{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QX4PKZJ3ZXNZW4ERJM24IRTEZD","short_pith_number":"pith:QX4PKZJ3","canonical_record":{"source":{"id":"2408.14037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-26T06:14:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41031844243055b70082e93363c5d7233c0e1adef1362f78654ee327408a2c53","abstract_canon_sha256":"662821a6de3b6afa13b4bf7c11dbb35648760550932749e8f6e88822e427a369"},"schema_version":"1.0"},"canonical_sha256":"85f8f5653bcddb9b70914b35c44664c8d2f1fe76f8fdb1b50ed7190ef96d6182","source":{"kind":"arxiv","id":"2408.14037","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14037","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14037v1","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14037","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"QX4PKZJ3ZXNZ","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"QX4PKZJ3ZXNZW4ER","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"QX4PKZJ3","created_at":"2026-07-05T10:17:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QX4PKZJ3ZXNZW4ERJM24IRTEZD","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14037","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-26T06:14:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"41031844243055b70082e93363c5d7233c0e1adef1362f78654ee327408a2c53","abstract_canon_sha256":"662821a6de3b6afa13b4bf7c11dbb35648760550932749e8f6e88822e427a369"},"schema_version":"1.0"},"canonical_sha256":"85f8f5653bcddb9b70914b35c44664c8d2f1fe76f8fdb1b50ed7190ef96d6182","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:49.132600Z","signature_b64":"5RvMnksxDz7ndR8SFwzTr1rg+aFVMHZzxmb8IJy6Rac/1CGMg/S4CY6tRXbAKlejsWMTbCs74v1AVllECC37Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f8f5653bcddb9b70914b35c44664c8d2f1fe76f8fdb1b50ed7190ef96d6182","last_reissued_at":"2026-07-05T10:17:49.132036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:49.132036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14037","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fOp8GCjSBo3i+hoI7PjyOyiWImYYPXQs9/ymB5Xq3x25sFOXqcR5HdUZE7mNTIK1RUultyoGn/DhAeZ+sv2/CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:28:09.478008Z"},"content_sha256":"c6b09b534fa08b9195201ca9551c3075a1ffe598fc15ba2453a44da376e68268","schema_version":"1.0","event_id":"sha256:c6b09b534fa08b9195201ca9551c3075a1ffe598fc15ba2453a44da376e68268"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QX4PKZJ3ZXNZW4ERJM24IRTEZD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chethan Bhateja, Dorsa Sadigh, Joey Hejna, Karl Pertsch, Yichen Jiang","submitted_at":"2024-08-26T06:14:25Z","abstract_excerpt":"Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language processing, little work in robotics has questioned what data such models should actually be trained on. In this work we investigate how to weigh different subsets or ``domains'' of robotics datasets for robot foundation model pre-training. Concrete, we use distributionally robust optimization (DRO) to maximize worst-case performance across all possible downstream do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14037","kind":"arxiv","version":1},"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/2408.14037/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DqeQl+lirorOB4pqCEabpzZrlNlB3U9iF5fHkW4ox6yGBndPJMYubGrQ7JNNI04vzVGsUn9vpFz+2/Wt5VxgDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T02:28:09.478496Z"},"content_sha256":"318d3c51e42ac7ae71357a0a59d2a9760ae0583f5153fc74f52e0ff800e4f9a2","schema_version":"1.0","event_id":"sha256:318d3c51e42ac7ae71357a0a59d2a9760ae0583f5153fc74f52e0ff800e4f9a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD/bundle.json","state_url":"https://pith.science/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T02:28:09Z","links":{"resolver":"https://pith.science/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD","bundle":"https://pith.science/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD/bundle.json","state":"https://pith.science/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QX4PKZJ3ZXNZW4ERJM24IRTEZD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QX4PKZJ3ZXNZW4ERJM24IRTEZD","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":"662821a6de3b6afa13b4bf7c11dbb35648760550932749e8f6e88822e427a369","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-26T06:14:25Z","title_canon_sha256":"41031844243055b70082e93363c5d7233c0e1adef1362f78654ee327408a2c53"},"schema_version":"1.0","source":{"id":"2408.14037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14037","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14037v1","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14037","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"QX4PKZJ3ZXNZ","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"QX4PKZJ3ZXNZW4ER","created_at":"2026-07-05T10:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"QX4PKZJ3","created_at":"2026-07-05T10:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:318d3c51e42ac7ae71357a0a59d2a9760ae0583f5153fc74f52e0ff800e4f9a2","target":"graph","created_at":"2026-07-05T10:17:49Z","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/2408.14037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Increasingly large imitation learning datasets are being collected with the goal of training foundation models for robotics. However, despite the fact that data selection has been of utmost importance in vision and natural language processing, little work in robotics has questioned what data such models should actually be trained on. In this work we investigate how to weigh different subsets or ``domains'' of robotics datasets for robot foundation model pre-training. Concrete, we use distributionally robust optimization (DRO) to maximize worst-case performance across all possible downstream do","authors_text":"Chethan Bhateja, Dorsa Sadigh, Joey Hejna, Karl Pertsch, Yichen Jiang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-26T06:14:25Z","title":"Re-Mix: Optimizing Data Mixtures for Large Scale Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14037","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:c6b09b534fa08b9195201ca9551c3075a1ffe598fc15ba2453a44da376e68268","target":"record","created_at":"2026-07-05T10:17:49Z","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":"662821a6de3b6afa13b4bf7c11dbb35648760550932749e8f6e88822e427a369","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-26T06:14:25Z","title_canon_sha256":"41031844243055b70082e93363c5d7233c0e1adef1362f78654ee327408a2c53"},"schema_version":"1.0","source":{"id":"2408.14037","kind":"arxiv","version":1}},"canonical_sha256":"85f8f5653bcddb9b70914b35c44664c8d2f1fe76f8fdb1b50ed7190ef96d6182","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85f8f5653bcddb9b70914b35c44664c8d2f1fe76f8fdb1b50ed7190ef96d6182","first_computed_at":"2026-07-05T10:17:49.132036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:49.132036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5RvMnksxDz7ndR8SFwzTr1rg+aFVMHZzxmb8IJy6Rac/1CGMg/S4CY6tRXbAKlejsWMTbCs74v1AVllECC37Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:49.132600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6b09b534fa08b9195201ca9551c3075a1ffe598fc15ba2453a44da376e68268","sha256:318d3c51e42ac7ae71357a0a59d2a9760ae0583f5153fc74f52e0ff800e4f9a2"],"state_sha256":"a1f81c994818878b783c7db9d446d77cd478d45dd624ef2c0a466c237ae221b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kGCrHjlnYU1U8M5Ak/LLtpCcPuNm1f+caLNjHnD8AFsn/6+kNRr5cxxSVZImL3KslHwq/Jj98ZNdQ0inrj4IAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T02:28:09.482061Z","bundle_sha256":"55f4dd832286142a3b1444f0821695b196316158fd1627628c2e84792745ccf4"}}