{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:25BV3Y7HBUEAM5F5LMZWKMI7OE","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":"3958ef7841f0a1bcc8a403a4ceef910881b72d946523c6ceb4639e996742bd2e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T10:37:23Z","title_canon_sha256":"b94b726dbf335a9fd466d550e38a69aacb1d0b631f21bb878a9a75e3f3bf0077"},"schema_version":"1.0","source":{"id":"2606.18910","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18910","created_at":"2026-06-19T16:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18910v1","created_at":"2026-06-19T16:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18910","created_at":"2026-06-19T16:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"25BV3Y7HBUEA","created_at":"2026-06-19T16:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"25BV3Y7HBUEAM5F5","created_at":"2026-06-19T16:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"25BV3Y7H","created_at":"2026-06-19T16:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:621937964a7273f4b349c7f8e948d429ab04a2759d7ff73f1e9a37198fbb4903","target":"graph","created_at":"2026-06-19T16:11:51Z","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/2606.18910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Language Model (LLM) reasoning. However, standard post-training methods primarily optimize single-shot objectives, creating a fundamental misalignment with multi-step inference dynamics. While recent work treats this as multi-turn reinforcement learning (RL), conventional approaches optimize over the multi-step trajectories directly, failing to further exploit the high-quality mistakes in intermediate steps that model can learn from correcting them. We propose a two-stage iterative framework that a","authors_text":"Amr Sharaf, Arijit Biswas, Hongzhou Lin, Mingyi Hong, Mohammad Ghavamzadeh, Ruida Zhou, Xinyan Zhao, Yuanxin Liu, Zhaoran Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T10:37:23Z","title":"REVES: REvision and VErification--Augmented Training for Test-Time Scaling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18910","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":"sha256:40c74a5021e0768a9bdd7c62f6b94557c04284be62bee29b678c4b72154d7e71","target":"record","created_at":"2026-06-19T16:11:51Z","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":"3958ef7841f0a1bcc8a403a4ceef910881b72d946523c6ceb4639e996742bd2e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T10:37:23Z","title_canon_sha256":"b94b726dbf335a9fd466d550e38a69aacb1d0b631f21bb878a9a75e3f3bf0077"},"schema_version":"1.0","source":{"id":"2606.18910","kind":"arxiv","version":1}},"canonical_sha256":"d7435de3e70d080674bd5b3365311f711ec971562209f3b1bf67b2ff63e90582","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7435de3e70d080674bd5b3365311f711ec971562209f3b1bf67b2ff63e90582","first_computed_at":"2026-06-19T16:11:51.642043Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:51.642043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XrtCb/pvZ5AGZ6/5R7Uxrux6p6xU0OT/7PaftE6my069pQEUd6ade1m5z8Ps6QxlNFnZ95s7e6zhcHtizautCA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:51.642486Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18910","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40c74a5021e0768a9bdd7c62f6b94557c04284be62bee29b678c4b72154d7e71","sha256:621937964a7273f4b349c7f8e948d429ab04a2759d7ff73f1e9a37198fbb4903"],"state_sha256":"b75280fc783b6d87a898abf09e51e059116d71b5a00c5ddca5d57fc6548e9c32"}