{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PF5A6TMY4NJIFF46EHLGM2QJZR","short_pith_number":"pith:PF5A6TMY","schema_version":"1.0","canonical_sha256":"797a0f4d98e35282979e21d6666a09cc68a4539d21ef5007e785d9c6023dc67c","source":{"kind":"arxiv","id":"2606.13233","version":1},"attestation_state":"computed","paper":{"title":"ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donghoon Yoo, Hanyul Ryu, Jae Gon Kim, Janghwan Lee, Jungwook Choi, Sihwa Lee, Soojung Ryu","submitted_at":"2026-06-11T11:47:40Z","abstract_excerpt":"Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on tok"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.13233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T11:47:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4b37b9dfc1fba834a958a7089b1a8251ca3fe573f21676a138b3381faad59f96","abstract_canon_sha256":"bb81bcd9fdd5453bc71b1f04f076dcdb474cbf44108799835b5fe06aa1ecd4b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:48.081678Z","signature_b64":"P9PUUMTLIHXCurkYigykqN5wldCyLxLLBllFyCAmpWXOUiEL5RafZ+zCf0axsbdxOPkAdATg5TD4GYf4FZBlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"797a0f4d98e35282979e21d6666a09cc68a4539d21ef5007e785d9c6023dc67c","last_reissued_at":"2026-06-12T01:09:48.081101Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:48.081101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donghoon Yoo, Hanyul Ryu, Jae Gon Kim, Janghwan Lee, Jungwook Choi, Sihwa Lee, Soojung Ryu","submitted_at":"2026-06-11T11:47:40Z","abstract_excerpt":"Large reasoning models (LRMs) improve complex problem-solving by generating long intermediate reasoning traces, but this substantially increases inference costs. NVFP4 inference offers a promising approach to reduce both computational and memory costs through hardware-supported low-precision execution. However, directly applying NVFP4 to LRMs introduces two practical limitations: reasoning accuracy degrades under quantization, and existing NVFP4 kernels do not fully realize latency benefits in small-batch autoregressive decoding. In this work, we analyze the effect of NVFP4 quantization on tok"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13233","kind":"arxiv","version":1},"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/2606.13233/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.13233","created_at":"2026-06-12T01:09:48.081184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13233v1","created_at":"2026-06-12T01:09:48.081184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13233","created_at":"2026-06-12T01:09:48.081184+00:00"},{"alias_kind":"pith_short_12","alias_value":"PF5A6TMY4NJI","created_at":"2026-06-12T01:09:48.081184+00:00"},{"alias_kind":"pith_short_16","alias_value":"PF5A6TMY4NJIFF46","created_at":"2026-06-12T01:09:48.081184+00:00"},{"alias_kind":"pith_short_8","alias_value":"PF5A6TMY","created_at":"2026-06-12T01:09:48.081184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR","json":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR.json","graph_json":"https://pith.science/api/pith-number/PF5A6TMY4NJIFF46EHLGM2QJZR/graph.json","events_json":"https://pith.science/api/pith-number/PF5A6TMY4NJIFF46EHLGM2QJZR/events.json","paper":"https://pith.science/paper/PF5A6TMY"},"agent_actions":{"view_html":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR","download_json":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR.json","view_paper":"https://pith.science/paper/PF5A6TMY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13233&json=true","fetch_graph":"https://pith.science/api/pith-number/PF5A6TMY4NJIFF46EHLGM2QJZR/graph.json","fetch_events":"https://pith.science/api/pith-number/PF5A6TMY4NJIFF46EHLGM2QJZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR/action/storage_attestation","attest_author":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR/action/author_attestation","sign_citation":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR/action/citation_signature","submit_replication":"https://pith.science/pith/PF5A6TMY4NJIFF46EHLGM2QJZR/action/replication_record"}},"created_at":"2026-06-12T01:09:48.081184+00:00","updated_at":"2026-06-12T01:09:48.081184+00:00"}