{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MAXCRX555ZGVIDHHETOWKWQU2M","short_pith_number":"pith:MAXCRX55","schema_version":"1.0","canonical_sha256":"602e28dfbdee4d540ce724dd655a14d32d0ed234e38beedb6a06fdd7c8013232","source":{"kind":"arxiv","id":"2407.15840","version":3},"attestation_state":"computed","paper":{"title":"QueST: Self-Supervised Skill Abstractions for Learning Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Albert Wilcox, Animesh Garg, Atharva Mete, Haotian Xue, Yongxin Chen","submitted_at":"2024-07-22T17:57:59Z","abstract_excerpt":"Generalization capabilities, or rather a lack thereof, is one of the most important unsolved problems in the field of robot learning, and while several large scale efforts have set out to tackle this problem, unsolved it remains. In this paper, we hypothesize that learning temporal action abstractions using latent variable models (LVMs), which learn to map data to a compressed latent space and back, is a promising direction towards low-level skills that can readily be used for new tasks. Although several works have attempted to show this, they have generally been limited by architectures that "},"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":"2407.15840","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-22T17:57:59Z","cross_cats_sorted":[],"title_canon_sha256":"84868cc27c27615b60af1dad0d6b610ef4b9e31e2632d2888fcd10374ade1030","abstract_canon_sha256":"baaf2a1713e49c7ff666344448ae66f1e6b12cac6417c4e7d7697dc46c77ebb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:37.511414Z","signature_b64":"DYEkhGS3QjM+6hjGskJ95Ib3Nz90V0PmR5XugFnop2skIDXo8z5BHuDozwjnMeVeLxKwYLsj0lqQ4yBfyP/pBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"602e28dfbdee4d540ce724dd655a14d32d0ed234e38beedb6a06fdd7c8013232","last_reissued_at":"2026-07-05T09:05:37.510944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:37.510944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QueST: Self-Supervised Skill Abstractions for Learning Continuous Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Albert Wilcox, Animesh Garg, Atharva Mete, Haotian Xue, Yongxin Chen","submitted_at":"2024-07-22T17:57:59Z","abstract_excerpt":"Generalization capabilities, or rather a lack thereof, is one of the most important unsolved problems in the field of robot learning, and while several large scale efforts have set out to tackle this problem, unsolved it remains. In this paper, we hypothesize that learning temporal action abstractions using latent variable models (LVMs), which learn to map data to a compressed latent space and back, is a promising direction towards low-level skills that can readily be used for new tasks. Although several works have attempted to show this, they have generally been limited by architectures that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15840","kind":"arxiv","version":3},"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/2407.15840/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":"2407.15840","created_at":"2026-07-05T09:05:37.511002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15840v3","created_at":"2026-07-05T09:05:37.511002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15840","created_at":"2026-07-05T09:05:37.511002+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAXCRX555ZGV","created_at":"2026-07-05T09:05:37.511002+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAXCRX555ZGVIDHH","created_at":"2026-07-05T09:05:37.511002+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAXCRX55","created_at":"2026-07-05T09:05:37.511002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19138","citing_title":"COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19138","citing_title":"COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07339","citing_title":"Real-Time Execution of Action Chunking Flow Policies","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19734","citing_title":"UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09747","citing_title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M","json":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M.json","graph_json":"https://pith.science/api/pith-number/MAXCRX555ZGVIDHHETOWKWQU2M/graph.json","events_json":"https://pith.science/api/pith-number/MAXCRX555ZGVIDHHETOWKWQU2M/events.json","paper":"https://pith.science/paper/MAXCRX55"},"agent_actions":{"view_html":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M","download_json":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M.json","view_paper":"https://pith.science/paper/MAXCRX55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15840&json=true","fetch_graph":"https://pith.science/api/pith-number/MAXCRX555ZGVIDHHETOWKWQU2M/graph.json","fetch_events":"https://pith.science/api/pith-number/MAXCRX555ZGVIDHHETOWKWQU2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M/action/storage_attestation","attest_author":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M/action/author_attestation","sign_citation":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M/action/citation_signature","submit_replication":"https://pith.science/pith/MAXCRX555ZGVIDHHETOWKWQU2M/action/replication_record"}},"created_at":"2026-07-05T09:05:37.511002+00:00","updated_at":"2026-07-05T09:05:37.511002+00:00"}