{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UVKKH7MFGHQG22B7POPDPATBPP","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":"f9b02e508659b8a20edf7a162d484037f4a51d6e18a872b75b4cc46bdd7a2b90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T04:10:57Z","title_canon_sha256":"f95bb28957cc0cb08b299f7ea0c42c81321e759bf7442524fa1927f3688dc637"},"schema_version":"1.0","source":{"id":"2402.14270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14270","created_at":"2026-07-05T07:50:55Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14270v2","created_at":"2026-07-05T07:50:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14270","created_at":"2026-07-05T07:50:55Z"},{"alias_kind":"pith_short_12","alias_value":"UVKKH7MFGHQG","created_at":"2026-07-05T07:50:55Z"},{"alias_kind":"pith_short_16","alias_value":"UVKKH7MFGHQG22B7","created_at":"2026-07-05T07:50:55Z"},{"alias_kind":"pith_short_8","alias_value":"UVKKH7MF","created_at":"2026-07-05T07:50:55Z"}],"graph_snapshots":[{"event_id":"sha256:c0e1a5ead4f7d2dc6504247479583d5439b4e0f80e16c995a4bc74065afab932","target":"graph","created_at":"2026-07-05T07:50:55Z","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/2402.14270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the rapidly advancing arena of large language models (LLMs), a key challenge is to enhance their capabilities amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets, with a specific focus on selective retention of samples that incur moderately high losses. These samples are deemed informative and beneficial for model refinement, contrasting with the highest-loss samples, which would be discarded due to their correlation with data noise and complexity. We then form","authors_text":"Daouda Sow, Junjie Yang, Mingyuan Zhou, Tianlong Chen, Xuxi Chen, Yingbin Liang, Zhangyang Wang, Zhendong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T04:10:57Z","title":"Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14270","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:e806cb5fbabcf7d8108f189c769f3338bf73b4dadcf446e3809713c4d6120f52","target":"record","created_at":"2026-07-05T07:50:55Z","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":"f9b02e508659b8a20edf7a162d484037f4a51d6e18a872b75b4cc46bdd7a2b90","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T04:10:57Z","title_canon_sha256":"f95bb28957cc0cb08b299f7ea0c42c81321e759bf7442524fa1927f3688dc637"},"schema_version":"1.0","source":{"id":"2402.14270","kind":"arxiv","version":2}},"canonical_sha256":"a554a3fd8531e06d683f7b9e3782617bf4a3ae086c52643a69fbcd8c0b697933","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a554a3fd8531e06d683f7b9e3782617bf4a3ae086c52643a69fbcd8c0b697933","first_computed_at":"2026-07-05T07:50:55.847966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:55.847966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6dRnpqOEJl/GnPySrH3Vs+0NuRt2piNfr6ytVs6aabak0Yk+D6VOJC/P+ejfufe8dWvxiOjCc4593jVhJazfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:55.848390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e806cb5fbabcf7d8108f189c769f3338bf73b4dadcf446e3809713c4d6120f52","sha256:c0e1a5ead4f7d2dc6504247479583d5439b4e0f80e16c995a4bc74065afab932"],"state_sha256":"f039c409ce73bf90772eb0df3a12bbc0b5d6e841c8d58ab05a25ffbe2beca45c"}