{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DKGLUWDEZ4KFERKZ6UFHSHOTWR","short_pith_number":"pith:DKGLUWDE","canonical_record":{"source":{"id":"2505.20380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:32:14Z","cross_cats_sorted":[],"title_canon_sha256":"6b4cb622152ac3a5f1a65f9d6c48a534a1bdfce86664d0a8f224e3c28b975808","abstract_canon_sha256":"1afc186edce55807633c1001f0dd28884d62e852bca03b1b624e1fc0fee1af00"},"schema_version":"1.0"},"canonical_sha256":"1a8cba5864cf14524559f50a791dd3b466028eeff7ffafcd97d1ae13e9f197e8","source":{"kind":"arxiv","id":"2505.20380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20380","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20380v1","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20380","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"DKGLUWDEZ4KF","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"DKGLUWDEZ4KFERKZ","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"DKGLUWDE","created_at":"2026-07-05T11:10:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DKGLUWDEZ4KFERKZ6UFHSHOTWR","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20380","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:32:14Z","cross_cats_sorted":[],"title_canon_sha256":"6b4cb622152ac3a5f1a65f9d6c48a534a1bdfce86664d0a8f224e3c28b975808","abstract_canon_sha256":"1afc186edce55807633c1001f0dd28884d62e852bca03b1b624e1fc0fee1af00"},"schema_version":"1.0"},"canonical_sha256":"1a8cba5864cf14524559f50a791dd3b466028eeff7ffafcd97d1ae13e9f197e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:11.960837Z","signature_b64":"1htQ3o3/WOsqD3ORWWS5/+D/Eyi/igheQ8xULWlh3wG7RIys9YiROW3S3gaIbOELeVNPVtzkrl0oO26yUNnDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a8cba5864cf14524559f50a791dd3b466028eeff7ffafcd97d1ae13e9f197e8","last_reissued_at":"2026-07-05T11:10:11.960370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:11.960370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20380","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":"2026-07-05T11:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HgfF++u65O/hCnyThfGQvs6lgVvcR9nCzKTzgWxf4/o3hxHRRxV9Kp3ZRkz+/X5zesh4tKWp14n04SJ1iNKFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:48:45.180175Z"},"content_sha256":"b4d0c1a4fecee4c5d6a485e79a35739c3cd13b889535c7555cbf97bd4e253503","schema_version":"1.0","event_id":"sha256:b4d0c1a4fecee4c5d6a485e79a35739c3cd13b889535c7555cbf97bd4e253503"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DKGLUWDEZ4KFERKZ6UFHSHOTWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Maria Ios Glarou, Martin Jaggi, Simin Fan","submitted_at":"2025-05-26T17:32:14Z","abstract_excerpt":"The performance of large language models (LLMs) across diverse downstream applications is fundamentally governed by the quality and composition of their pretraining corpora. Existing domain reweighting algorithms primarily optimize data mixtures for a single target task, thereby resulting in models that overfit to specialized objectives while exhibiting substantial performance degradation on other benchmarks. This paper introduces Group Robust Multi-target Adaptive PrEtraining (GRAPE), a novel multi-source-multi-target domain reweighting framework designed to calibrate pretraining data mixture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20380","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/2505.20380/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":"2026-07-05T11:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXQ8ASzlTHHCw0+02K1psnmhHgYatgn/viksTrZpWIhAbHCm1DeXb2Uwzw9N71GWbqSym1N50LxF8iPmt84yCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T18:48:45.180664Z"},"content_sha256":"524174495d0d5e7a9a6622d9c5b9ca2318ca54e77856afdeff06f3fc9d652fa5","schema_version":"1.0","event_id":"sha256:524174495d0d5e7a9a6622d9c5b9ca2318ca54e77856afdeff06f3fc9d652fa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR/bundle.json","state_url":"https://pith.science/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR/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":"2026-08-14T18:48:45Z","links":{"resolver":"https://pith.science/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR","bundle":"https://pith.science/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR/bundle.json","state":"https://pith.science/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DKGLUWDEZ4KFERKZ6UFHSHOTWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DKGLUWDEZ4KFERKZ6UFHSHOTWR","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":"1afc186edce55807633c1001f0dd28884d62e852bca03b1b624e1fc0fee1af00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:32:14Z","title_canon_sha256":"6b4cb622152ac3a5f1a65f9d6c48a534a1bdfce86664d0a8f224e3c28b975808"},"schema_version":"1.0","source":{"id":"2505.20380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20380","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20380v1","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20380","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"DKGLUWDEZ4KF","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"DKGLUWDEZ4KFERKZ","created_at":"2026-07-05T11:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"DKGLUWDE","created_at":"2026-07-05T11:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:524174495d0d5e7a9a6622d9c5b9ca2318ca54e77856afdeff06f3fc9d652fa5","target":"graph","created_at":"2026-07-05T11:10:11Z","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/2505.20380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of large language models (LLMs) across diverse downstream applications is fundamentally governed by the quality and composition of their pretraining corpora. Existing domain reweighting algorithms primarily optimize data mixtures for a single target task, thereby resulting in models that overfit to specialized objectives while exhibiting substantial performance degradation on other benchmarks. This paper introduces Group Robust Multi-target Adaptive PrEtraining (GRAPE), a novel multi-source-multi-target domain reweighting framework designed to calibrate pretraining data mixture","authors_text":"Maria Ios Glarou, Martin Jaggi, Simin Fan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:32:14Z","title":"GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20380","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:b4d0c1a4fecee4c5d6a485e79a35739c3cd13b889535c7555cbf97bd4e253503","target":"record","created_at":"2026-07-05T11:10:11Z","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":"1afc186edce55807633c1001f0dd28884d62e852bca03b1b624e1fc0fee1af00","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:32:14Z","title_canon_sha256":"6b4cb622152ac3a5f1a65f9d6c48a534a1bdfce86664d0a8f224e3c28b975808"},"schema_version":"1.0","source":{"id":"2505.20380","kind":"arxiv","version":1}},"canonical_sha256":"1a8cba5864cf14524559f50a791dd3b466028eeff7ffafcd97d1ae13e9f197e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a8cba5864cf14524559f50a791dd3b466028eeff7ffafcd97d1ae13e9f197e8","first_computed_at":"2026-07-05T11:10:11.960370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:11.960370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1htQ3o3/WOsqD3ORWWS5/+D/Eyi/igheQ8xULWlh3wG7RIys9YiROW3S3gaIbOELeVNPVtzkrl0oO26yUNnDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:11.960837Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4d0c1a4fecee4c5d6a485e79a35739c3cd13b889535c7555cbf97bd4e253503","sha256:524174495d0d5e7a9a6622d9c5b9ca2318ca54e77856afdeff06f3fc9d652fa5"],"state_sha256":"93737c7c98cf663201f6866a4d602fed77ee727b9d8f2a6c71e7f2ec7036a28f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5un5XTm6ao3TfIi8w3f4LiPkLlppJj7Q63KQE3eO79w0BOkRRW/MRRujIPRWBMTuj6x4Ykg3C5jWl221DWf6DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T18:48:45.185781Z","bundle_sha256":"f404f6bdf4b040123ca7c422017d4e8c5f4e4ee7ddc9fd4a6966c9fced3b8828"}}