind":"arxiv","id":"2312.08566","version":1},"attestation_state":"computed","paper":{"title":"Learning adaptive planning representations with natural language guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.AI","authors_text":"Jacob Andreas, Jiahai Feng, Jiayuan Mao, Joshua B. Tenenbaum, Lionel Wong, Noa Korneev, Pratyusha Sharma, Zachary S. Siegel","submitted_at":"2023-12-13T23:35:31Z","abstract_excerpt":"Effective planning in the real world requires not only world knowledge, but the ability to leverage that knowledge to build the right representation of the task at hand. Decades of hierarchical planning techniques have used domain-specific temporal action abstractions to support efficient and accurate planning, almost always relying on human priors and domain knowledge to decompose hard tasks into smaller subproblems appropriate for a goal or set of goals. This paper describes Ada (Action Domain Acquisition), a framework for automatically constructing task-specific planning representations usi"},"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":"2312.08566","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T23:35:31Z","cross_cats_sorted":["cs.CL","cs.RO"],"title_canon_sha256":"b8eb080afde059befb28b37c01c8f075d78424f942fc269b755d4bf0c86fa60e","abstract_canon_sha256":"bbc0176cc4637758c74d7a3b8a3c5bc9376abaed9e586d72958a9b781ea45219"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:06.012385Z","signature_b64":"sdpZtIn/dyVOyu3nW87SjTMZ5r5nIoj66byUYcEEwMkIJxPwTyP4X4VRFuYVKDYm+YvH2m2fqkZWc8Q+QpyHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0793206e8ceb66bbfb8adbd5448a9eb5d27117d248eeec92394c07acc0ea2a8d","last_reissued_at":"2026-07-05T07:24:06.011942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:06.011942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning adaptive planning representations with natural language guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.RO"],"primary_cat":"cs.AI","authors_text":"Jacob Andreas, Jiahai Feng, Jiayuan Mao, Joshua B. Tenenbaum, Lionel Wong, Noa Korneev, Pratyusha Sharma, Zachary S. Siegel","submitted_at":"2023-12-13T23:35:31Z","abstract_excerpt":"Effective planning in the real world requires not only world knowledge, but the ability to leverage that knowledge to build the right representation of the task at hand. Decades of hierarchical planning techniques have used domain-specific temporal action abstractions to support efficient and accurate planning, almost always relying on human priors and domain knowledge to decompose hard tasks into smaller subproblems appropriate for a goal or set of goals. This paper describes Ada (Action Domain Acquisition), a framework for automatically constructing task-specific planning representations usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.08566","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/2312.08566/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":"2312.08566","created_at":"2026-07-05T07:24:06.011998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.08566v1","created_at":"2026-07-05T07:24:06.011998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.08566","created_at":"2026-07-05T07:24:06.011998+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6JSA3UM5NTL","created_at":"2026-07-05T07:24:06.011998+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6JSA3UM5NTLX64K","created_at":"2026-07-05T07:24:06.011998+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6JSA3UM","created_at":"2026-07-05T07:24:06.011998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06501","citing_title":"Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22488","citing_title":"SCOPE: Evolving Symbolic World for Planning in Open-Ended Environments","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12131","citing_title":"Rollout Cards: A Reproducibility Standard for Agent Research","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX","json":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX.json","graph_json":"https://pith.science/api/pith-number/A6JSA3UM5NTLX64K3PKUJCU6WX/graph.json","events_json":"https://pith.science/api/pith-number/A6JSA3UM5NTLX64K3PKUJCU6WX/events.json","paper":"https://pith.science/paper/A6JSA3UM"},"agent_actions":{"view_html":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX","download_json":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX.json","view_paper":"https://pith.science/paper/A6JSA3UM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.08566&json=true","fetch_graph":"https://pith.science/api/pith-number/A6JSA3UM5NTLX64K3PKUJCU6WX/graph.json","fetch_events":"https://pith.science/api/pith-number/A6JSA3UM5NTLX64K3PKUJCU6WX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX/action/storage_attestation","attest_author":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX/action/author_attestation","sign_citation":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX/action/citation_signature","submit_replication":"https://pith.science/pith/A6JSA3UM5NTLX64K3PKUJCU6WX/action/replication_record"}},"created_at":"2026-07-05T07:24:06.011998+00:00","updated_at":"2026-07-05T07:24:06.011998+00:00"}