{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:APR7QEVTTGM7SZUG2PA6CXMUJS","short_pith_number":"pith:APR7QEVT","canonical_record":{"source":{"id":"2502.06733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T17:57:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3eef87dccaea1854c84df7d298164ebb702ac01d40f7890e89833b68b1085175","abstract_canon_sha256":"96b08f7932222c6a30bcba9c8d1d6d82db4c0a8f51a3d486ead1f12be9708932"},"schema_version":"1.0"},"canonical_sha256":"03e3f812b39999f96686d3c1e15d944cae3615fc2970e3f5532ebd3fcd898b12","source":{"kind":"arxiv","id":"2502.06733","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06733","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06733v1","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06733","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"APR7QEVTTGM7","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"APR7QEVTTGM7SZUG","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"APR7QEVT","created_at":"2026-07-05T10:12:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:APR7QEVTTGM7SZUG2PA6CXMUJS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.06733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T17:57:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3eef87dccaea1854c84df7d298164ebb702ac01d40f7890e89833b68b1085175","abstract_canon_sha256":"96b08f7932222c6a30bcba9c8d1d6d82db4c0a8f51a3d486ead1f12be9708932"},"schema_version":"1.0"},"canonical_sha256":"03e3f812b39999f96686d3c1e15d944cae3615fc2970e3f5532ebd3fcd898b12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:11.460996Z","signature_b64":"RF7KWOEHSBTb5lc3gg/Je+lrxe5CwnjllLB6rD5oOWxiVqMsOlODTobYDDHe01gbErnC304x0/FkYZ8uyY8DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03e3f812b39999f96686d3c1e15d944cae3615fc2970e3f5532ebd3fcd898b12","last_reissued_at":"2026-07-05T10:12:11.460519Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:11.460519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.06733","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":"2026-07-05T10:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z9GNV53IwwDuYbGuh2meDxGj3PNDkcAGSOGdu9zSN6ga0viYycOt16r9DEPof/usA2nOqHL2yepHOuXcUCVgBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:39:28.509639Z"},"content_sha256":"5a0484b8e3ace75711ef24d64b9338adde72d02ad6f90d26a03417c93d0836db","schema_version":"1.0","event_id":"sha256:5a0484b8e3ace75711ef24d64b9338adde72d02ad6f90d26a03417c93d0836db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:APR7QEVTTGM7SZUG2PA6CXMUJS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daouda Sow, Hans-Arno Jacobsen, Herbert Woisetschl\\\"ager, Saikiran Bulusu, Shiqiang Wang, Yingbin Liang","submitted_at":"2025-02-10T17:57:15Z","abstract_excerpt":"Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current training paradigms treat all samples equally, overlooking the importance or relevance of individual samples throughout the training process. Existing reweighting strategies, which primarily focus on group-level data importance, fail to leverage fine-grained instance-level information and do not adapt dynamically to individual sample importance as training progresses. In this paper, we introduce novel algorithms for d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06733","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/2502.06733/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":"2026-07-05T10:12:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DAsOIwDQnyBlE1WbyeB0oS06eOmzL+AFYLcpQCTyHX0wikxs7Zud4nCLvlQ6pq8pPisdpjYtws47c+rJ8e6nAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:39:28.510372Z"},"content_sha256":"3dd90881c586910007ab8a2c820707c94814700072f9f99d60aba65110b755b7","schema_version":"1.0","event_id":"sha256:3dd90881c586910007ab8a2c820707c94814700072f9f99d60aba65110b755b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/APR7QEVTTGM7SZUG2PA6CXMUJS/bundle.json","state_url":"https://pith.science/pith/APR7QEVTTGM7SZUG2PA6CXMUJS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/APR7QEVTTGM7SZUG2PA6CXMUJS/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":"2026-08-08T15:39:28Z","links":{"resolver":"https://pith.science/pith/APR7QEVTTGM7SZUG2PA6CXMUJS","bundle":"https://pith.science/pith/APR7QEVTTGM7SZUG2PA6CXMUJS/bundle.json","state":"https://pith.science/pith/APR7QEVTTGM7SZUG2PA6CXMUJS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/APR7QEVTTGM7SZUG2PA6CXMUJS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:APR7QEVTTGM7SZUG2PA6CXMUJS","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":"96b08f7932222c6a30bcba9c8d1d6d82db4c0a8f51a3d486ead1f12be9708932","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T17:57:15Z","title_canon_sha256":"3eef87dccaea1854c84df7d298164ebb702ac01d40f7890e89833b68b1085175"},"schema_version":"1.0","source":{"id":"2502.06733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06733","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06733v1","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06733","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_12","alias_value":"APR7QEVTTGM7","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_16","alias_value":"APR7QEVTTGM7SZUG","created_at":"2026-07-05T10:12:11Z"},{"alias_kind":"pith_short_8","alias_value":"APR7QEVT","created_at":"2026-07-05T10:12:11Z"}],"graph_snapshots":[{"event_id":"sha256:3dd90881c586910007ab8a2c820707c94814700072f9f99d60aba65110b755b7","target":"graph","created_at":"2026-07-05T10:12:11Z","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/2502.06733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current training paradigms treat all samples equally, overlooking the importance or relevance of individual samples throughout the training process. Existing reweighting strategies, which primarily focus on group-level data importance, fail to leverage fine-grained instance-level information and do not adapt dynamically to individual sample importance as training progresses. In this paper, we introduce novel algorithms for d","authors_text":"Daouda Sow, Hans-Arno Jacobsen, Herbert Woisetschl\\\"ager, Saikiran Bulusu, Shiqiang Wang, Yingbin Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T17:57:15Z","title":"Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06733","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":"sha256:5a0484b8e3ace75711ef24d64b9338adde72d02ad6f90d26a03417c93d0836db","target":"record","created_at":"2026-07-05T10:12:11Z","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":"96b08f7932222c6a30bcba9c8d1d6d82db4c0a8f51a3d486ead1f12be9708932","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-10T17:57:15Z","title_canon_sha256":"3eef87dccaea1854c84df7d298164ebb702ac01d40f7890e89833b68b1085175"},"schema_version":"1.0","source":{"id":"2502.06733","kind":"arxiv","version":1}},"canonical_sha256":"03e3f812b39999f96686d3c1e15d944cae3615fc2970e3f5532ebd3fcd898b12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03e3f812b39999f96686d3c1e15d944cae3615fc2970e3f5532ebd3fcd898b12","first_computed_at":"2026-07-05T10:12:11.460519Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:11.460519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RF7KWOEHSBTb5lc3gg/Je+lrxe5CwnjllLB6rD5oOWxiVqMsOlODTobYDDHe01gbErnC304x0/FkYZ8uyY8DCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:11.460996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a0484b8e3ace75711ef24d64b9338adde72d02ad6f90d26a03417c93d0836db","sha256:3dd90881c586910007ab8a2c820707c94814700072f9f99d60aba65110b755b7"],"state_sha256":"a2708fc1a42c654813977372e085dc9012313681b24f4e03671b0671615876f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AvgZ1BvKbTwNCVqh7ExQcb4EIrVTeeT6L9PWG+Fqwc2H7SLaLjsESWCSHVXuPHCuY0yZ6H+hTsj5JgOsudU+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:39:28.516365Z","bundle_sha256":"05a9664cfa4157e5110e25b6243372be41d80b47ab9c6949d5e9e73e7adbb639"}}