{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:W72U54EM6JM6AFMSCZ2WGNQYOU","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":"fc00dd4fc93249f7711aecafb0ac83095c2cddc021603f778dda91bfb816636f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T03:36:45Z","title_canon_sha256":"ce1df9c4aedfc5b510016fe61bdea52f45c722cbf6bbe28de375b721a58dea43"},"schema_version":"1.0","source":{"id":"2503.09029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.09029","created_at":"2026-07-05T10:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"2503.09029v1","created_at":"2026-07-05T10:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09029","created_at":"2026-07-05T10:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"W72U54EM6JM6","created_at":"2026-07-05T10:29:46Z"},{"alias_kind":"pith_short_16","alias_value":"W72U54EM6JM6AFMS","created_at":"2026-07-05T10:29:46Z"},{"alias_kind":"pith_short_8","alias_value":"W72U54EM","created_at":"2026-07-05T10:29:46Z"}],"graph_snapshots":[{"event_id":"sha256:09570a7a9e41e6e713be37824c2638db0b5eb936c511644d3c18be3b8b38b0b9","target":"graph","created_at":"2026-07-05T10:29:46Z","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/2503.09029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability. Therefore, this work proposes a difficulty-aware self-training (DAST) framework that focuses on improving both the quantity and quality of self-generated responses on challenging queries during self-training. DAST is specified in three components: 1) sampling-based difficulty level estimation, 2) difficulty-aware data augmentation, and 3) the self-training algorithm using SFT and DPO respectively. Experiments on m","authors_text":"Boyang Xue, Fei Mi, Hongling Xu, Hongru Wang, Kam-Fai Wong, Lifeng Shang, Qi Zhu, Qun Liu, Rui Wang, Sheng Wang, Yasheng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T03:36:45Z","title":"DAST: Difficulty-Aware Self-Training on Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09029","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":"sha256:6545ff778ea84ff4466c0c5e17f6d16b97fff6a71cdcca096027c68bb2c38671","target":"record","created_at":"2026-07-05T10:29:46Z","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":"fc00dd4fc93249f7711aecafb0ac83095c2cddc021603f778dda91bfb816636f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T03:36:45Z","title_canon_sha256":"ce1df9c4aedfc5b510016fe61bdea52f45c722cbf6bbe28de375b721a58dea43"},"schema_version":"1.0","source":{"id":"2503.09029","kind":"arxiv","version":1}},"canonical_sha256":"b7f54ef08cf259e015921675633618750c3cbe5fe08ead1dda4a45b694fd834f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7f54ef08cf259e015921675633618750c3cbe5fe08ead1dda4a45b694fd834f","first_computed_at":"2026-07-05T10:29:46.247988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:46.247988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g/+tYTEmqN40sUheFk2KhP07Ju72a7nOm2HempLIdGEaE6KYJHEPDHyjh9qtfQTyKHYz5IooFnhwUItJBsFCAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:46.248564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.09029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6545ff778ea84ff4466c0c5e17f6d16b97fff6a71cdcca096027c68bb2c38671","sha256:09570a7a9e41e6e713be37824c2638db0b5eb936c511644d3c18be3b8b38b0b9"],"state_sha256":"4fa9820e8d34ddd66afe6a72ed92568f62e644d41e48d3f4d2b53840dc4bedb5"}