{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L47S34273GOIRAZOSTLRWHU7UC","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":"2bc4d81a92d91460b4e8c6a9ccb81c2110fa3bed298afc75c8ea8191a776b982","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:55:10Z","title_canon_sha256":"a83843d5f587166d79e5b1d79973bf1a3633d8261d890d2530407b067c44711a"},"schema_version":"1.0","source":{"id":"2505.09603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09603","created_at":"2026-06-23T01:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09603v2","created_at":"2026-06-23T01:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09603","created_at":"2026-06-23T01:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"L47S34273GOI","created_at":"2026-06-23T01:12:45Z"},{"alias_kind":"pith_short_16","alias_value":"L47S34273GOIRAZO","created_at":"2026-06-23T01:12:45Z"},{"alias_kind":"pith_short_8","alias_value":"L47S3427","created_at":"2026-06-23T01:12:45Z"}],"graph_snapshots":[{"event_id":"sha256:4547ad6cc4a730461a5ccc65f30c3086b07eebf2029e745b064169b209140d1b","target":"graph","created_at":"2026-06-23T01:12:45Z","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/2505.09603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, the robotics community has amassed ever larger and more diverse datasets to train generalist policies. However, while these policies achieve strong mean performance across a variety of tasks, they often underperform on individual, specialized tasks and require further tuning on newly acquired task-specific data. Combining task-specific data with carefully curated subsets of large prior datasets via co-training can produce better specialized policies, but selecting data naively may actually harm downstream performance. To address this, we introduce DataMIL, a data selection framework ","authors_text":"Alaa Khaddaj, Aleksander Madry, Andrew Ilyas, Logan Engstrom, Roberto Mart\\'in-Mart\\'in, Shivin Dass","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:55:10Z","title":"DataMIL: Selecting Data for Robot Imitation Learning with Datamodels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09603","kind":"arxiv","version":2},"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":"sha256:3555a60910dae365cb52ea5119b7ae0382e221bbe5621ec3849325474d025a6f","target":"record","created_at":"2026-06-23T01:12:45Z","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":"2bc4d81a92d91460b4e8c6a9ccb81c2110fa3bed298afc75c8ea8191a776b982","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:55:10Z","title_canon_sha256":"a83843d5f587166d79e5b1d79973bf1a3633d8261d890d2530407b067c44711a"},"schema_version":"1.0","source":{"id":"2505.09603","kind":"arxiv","version":2}},"canonical_sha256":"5f3f2df35fd99c88832e94d71b1e9fa0a19abcc9ee60eb355addafcbf7b137e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f3f2df35fd99c88832e94d71b1e9fa0a19abcc9ee60eb355addafcbf7b137e0","first_computed_at":"2026-06-23T01:12:45.711263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:45.711263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FZ5zU85kmEXX/2yCZoxw2ZKymFGJj/ZkZ4Bfi3ouutGwwJqV4Ccc4fABFTTjez3jl5Qw4GCTdPX+ajO0efcODw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:45.711807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3555a60910dae365cb52ea5119b7ae0382e221bbe5621ec3849325474d025a6f","sha256:4547ad6cc4a730461a5ccc65f30c3086b07eebf2029e745b064169b209140d1b"],"state_sha256":"eae93a5f313d9d0f620a34135d84b81fe17fcf0ce476be7e73e49f480daaacc2"}