{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IMJPHJWW7CZS6V6GFBFJBC3HCN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c83a37017ed4c6191e6a05cb7e4ed6ee97358ee32e9f90f64331124ad3cc70b0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-16T14:25:29Z","title_canon_sha256":"8beb8d453394a183f3ff8e861bafe5b04130dfabf84bd1402949fb017afa82e1"},"schema_version":"1.0","source":{"id":"2506.13536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13536","created_at":"2026-07-05T11:22:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13536v1","created_at":"2026-07-05T11:22:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13536","created_at":"2026-07-05T11:22:21Z"},{"alias_kind":"pith_short_12","alias_value":"IMJPHJWW7CZS","created_at":"2026-07-05T11:22:21Z"},{"alias_kind":"pith_short_16","alias_value":"IMJPHJWW7CZS6V6G","created_at":"2026-07-05T11:22:21Z"},{"alias_kind":"pith_short_8","alias_value":"IMJPHJWW","created_at":"2026-07-05T11:22:21Z"}],"graph_snapshots":[{"event_id":"sha256:3137a6564fb412fbbddd609a6f1f72783b042b5392e3e850986e297d6e33ba69","target":"graph","created_at":"2026-07-05T11:22:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.13536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning from large multi-task demonstration datasets has emerged as a promising path for building generally-capable robots. As a result, 1000s of hours have been spent on building such large-scale datasets around the globe. Despite the continuous growth of such efforts, we still lack a systematic understanding of what data should be collected to improve the utility of a robotics dataset and facilitate downstream policy learning. In this work, we conduct a large-scale dataset composition study to answer this question. We develop a data generation framework to procedurally emulate com","authors_text":"Ajay Mandlekar, Danfei Xu, Kuancheng Wang, Matthew Bronars, Nadun Ranawaka Arachchige, Soroush Nasiriany, Vaibhav Saxena, Woo Chul Shin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-16T14:25:29Z","title":"What Matters in Learning from Large-Scale Datasets for Robot Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13536","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:39d9c625cd96a505b4ae6fa936450756a0439a740ea5b4d6397300c138238a92","target":"record","created_at":"2026-07-05T11:22:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c83a37017ed4c6191e6a05cb7e4ed6ee97358ee32e9f90f64331124ad3cc70b0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-16T14:25:29Z","title_canon_sha256":"8beb8d453394a183f3ff8e861bafe5b04130dfabf84bd1402949fb017afa82e1"},"schema_version":"1.0","source":{"id":"2506.13536","kind":"arxiv","version":1}},"canonical_sha256":"4312f3a6d6f8b32f57c6284a908b67134fa7e6b6bf7fc81659dfc574a0151815","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4312f3a6d6f8b32f57c6284a908b67134fa7e6b6bf7fc81659dfc574a0151815","first_computed_at":"2026-07-05T11:22:21.822050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:21.822050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LzSVpUHwDOj3CZVL/q59hwYDB7M+IcgM9PW82Lf1EiNvUOv0snW5QhJrCueAhgGxY1yg0rDolXfPkzJZYtTkBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:21.822532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39d9c625cd96a505b4ae6fa936450756a0439a740ea5b4d6397300c138238a92","sha256:3137a6564fb412fbbddd609a6f1f72783b042b5392e3e850986e297d6e33ba69"],"state_sha256":"8ab537e800590fda7e42d476fda3a2dd65a098ac07c2bbbe5015ba3e0e8cf69f"}