{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FS3RZCHDJD63U6L4A5AADL2ABX","short_pith_number":"pith:FS3RZCHD","canonical_record":{"source":{"id":"2606.00437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T00:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"630fffe87ac7a7630aa476e4c8a83064a68c8fe474c475f8b141ab17d60557ba","abstract_canon_sha256":"2fc18de3006e99b86b9bfe2fc33d1913e3ee235a1f6f8f69fc42f2f1bb6681fb"},"schema_version":"1.0"},"canonical_sha256":"2cb71c88e348fdba797c074001af400dca8caee3ea7c3a1896944691568f6e90","source":{"kind":"arxiv","id":"2606.00437","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FS3RZCHDJD63U6L4A5AADL2ABX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.00437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-30T00:05:14Z","cross_cats_sorted":[],"title_canon_sha256":"630fffe87ac7a7630aa476e4c8a83064a68c8fe474c475f8b141ab17d60557ba","abstract_canon_sha256":"2fc18de3006e99b86b9bfe2fc33d1913e3ee235a1f6f8f69fc42f2f1bb6681fb"},"schema_version":"1.0"},"canonical_sha256":"2cb71c88e348fdba797c074001af400dca8caee3ea7c3a1896944691568f6e90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:54.600881Z","signature_b64":"PEzGM8ChfLkoax1i3JiDwKhL5p9Bkxnp1arst1XqVetHJQg9K22Vt3MXqpaX8D2phH4t3TqImOW/2Z+QeEDHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb71c88e348fdba797c074001af400dca8caee3ea7c3a1896944691568f6e90","last_reissued_at":"2026-06-02T01:03:54.600494Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:54.600494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.00437","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xEfH3XwMnzhBCJVa24IimD2ucNvP+Oq8W6LPyN4Emyr0uTrqY6AizTHuBuc/xeU5fWJ9X+wYhutjgJKWr3eDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:43:42.452584Z"},"content_sha256":"d63f5d8a3de4788c7a718e16144968dff9892d56493ec0a743aa68cdc0aaf63f","schema_version":"1.0","event_id":"sha256:d63f5d8a3de4788c7a718e16144968dff9892d56493ec0a743aa68cdc0aaf63f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FS3RZCHDJD63U6L4A5AADL2ABX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anuj Sharma, Fariya Afrin, Ibne Farabi Shihab, Sanjeda Akter","submitted_at":"2026-05-30T00:05:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00437","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/2606.00437/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dFXzjp+vHA2SRKsdrFaXH1MT0XSd1vwOJE/5UdZNyJD5EWex06s6e6MulR5rFSSLiKa9p3TaJLDaWzsxuObAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:43:42.452958Z"},"content_sha256":"ddd40a6d301184737e3d7d3d21334f62a3903136d66b6ba6880051672d1c6fa5","schema_version":"1.0","event_id":"sha256:ddd40a6d301184737e3d7d3d21334f62a3903136d66b6ba6880051672d1c6fa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FS3RZCHDJD63U6L4A5AADL2ABX/bundle.json","state_url":"https://pith.science/pith/FS3RZCHDJD63U6L4A5AADL2ABX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FS3RZCHDJD63U6L4A5AADL2ABX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T09:43:42Z","links":{"resolver":"https://pith.science/pith/FS3RZCHDJD63U6L4A5AADL2ABX","bundle":"https://pith.science/pith/FS3RZCHDJD63U6L4A5AADL2ABX/bundle.json","state":"https://pith.science/pith/FS3RZCHDJD63U6L4A5AADL2ABX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FS3RZCHDJD63U6L4A5AADL2ABX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKsfNa9JAyvX7l7t5MY56Ttp89wcuxGOnrx6Cv7RqgYgZKLcAck6y+bBdthPF6DNVn7oblKSIYo5mAbY7hnQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:43:42.454925Z","bundle_sha256":"261b41af33016716b14de115382a5c8ead6a2d4aae01d9193352b8b29bce1ef1"}}