{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QSMJBTON7HYSTF5FNUCYM4HMX7","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":"7e06c6b02da3612d29ec6e8f1d9b844fc7d193648d1bae1153c6b1e7c331e990","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:06:24Z","title_canon_sha256":"4b45a0a6b940e9cd1c9701a70d402bc31d2503c5064054cc3b433b1069da6fdc"},"schema_version":"1.0","source":{"id":"2412.14780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14780","created_at":"2026-07-05T09:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14780v1","created_at":"2026-07-05T09:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14780","created_at":"2026-07-05T09:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"QSMJBTON7HYS","created_at":"2026-07-05T09:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"QSMJBTON7HYSTF5F","created_at":"2026-07-05T09:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"QSMJBTON","created_at":"2026-07-05T09:51:52Z"}],"graph_snapshots":[{"event_id":"sha256:aee6ae1c2a5d2754b31f65230cfea64389aad9bb39d157c5977ddcae3e86b206","target":"graph","created_at":"2026-07-05T09:51:52Z","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/2412.14780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When using agent-task datasets to enhance agent capabilities for Large Language Models (LLMs), current methodologies often treat all tokens within a sample equally. However, we argue that tokens serving different roles - specifically, reasoning tokens versus boilerplate tokens (e.g., those governing output format) - differ significantly in importance and learning complexity, necessitating their disentanglement and distinct treatment. To address this, we propose a novel Shuffle-Aware Discriminator (SHAD) for adaptive token discrimination. SHAD classifies tokens by exploiting predictability diff","authors_text":"Fuli Feng, Jianxin Ma, Junyang Lin, Yang Zhang, Zhenru Zhang, Ziang Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:06:24Z","title":"Disentangling Reasoning Tokens and Boilerplate Tokens For Language Model Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14780","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:b3e56d59e0a61420dd76f6deb9cc519fc582df2905952f6befcf02a0629d38dd","target":"record","created_at":"2026-07-05T09:51:52Z","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":"7e06c6b02da3612d29ec6e8f1d9b844fc7d193648d1bae1153c6b1e7c331e990","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T12:06:24Z","title_canon_sha256":"4b45a0a6b940e9cd1c9701a70d402bc31d2503c5064054cc3b433b1069da6fdc"},"schema_version":"1.0","source":{"id":"2412.14780","kind":"arxiv","version":1}},"canonical_sha256":"849890cdcdf9f12997a56d058670ecbfd5930fbc9e64cf9cfee3aa5bc4dcd078","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"849890cdcdf9f12997a56d058670ecbfd5930fbc9e64cf9cfee3aa5bc4dcd078","first_computed_at":"2026-07-05T09:51:52.704421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:52.704421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QCLLblsujKZ1JVNQgA0ixpVNooXeYbaHi3gliAIpbZA6ryF13CxkKY4G5OQSsqVfb8BcSr5s2CpmHQuQHTa8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:52.704891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3e56d59e0a61420dd76f6deb9cc519fc582df2905952f6befcf02a0629d38dd","sha256:aee6ae1c2a5d2754b31f65230cfea64389aad9bb39d157c5977ddcae3e86b206"],"state_sha256":"3e3aa33c4cf015b21742a5ff7a4fbc2b170af49f89a42b5a91105e53d2d7859c"}