{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CWGHMEMW4JCPDHENVPUFRVB66U","short_pith_number":"pith:CWGHMEMW","canonical_record":{"source":{"id":"2305.10429","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:58:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09e9671ae95ded18ffafdf0c1d0bda7690860ca9c99d28de5eabd68b6b5aa6f0","abstract_canon_sha256":"080c8e43d4f39066a368bf7a5ddecb760bc25eb88dd1bc9de7118ce58eb05037"},"schema_version":"1.0"},"canonical_sha256":"158c761196e244f19c8dabe858d43ef52a0ef11ef088f26169d956e7b0c0fa27","source":{"kind":"arxiv","id":"2305.10429","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10429","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10429v4","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10429","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"CWGHMEMW4JCP","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"CWGHMEMW4JCPDHEN","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"CWGHMEMW","created_at":"2026-07-05T07:14:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CWGHMEMW4JCPDHENVPUFRVB66U","target":"record","payload":{"canonical_record":{"source":{"id":"2305.10429","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:58:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"09e9671ae95ded18ffafdf0c1d0bda7690860ca9c99d28de5eabd68b6b5aa6f0","abstract_canon_sha256":"080c8e43d4f39066a368bf7a5ddecb760bc25eb88dd1bc9de7118ce58eb05037"},"schema_version":"1.0"},"canonical_sha256":"158c761196e244f19c8dabe858d43ef52a0ef11ef088f26169d956e7b0c0fa27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:53.565311Z","signature_b64":"VYMXwy2Dq30AmZbJ9R8sguVHPds6FDnwmTTZAZq/NA5jt0fu73LKs7Rnd1AlEwx41lAqxDLL5Po+V98WKCKpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158c761196e244f19c8dabe858d43ef52a0ef11ef088f26169d956e7b0c0fa27","last_reissued_at":"2026-07-05T07:14:53.564770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:53.564770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.10429","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaVGjClrfKBGxbVvw2FPHAeBnY2WXsiZTOZknsxMFqg03n6N6rM7SrVDX9dx9Lj2sj3l9aqAcz/LG8p13f5rCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:32:53.381025Z"},"content_sha256":"00d78d654dcc1e7b32045384cdb3c390362d7863a05261943ffa5df8827f9d83","schema_version":"1.0","event_id":"sha256:00d78d654dcc1e7b32045384cdb3c390362d7863a05261943ffa5df8827f9d83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CWGHMEMW4JCPDHENVPUFRVB66U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adams Wei Yu, Hanxiao Liu, Hieu Pham, Nan Du, Percy Liang, Quoc V. Le, Sang Michael Xie, Tengyu Ma, Xuanyi Dong, Yifeng Lu","submitted_at":"2023-05-17T17:58:13Z","abstract_excerpt":"The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affect language model (LM) performance. In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a small proxy model using group distributionally robust optimization (Group DRO) over domains to produce domain weights (mixture proportions) without knowledge of downstream tasks. We then resample a dataset with these domain weights and train a larger, full-sized model. In our experiments, we use DoReMi on a 280M-parameter proxy model to set the domain weights f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10429","kind":"arxiv","version":4},"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/2305.10429/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":"2026-07-05T07:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GSf1PxiNQIJqQF7+6ETCpMwAQNJussNIHt/yFkV6jGxiF++5DaSbWvqN7IuFxt8fQTEV0M7WEIgyiSS3ItB/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:32:53.381532Z"},"content_sha256":"bae4908f074fddd0235052a9df54b0ab61762c29a6201049f81a641771ce0e6a","schema_version":"1.0","event_id":"sha256:bae4908f074fddd0235052a9df54b0ab61762c29a6201049f81a641771ce0e6a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWGHMEMW4JCPDHENVPUFRVB66U/bundle.json","state_url":"https://pith.science/pith/CWGHMEMW4JCPDHENVPUFRVB66U