{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CWSX7FNMBCD746MICE55TNFLJS","short_pith_number":"pith:CWSX7FNM","schema_version":"1.0","canonical_sha256":"15a57f95ac0887fe7988113bd9b4ab4cbb5749a3401428b952fffb17eaff8076","source":{"kind":"arxiv","id":"2309.08587","version":2},"attestation_state":"computed","paper":{"title":"Compositional Foundation Models for Hierarchical Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhi Gupta, Akash Srivastava, Anurag Ajay, Josh Tenenbaum, Leslie Kaelbling, Pulkit Agrawal, Seungwook Han, Shuang Li, Tommi Jaakkola, Yilun Du","submitted_at":"2023-09-15T17:44:05Z","abstract_excerpt":"To make effective decisions in novel environments with long-horizon goals, it is crucial to engage in hierarchical reasoning across spatial and temporal scales. This entails planning abstract subgoal sequences, visually reasoning about the underlying plans, and executing actions in accordance with the devised plan through visual-motor control. We propose Compositional Foundation Models for Hierarchical Planning (HiP), a foundation model which leverages multiple expert foundation model trained on language, vision and action data individually jointly together to solve long-horizon tasks. We use "},"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":"2309.08587","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T17:44:05Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"eca70e241b6ce5b8f8bccc079aa5964d0f9153f0b59c2332a4953dc8f4610e8d","abstract_canon_sha256":"30e0bb13ed97a836a2cca7955b058875c9f9f91ee4d535faff6fd7642a6ae73c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:49.953560Z","signature_b64":"21EMvgi3Zn2fgh5E12Ntp2s83L3c5ej6bwX9r+McxJDxWdEJOr3lsXJ7H+fFZenTKePnVXLCt4tIBXvMiHLXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15a57f95ac0887fe7988113bd9b4ab4cbb5749a3401428b952fffb17eaff8076","last_reissued_at":"2026-07-05T06:52:49.953080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:49.953080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Foundation Models for Hierarchical Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhi Gupta, Akash Srivastava, Anurag Ajay, Josh Tenenbaum, Leslie Kaelbling, Pulkit Agrawal, Seungwook Han, Shuang Li, Tommi Jaakkola, Yilun Du","submitted_at":"2023-09-15T17:44:05Z","abstract_excerpt":"To make effective decisions in novel environments with long-horizon goals, it is crucial to engage in hierarchical reasoning across spatial and temporal scales. This entails planning abstract subgoal sequences, visually reasoning about the underlying plans, and executing actions in accordance with the devised plan through visual-motor control. We propose Compositional Foundation Models for Hierarchical Planning (HiP), a foundation model which leverages multiple expert foundation model trained on language, vision and action data individually jointly together to solve long-horizon tasks. We use "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08587","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/2309.08587/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":"2309.08587","created_at":"2026-07-05T06:52:49.953136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08587v2","created_at":"2026-07-05T06:52:49.953136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08587","created_at":"2026-07-05T06:52:49.953136+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWSX7FNMBCD7","created_at":"2026-07-05T06:52:49.953136+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWSX7FNMBCD746MI","created_at":"2026-07-05T06:52:49.953136+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWSX7FNM","created_at":"2026-07-05T06:52:49.953136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06418","citing_title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16054","citing_title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","ref_index":266,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23468","citing_title":"Multi-Modal Manipulation via Multi-Modal Policy Consensus","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2402.10885","citing_title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2310.10639","citing_title":"Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21232","citing_title":"ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21232","citing_title":"ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03065","citing_title":"OGPO: Sample Efficient Full-Finetuning of Generative Control Policies","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS","json":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS.json","graph_json":"https://pith.science/api/pith-number/CWSX7FNMBCD746MICE55TNFLJS/graph.json","events_json":"https://pith.science/api/pith-number/CWSX7FNMBCD746MICE55TNFLJS/events.json","paper":"https://pith.science/paper/CWSX7FNM"},"agent_actions":{"view_html":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS","download_json":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS.json","view_paper":"https://pith.science/paper/CWSX7FNM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08587&json=true","fetch_graph":"https://pith.science/api/pith-number/CWSX7FNMBCD746MICE55TNFLJS/graph.json","fetch_events":"https://pith.science/api/pith-number/CWSX7FNMBCD746MICE55TNFLJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS/action/storage_attestation","attest_author":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS/action/author_attestation","sign_citation":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS/action/citation_signature","submit_replication":"https://pith.science/pith/CWSX7FNMBCD746MICE55TNFLJS/action/replication_record"}},"created_at":"2026-07-05T06:52:49.953136+00:00","updated_at":"2026-07-05T06:52:49.953136+00:00"}