{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FS3RZCHDJD63U6L4A5AADL2ABX","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":"2fc18de3006e99b86b9bfe2fc33d1913e3ee235a1f6f8f69fc42f2f1bb6681fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T00:05:14Z","title_canon_sha256":"630fffe87ac7a7630aa476e4c8a83064a68c8fe474c475f8b141ab17d60557ba"},"schema_version":"1.0","source":{"id":"2606.00437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00437","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00437v1","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00437","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"FS3RZCHDJD63","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"FS3RZCHDJD63U6L4","created_at":"2026-06-02T01:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"FS3RZCHD","created_at":"2026-06-02T01:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:ddd40a6d301184737e3d7d3d21334f62a3903136d66b6ba6880051672d1c6fa5","target":"graph","created_at":"2026-06-02T01:03:54Z","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/2606.00437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Process reward models (PRMs) are widely used in language-model training with dense step-level supervision. They assume PRM scores are stable proxies for step correctness under label-preserving transformations. These transformations change reasoning structure but preserve final answers. We argue this assumption is not well validated. Such transformations can change how PRM scores relate to correctness signals, leading to different failure modes across models.To address this gap, we introduce \\textbf{EST-PRM}, a stress-testing framework for dense process rewards. It applies three transformations","authors_text":"Anuj Sharma, Fariya Afrin, Ibne Farabi Shihab, Sanjeda Akter","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T00:05:14Z","title":"EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00437","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:d63f5d8a3de4788c7a718e16144968dff9892d56493ec0a743aa68cdc0aaf63f","target":"record","created_at":"2026-06-02T01:03:54Z","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":"2fc18de3006e99b86b9bfe2fc33d1913e3ee235a1f6f8f69fc42f2f1bb6681fb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T00:05:14Z","title_canon_sha256":"630fffe87ac7a7630aa476e4c8a83064a68c8fe474c475f8b141ab17d60557ba"},"schema_version":"1.0","source":{"id":"2606.00437","kind":"arxiv","version":1}},"canonical_sha256":"2cb71c88e348fdba797c074001af400dca8caee3ea7c3a1896944691568f6e90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cb71c88e348fdba797c074001af400dca8caee3ea7c3a1896944691568f6e90","first_computed_at":"2026-06-02T01:03:54.600494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:54.600494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PEzGM8ChfLkoax1i3JiDwKhL5p9Bkxnp1arst1XqVetHJQg9K22Vt3MXqpaX8D2phH4t3TqImOW/2Z+QeEDHCQ==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:54.600881Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d63f5d8a3de4788c7a718e16144968dff9892d56493ec0a743aa68cdc0aaf63f","sha256:ddd40a6d301184737e3d7d3d21334f62a3903136d66b6ba6880051672d1c6fa5"],"state_sha256":"e341269889987ae45d3b9fdc59d03a655e190936c98e9420165817b55c17a3b6"}