{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZQDKNU45H4BUQGUE32EJECTA5A","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":"01e0010ca548b461479dc1206e09bd968657f6526d98866f89812aa7ea039c2d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T22:21:56Z","title_canon_sha256":"4e434a6d3772e934bbee2b636b7dd6d73c279f159e83fbb4162ea9d56d8f0817"},"schema_version":"1.0","source":{"id":"2502.10581","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10581","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10581v2","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10581","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZQDKNU45H4BU","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_16","alias_value":"ZQDKNU45H4BUQGUE","created_at":"2026-07-05T10:39:47Z"},{"alias_kind":"pith_short_8","alias_value":"ZQDKNU45","created_at":"2026-07-05T10:39:47Z"}],"graph_snapshots":[{"event_id":"sha256:2c366f00bf2511b1d151c3a8a0084b6195f8b80398199b2f04bcadb48252e979","target":"graph","created_at":"2026-07-05T10:39:47Z","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/2502.10581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As large language models have evolved, it has become crucial to distinguish between process supervision and outcome supervision -- two key reinforcement learning approaches to complex reasoning tasks. While process supervision offers intuitive advantages for long-term credit assignment, the precise relationship between these paradigms has remained an open question. Conventional wisdom suggests that outcome supervision is fundamentally more challenging due to the trajectory-level coverage problem, leading to significant investment in collecting fine-grained process supervision data.\n  In this p","authors_text":"Alexander Rakhlin, Tengyang Xie, Zeyu Jia","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T22:21:56Z","title":"Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10581","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:c9dfdc6fe073aa24c5fde4ce1e177f232ba28a8c3b6726ef5e4eb9081e7521eb","target":"record","created_at":"2026-07-05T10:39:47Z","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":"01e0010ca548b461479dc1206e09bd968657f6526d98866f89812aa7ea039c2d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T22:21:56Z","title_canon_sha256":"4e434a6d3772e934bbee2b636b7dd6d73c279f159e83fbb4162ea9d56d8f0817"},"schema_version":"1.0","source":{"id":"2502.10581","kind":"arxiv","version":2}},"canonical_sha256":"cc06a6d39d3f03481a84de88920a60e81ad2fc6c5db82cb0b1a7ab7f34d5ead2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc06a6d39d3f03481a84de88920a60e81ad2fc6c5db82cb0b1a7ab7f34d5ead2","first_computed_at":"2026-07-05T10:39:47.277266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:47.277266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IBLF/7InVFmND5jIz4b8MxJlqAgMUEfKJOFBqfZvZVMyhVrE6PiOMPZDV/YODnS9ouaV7xun50Pni/M2Eei3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:47.277833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10581","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9dfdc6fe073aa24c5fde4ce1e177f232ba28a8c3b6726ef5e4eb9081e7521eb","sha256:2c366f00bf2511b1d151c3a8a0084b6195f8b80398199b2f04bcadb48252e979"],"state_sha256":"a90daef4f4282a21a5ed7145be8bd855d740ccb807995d915acd9b05d4ab4b9f"}