{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CRHQGEAL2NXPWMS3QCF7CKIJGO","short_pith_number":"pith:CRHQGEAL","canonical_record":{"source":{"id":"2502.17407","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T18:36:15Z","cross_cats_sorted":[],"title_canon_sha256":"a019c48e9bea09b0ace05f27587a5e40b8171c129669322b3a5062f3fa4220d7","abstract_canon_sha256":"378df2230082c957fb6536626cf5d2cacc77807756772c28fbd4a7c0ffcc3dd9"},"schema_version":"1.0"},"canonical_sha256":"144f03100bd36efb325b808bf1290933a9501f13d4bf06b3052740191bd8d18c","source":{"kind":"arxiv","id":"2502.17407","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17407","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17407v2","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17407","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"CRHQGEAL2NXP","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"CRHQGEAL2NXPWMS3","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"CRHQGEAL","created_at":"2026-07-05T11:46:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CRHQGEAL2NXPWMS3QCF7CKIJGO","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17407","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T18:36:15Z","cross_cats_sorted":[],"title_canon_sha256":"a019c48e9bea09b0ace05f27587a5e40b8171c129669322b3a5062f3fa4220d7","abstract_canon_sha256":"378df2230082c957fb6536626cf5d2cacc77807756772c28fbd4a7c0ffcc3dd9"},"schema_version":"1.0"},"canonical_sha256":"144f03100bd36efb325b808bf1290933a9501f13d4bf06b3052740191bd8d18c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:39.557415Z","signature_b64":"zfpZj+AeO1y2Jg1dHBDagqVzSbnKyxD7xxfAVBout2YXs4gU83AjIFLuKc0c55nZsvcc8dmz8FKJXp5Hv3VtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"144f03100bd36efb325b808bf1290933a9501f13d4bf06b3052740191bd8d18c","last_reissued_at":"2026-07-05T11:46:39.556920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:39.556920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17407","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:46:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"reH/9nUNmfmOTBLJTF0dQ8ZE312DWrSODX9o8alBFSB4TPsGK1A2uMxwnLStBoFeEFH3orR50lu41B/pobHbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:41:57.510693Z"},"content_sha256":"65e74499f9348883a612ce040682d761ce2a58c97e112c3aac645d8b324aceb1","schema_version":"1.0","event_id":"sha256:65e74499f9348883a612ce040682d761ce2a58c97e112c3aac645d8b324aceb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CRHQGEAL2NXPWMS3QCF7CKIJGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guijin Son, Hyunwoo Ko, James Thorne, Jiwoo Hong","submitted_at":"2025-02-24T18:36:15Z","abstract_excerpt":"Scaling pre-training compute has proven effective for achieving mulitlinguality, but does the same hold for test-time scaling? In this work, we introduce MCLM, a multilingual math benchmark featuring competition-level problems in 55 languages. We test three test-time scaling methods-Outcome Reward Modeling (ORM), Process Reward Modeling (ORM), and Budget Forcing (BF)-on both Qwen2.5-1.5B Math and MR1-1.5B, a multilingual LLM we trained for extended reasoning. Our experiments show that using Qwen2.5-1.5B Math with ORM achieves a score of 35.8 on MCLM, while BF on MR1-1.5B attains 35.2. Although"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17407","kind":"arxiv","version":2},"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/2502.17407/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":"2026-07-05T11:46:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3ui3fZ/9Ch8LN7MwQ3Rwarav9rlpHJj7RShSdmsfGTljYfG/KoxRXrTLb3aJh0Yh3rGeg+8cF48pilzjWEFZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:41:57.511590Z"},"content_sha256":"854a54b62621db661b5eb2a9b2a98f1d20ebda31e93058fb9872003ceb1ff664","schema_version":"1.0","event_id":"sha256:854a54b62621db661b5eb2a9b2a98f1d20ebda31e93058fb9872003ceb1ff664"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO/bundle.json","state_url":"https://pith.science/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO/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":"2026-08-08T09:41:57Z","links":{"resolver":"https://pith.science/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO","bundle":"https://pith.science/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO/bundle.json","state":"https://pith.science/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRHQGEAL2NXPWMS3QCF7CKIJGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CRHQGEAL2NXPWMS3QCF7CKIJGO","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":"378df2230082c957fb6536626cf5d2cacc77807756772c28fbd4a7c0ffcc3dd9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T18:36:15Z","title_canon_sha256":"a019c48e9bea09b0ace05f27587a5e40b8171c129669322b3a5062f3fa4220d7"},"schema_version":"1.0","source":{"id":"2502.17407","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17407","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17407v2","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17407","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"pith_short_12","alias_value":"CRHQGEAL2NXP","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"pith_short_16","alias_value":"CRHQGEAL2NXPWMS3","created_at":"2026-07-05T11:46:39Z"},{"alias_kind":"pith_short_8","alias_value":"CRHQGEAL","created_at":"2026-07-05T11:46:39Z"}],"graph_snapshots":[{"event_id":"sha256:854a54b62621db661b5eb2a9b2a98f1d20ebda31e93058fb9872003ceb1ff664","target":"graph","created_at":"2026-07-05T11:46:39Z","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/2502.17407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling pre-training compute has proven effective for achieving mulitlinguality, but does the same hold for test-time scaling? In this work, we introduce MCLM, a multilingual math benchmark featuring competition-level problems in 55 languages. We test three test-time scaling methods-Outcome Reward Modeling (ORM), Process Reward Modeling (ORM), and Budget Forcing (BF)-on both Qwen2.5-1.5B Math and MR1-1.5B, a multilingual LLM we trained for extended reasoning. Our experiments show that using Qwen2.5-1.5B Math with ORM achieves a score of 35.8 on MCLM, while BF on MR1-1.5B attains 35.2. Although","authors_text":"Guijin Son, Hyunwoo Ko, James Thorne, Jiwoo Hong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T18:36:15Z","title":"Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17407","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":"sha256:65e74499f9348883a612ce040682d761ce2a58c97e112c3aac645d8b324aceb1","target":"record","created_at":"2026-07-05T11:46:39Z","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":"378df2230082c957fb6536626cf5d2cacc77807756772c28fbd4a7c0ffcc3dd9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-24T18:36:15Z","title_canon_sha256":"a019c48e9bea09b0ace05f27587a5e40b8171c129669322b3a5062f3fa4220d7"},"schema_version":"1.0","source":{"id":"2502.17407","kind":"arxiv","version":2}},"canonical_sha256":"144f03100bd36efb325b808bf1290933a9501f13d4bf06b3052740191bd8d18c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"144f03100bd36efb325b808bf1290933a9501f13d4bf06b3052740191bd8d18c","first_computed_at":"2026-07-05T11:46:39.556920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:39.556920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zfpZj+AeO1y2Jg1dHBDagqVzSbnKyxD7xxfAVBout2YXs4gU83AjIFLuKc0c55nZsvcc8dmz8FKJXp5Hv3VtAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:39.557415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17407","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65e74499f9348883a612ce040682d761ce2a58c97e112c3aac645d8b324aceb1","sha256:854a54b62621db661b5eb2a9b2a98f1d20ebda31e93058fb9872003ceb1ff664"],"state_sha256":"8676f3caec20633d2a1365959a80002a9c253cbb24f17ba32e700ad14d5edb9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7wtljB1uNxcsMutpo7yJGR+tg63qWgc4JJETlJmbeCwyStnJ4nUmcmq0a393csGtTB4yoQGLDfD+URMDtsMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:41:57.517344Z","bundle_sha256":"d61993a7a2aca6caaadd7349233e7dfcd41fc90e09e02cd8dbf22057877071d9"}}