{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RHSOEBKKDBTJOM7QBI63EM333E","short_pith_number":"pith:RHSOEBKK","schema_version":"1.0","canonical_sha256":"89e4e2054a18669733f00a3db2337bd92ded3110a82e6832c66201d62c2808ce","source":{"kind":"arxiv","id":"2406.07539","version":2},"attestation_state":"computed","paper":{"title":"BAKU: An Efficient Transformer for Multi-Task Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Siddhant Haldar, Zhuoran Peng","submitted_at":"2024-06-11T17:58:54Z","abstract_excerpt":"Training generalist agents capable of solving diverse tasks is challenging, often requiring large datasets of expert demonstrations. This is particularly problematic in robotics, where each data point requires physical execution of actions in the real world. Thus, there is a pressing need for architectures that can effectively leverage the available training data. In this work, we present BAKU, a simple transformer architecture that enables efficient learning of multi-task robot policies. BAKU builds upon recent advancements in offline imitation learning and meticulously combines observation t"},"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":"2406.07539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-11T17:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"aa5f981d10ed86182b8d3a98177ca5ce1e6119665d535e2d6384edc120a0d15e","abstract_canon_sha256":"708e5f7c4716350bad609b4149ecd6581f4bebd7df9635f82c43a5ad76b88695"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:55.108615Z","signature_b64":"dtYbagfO/aPv7gO9alvUGxw5rAIPxTOYL/XIYzZPS/9nhCHjy6+GlI9YNNvtHzaZlrm/oB2DfsMTvF/IcPB+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89e4e2054a18669733f00a3db2337bd92ded3110a82e6832c66201d62c2808ce","last_reissued_at":"2026-07-05T08:44:55.108176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:55.108176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAKU: An Efficient Transformer for Multi-Task Policy Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Siddhant Haldar, Zhuoran Peng","submitted_at":"2024-06-11T17:58:54Z","abstract_excerpt":"Training generalist agents capable of solving diverse tasks is challenging, often requiring large datasets of expert demonstrations. This is particularly problematic in robotics, where each data point requires physical execution of actions in the real world. Thus, there is a pressing need for architectures that can effectively leverage the available training data. In this work, we present BAKU, a simple transformer architecture that enables efficient learning of multi-task robot policies. BAKU builds upon recent advancements in offline imitation learning and meticulously combines observation t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07539","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/2406.07539/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":"2406.07539","created_at":"2026-07-05T08:44:55.108235+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07539v2","created_at":"2026-07-05T08:44:55.108235+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07539","created_at":"2026-07-05T08:44:55.108235+00:00"},{"alias_kind":"pith_short_12","alias_value":"RHSOEBKKDBTJ","created_at":"2026-07-05T08:44:55.108235+00:00"},{"alias_kind":"pith_short_16","alias_value":"RHSOEBKKDBTJOM7Q","created_at":"2026-07-05T08:44:55.108235+00:00"},{"alias_kind":"pith_short_8","alias_value":"RHSOEBKK","created_at":"2026-07-05T08:44:55.108235+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06491","citing_title":"TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00229","citing_title":"Continuous Reasoning for Vision-Language-Action","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29570","citing_title":"Hierarchical Policy Learning via Spectral Decomposition","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25537","citing_title":"Action-Prior Denoising for Smooth Real-Time Chunking","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00110","citing_title":"General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18727","citing_title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01433","citing_title":"AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11665","citing_title":"Nautilus: From One Prompt to Plug-and-Play Robot Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E","json":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E.json","graph_json":"https://pith.science/api/pith-number/RHSOEBKKDBTJOM7QBI63EM333E/graph.json","events_json":"https://pith.science/api/pith-number/RHSOEBKKDBTJOM7QBI63EM333E/events.json","paper":"https://pith.science/paper/RHSOEBKK"},"agent_actions":{"view_html":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E","download_json":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E.json","view_paper":"https://pith.science/paper/RHSOEBKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07539&json=true","fetch_graph":"https://pith.science/api/pith-number/RHSOEBKKDBTJOM7QBI63EM333E/graph.json","fetch_events":"https://pith.science/api/pith-number/RHSOEBKKDBTJOM7QBI63EM333E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E/action/storage_attestation","attest_author":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E/action/author_attestation","sign_citation":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E/action/citation_signature","submit_replication":"https://pith.science/pith/RHSOEBKKDBTJOM7QBI63EM333E/action/replication_record"}},"created_at":"2026-07-05T08:44:55.108235+00:00","updated_at":"2026-07-05T08:44:55.108235+00:00"}