{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UTYSADMEPEU4EFTBHLS7ECW3AC","short_pith_number":"pith:UTYSADME","canonical_record":{"source":{"id":"2503.22456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-28T14:07:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bc8b1b8a5cd55f8efc7a261881eb766f2d159b437693ace45451504e30efbf2","abstract_canon_sha256":"dcacdb40cd64a1e5f95d12d761d0842c997fd79dc23a3f01523c7e53da1e5eb5"},"schema_version":"1.0"},"canonical_sha256":"a4f1200d847929c216613ae5f20adb00971a17a016f7bfb19ed360ed88cf392e","source":{"kind":"arxiv","id":"2503.22456","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UTYSADMEPEU4EFTBHLS7ECW3AC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.22456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-28T14:07:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5bc8b1b8a5cd55f8efc7a261881eb766f2d159b437693ace45451504e30efbf2","abstract_canon_sha256":"dcacdb40cd64a1e5f95d12d761d0842c997fd79dc23a3f01523c7e53da1e5eb5"},"schema_version":"1.0"},"canonical_sha256":"a4f1200d847929c216613ae5f20adb00971a17a016f7bfb19ed360ed88cf392e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:55.090452Z","signature_b64":"uXl41MHnA6+9DAtT+7gTUVHiI/oI3xumbmtsgBDj/fI7bvb/uhhBtuXQv4683JDktaUcX0/slcT01yj4CHX4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4f1200d847929c216613ae5f20adb00971a17a016f7bfb19ed360ed88cf392e","last_reissued_at":"2026-07-05T10:41:55.089971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:55.089971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.22456","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:41:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MWBl48ZS5gYITBnDW1Be8YGFuaQKeJr5Ri/KJ5pJGSE67ZDE/g8uyMAmGSCbzs/bwi753dZaZ07tlCpkU6tiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:13:02.108779Z"},"content_sha256":"72afbb017bd8293527b1ad589f45ee5c30592fb9168ef4cd994c87356af99d1c","schema_version":"1.0","event_id":"sha256:72afbb017bd8293527b1ad589f45ee5c30592fb9168ef4cd994c87356af99d1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UTYSADMEPEU4EFTBHLS7ECW3AC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Entropy-guided sequence weighting for efficient exploration in RL-based LLM fine-tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abdullah Vanlioglu","submitted_at":"2025-03-28T14:07:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22456","kind":"arxiv","version":2},"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/2503.22456/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":"2026-07-05T10:41:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7QXIUw2B8vicP8njagGq/wW3QUx3xGHhLkHdjdkWGLuS9/lDUUzdC/3NvfkhUe2i7nvOyenDki2NjHX5BEqEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T00:13:02.109264Z"},"content_sha256":"4a9d99413ed0972823ae8e8c10083db754965f6ec9689d26735f15c8880ee9b7","schema_version":"1.0","event_id":"sha256:4a9d99413ed0972823ae8e8c10083db754965f6ec9689d26735f15c8880ee9b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UTYSADMEPEU4EFTBHLS7ECW3AC/bundle.json","state_url":"https://pith.science/pith/UTYSADMEPEU4EFTBHLS7ECW3AC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UTYSADMEPEU4EFTBHLS7ECW3AC/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":"2026-08-08T00:13:02Z","links":{"resolver":"https://pith.science/pith/UTYSADMEPEU4EFTBHLS7ECW3AC","bundle":"https://pith.science/pith/UTYSADMEPEU4EFTBHLS7ECW3AC/bundle.json","state":"https://pith.science/pith/UTYSADMEPEU4EFTBHLS7ECW3AC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UTYSADMEPEU4EFTBHLS7ECW3AC/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHp2cI331MDEUBz6YFLwHcWcuL2ttbyGVg1W6Q2L0BPaiLoa2Z6jkvkl3bdg/3l1VNYwR3MXicN49O398jcPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T00:13:02.112844Z","bundle_sha256":"c127f1e7c078c45843db5316c11a2733b5c7156c508d083a7ff3e3d997cea298"}}