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWGHMEMW4JCPDHENVPUFRVB66U/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":"2026-08-06T09:32:53Z","links":{"resolver":"https://pith.science/pith/CWGHMEMW4JCPDHENVPUFRVB66U","bundle":"https://pith.science/pith/CWGHMEMW4JCPDHENVPUFRVB66U/bundle.json","state":"https://pith.science/pith/CWGHMEMW4JCPDHENVPUFRVB66U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWGHMEMW4JCPDHENVPUFRVB66U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CWGHMEMW4JCPDHENVPUFRVB66U","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":"080c8e43d4f39066a368bf7a5ddecb760bc25eb88dd1bc9de7118ce58eb05037","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:58:13Z","title_canon_sha256":"09e9671ae95ded18ffafdf0c1d0bda7690860ca9c99d28de5eabd68b6b5aa6f0"},"schema_version":"1.0","source":{"id":"2305.10429","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10429","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10429v4","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10429","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"CWGHMEMW4JCP","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"pith_short_16","alias_value":"CWGHMEMW4JCPDHEN","created_at":"2026-07-05T07:14:53Z"},{"alias_kind":"pith_short_8","alias_value":"CWGHMEMW","created_at":"2026-07-05T07:14:53Z"}],"graph_snapshots":[{"event_id":"sha256:bae4908f074fddd0235052a9df54b0ab61762c29a6201049f81a641771ce0e6a","target":"graph","created_at":"2026-07-05T07:14:53Z","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/2305.10429/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affect language model (LM) performance. In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a small proxy model using group distributionally robust optimization (Group DRO) over domains to produce domain weights (mixture proportions) without knowledge of downstream tasks. We then resample a dataset with these domain weights and train a larger, full-sized model. In our experiments, we use DoReMi on a 280M-parameter proxy model to set the domain weights f","authors_text":"Adams Wei Yu, Hanxiao Liu, Hieu Pham, Nan Du, Percy Liang, Quoc V. Le, Sang Michael Xie, Tengyu Ma, Xuanyi Dong, Yifeng Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:58:13Z","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10429","kind":"arxiv","version":4},"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":"sha256:00d78d654dcc1e7b32045384cdb3c390362d7863a05261943ffa5df8827f9d83","target":"record","created_at":"2026-07-05T07:14:53Z","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":"080c8e43d4f39066a368bf7a5ddecb760bc25eb88dd1bc9de7118ce58eb05037","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T17:58:13Z","title_canon_sha256":"09e9671ae95ded18ffafdf0c1d0bda7690860ca9c99d28de5eabd68b6b5aa6f0"},"schema_version":"1.0","source":{"id":"2305.10429","kind":"arxiv","version":4}},"canonical_sha256":"158c761196e244f19c8dabe858d43ef52a0ef11ef088f26169d956e7b0c0fa27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"158c761196e244f19c8dabe858d43ef52a0ef11ef088f26169d956e7b0c0fa27","first_computed_at":"2026-07-05T07:14:53.564770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:14:53.564770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VYMXwy2Dq30AmZbJ9R8sguVHPds6FDnwmTTZAZq/NA5jt0fu73LKs7Rnd1AlEwx41lAqxDLL5Po+V98WKCKpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:14:53.565311Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10429","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00d78d654dcc1e7b32045384cdb3c390362d7863a05261943ffa5df8827f9d83","sha256:bae4908f074fddd0235052a9df54b0ab61762c29a6201049f81a641771ce0e6a"],"state_sha256":"2a05140a34bad084597817409fb6c5129130e43b179023a2a0b77d9976f93b11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S3WMdeA5HDthlJz/BImDuJOrtOnaPiQjojx3VUCMHgLrPfMUixvlln2CEbKqyF3V75ChV+zJx+P6lzYARGSwDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:32:53.385375Z","bundle_sha256":"34067ae83f63262c8d737629ef5b472a585e8432864f436d7a6004c9f197b48f"}}