{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UTYSADMEPEU4EFTBHLS7ECW3AC","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":"dcacdb40cd64a1e5f95d12d761d0842c997fd79dc23a3f01523c7e53da1e5eb5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-28T14:07:51Z","title_canon_sha256":"5bc8b1b8a5cd55f8efc7a261881eb766f2d159b437693ace45451504e30efbf2"},"schema_version":"1.0","source":{"id":"2503.22456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.22456","created_at":"2026-07-05T10:41:55Z"},{"alias_kind":"arxiv_version","alias_value":"2503.22456v2","created_at":"2026-07-05T10:41:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22456","created_at":"2026-07-05T10:41:55Z"},{"alias_kind":"pith_short_12","alias_value":"UTYSADMEPEU4","created_at":"2026-07-05T10:41:55Z"},{"alias_kind":"pith_short_16","alias_value":"UTYSADMEPEU4EFTB","created_at":"2026-07-05T10:41:55Z"},{"alias_kind":"pith_short_8","alias_value":"UTYSADME","created_at":"2026-07-05T10:41:55Z"}],"graph_snapshots":[{"event_id":"sha256:4a9d99413ed0972823ae8e8c10083db754965f6ec9689d26735f15c8880ee9b7","target":"graph","created_at":"2026-07-05T10:41:55Z","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/2503.22456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Entropy-Guided Sequence Weighting (EGSW), a novel approach that enhances the exploration-exploitation tradeoff by dynamically assigning weights to generated outputs based on their advantage and entropy for Reinforcement Learning-based Large Language Model fine-tuning. EGSW integrates entropy regularization with advantage-based weighting to balance policy updates, enabling efficient exploration in high-dimensional state spaces. By employing temperature-scaled softmax weighting over sequences, EGSW prioritizing high-reward, high-uncertainty steps while maintaining training stability","authors_text":"Abdullah Vanlioglu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-28T14:07:51Z","title":"Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22456","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":"sha256:72afbb017bd8293527b1ad589f45ee5c30592fb9168ef4cd994c87356af99d1c","target":"record","created_at":"2026-07-05T10:41:55Z","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":"dcacdb40cd64a1e5f95d12d761d0842c997fd79dc23a3f01523c7e53da1e5eb5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-28T14:07:51Z","title_canon_sha256":"5bc8b1b8a5cd55f8efc7a261881eb766f2d159b437693ace45451504e30efbf2"},"schema_version":"1.0","source":{"id":"2503.22456","kind":"arxiv","version":2}},"canonical_sha256":"a4f1200d847929c216613ae5f20adb00971a17a016f7bfb19ed360ed88cf392e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4f1200d847929c216613ae5f20adb00971a17a016f7bfb19ed360ed88cf392e","first_computed_at":"2026-07-05T10:41:55.089971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:55.089971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uXl41MHnA6+9DAtT+7gTUVHiI/oI3xumbmtsgBDj/fI7bvb/uhhBtuXQv4683JDktaUcX0/slcT01yj4CHX4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:55.090452Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.22456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72afbb017bd8293527b1ad589f45ee5c30592fb9168ef4cd994c87356af99d1c","sha256:4a9d99413ed0972823ae8e8c10083db754965f6ec9689d26735f15c8880ee9b7"],"state_sha256":"46d996a8652d78266b25617b9737c2c05f8b0c8df9bfa53181a088ae83ba5896"}