{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:22IVXYKZWUQPE4M6A6CMSZEUIF","short_pith_number":"pith:22IVXYKZ","canonical_record":{"source":{"id":"2505.19126","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:47:39Z","cross_cats_sorted":[],"title_canon_sha256":"f73e3e02e53a9bf1fe4500a8d92d80d39699f300786f91b30509267ef457dcf9","abstract_canon_sha256":"a0a3f3f9dde74ec7377b1b2fef176b872b14c850bb439237aff198ffa05bcfe9"},"schema_version":"1.0"},"canonical_sha256":"d6915be159b520f2719e0784c964944151191fba9f921f3c47eedefd51dc05bb","source":{"kind":"arxiv","id":"2505.19126","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19126","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19126v1","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19126","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"22IVXYKZWUQP","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"22IVXYKZWUQPE4M6","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"22IVXYKZ","created_at":"2026-07-05T11:09:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:22IVXYKZWUQPE4M6A6CMSZEUIF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19126","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:47:39Z","cross_cats_sorted":[],"title_canon_sha256":"f73e3e02e53a9bf1fe4500a8d92d80d39699f300786f91b30509267ef457dcf9","abstract_canon_sha256":"a0a3f3f9dde74ec7377b1b2fef176b872b14c850bb439237aff198ffa05bcfe9"},"schema_version":"1.0"},"canonical_sha256":"d6915be159b520f2719e0784c964944151191fba9f921f3c47eedefd51dc05bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:25.335799Z","signature_b64":"f7rdZubVHcemwfjn0XneCy6NepmHjGlwKxgGdwOcVFP4nwIo9sHex/MeBd28rTOE3M6549y0CRxdX7mmfzNZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6915be159b520f2719e0784c964944151191fba9f921f3c47eedefd51dc05bb","last_reissued_at":"2026-07-05T11:09:25.335291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:25.335291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19126","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":"2026-07-05T11:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vr3ljBtg8oUaUHTcUayuf8X3wae7LUFLe8iCo7momBXnEs2IgtfhxIdY2p+N5YtmLQoQFsGt86z20nxnBZGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:21:01.727392Z"},"content_sha256":"8c71f60924d1caca5b884ac7fcbc17a882cae4ae9c37e74325ace7efa4346b7d","schema_version":"1.0","event_id":"sha256:8c71f60924d1caca5b884ac7fcbc17a882cae4ae9c37e74325ace7efa4346b7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:22IVXYKZWUQPE4M6A6CMSZEUIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMATH: A Multilingual Benchmark for Mathematical Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jing Sha, Ji-Rong Wen, Shijin Wang, Wayne Xin Zhao, Wenyang Luo","submitted_at":"2025-05-25T12:47:39Z","abstract_excerpt":"The advent of large reasoning models, such as OpenAI o1 and DeepSeek R1, has significantly advanced complex reasoning tasks. However, their capabilities in multilingual complex reasoning remain underexplored, with existing efforts largely focused on simpler tasks like MGSM. To address this gap, we introduce MMATH, a benchmark for multilingual complex reasoning spanning 374 high-quality math problems across 10 typologically diverse languages. Using MMATH, we observe that even advanced models like DeepSeek R1 exhibit substantial performance disparities across languages and suffer from a critical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19126","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/2505.19126/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":"2026-07-05T11:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbNUUZydzINQkDCwphZd9Dqc7HH8LQaVHMCr9m+7lZVlDInzUi1eqbe+N3c0pj0jinVaie//eRvAW6wPWY1MAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:21:01.727902Z"},"content_sha256":"6af33e8395f7d928c2b7b16a20a1cf8adfdf1b166e7825fdb0a759a502f3f4c2","schema_version":"1.0","event_id":"sha256:6af33e8395f7d928c2b7b16a20a1cf8adfdf1b166e7825fdb0a759a502f3f4c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/22IVXYKZWUQPE4M6A6CMSZEUIF/bundle.json","state_url":"https://pith.science/pith/22IVXYKZWUQPE4M6A6CMSZEUIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/22IVXYKZWUQPE4M6A6CMSZEUIF/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":"2026-08-08T18:21:01Z","links":{"resolver":"https://pith.science/pith/22IVXYKZWUQPE4M6A6CMSZEUIF","bundle":"https://pith.science/pith/22IVXYKZWUQPE4M6A6CMSZEUIF/bundle.json","state":"https://pith.science/pith/22IVXYKZWUQPE4M6A6CMSZEUIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/22IVXYKZWUQPE4M6A6CMSZEUIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:22IVXYKZWUQPE4M6A6CMSZEUIF","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":"a0a3f3f9dde74ec7377b1b2fef176b872b14c850bb439237aff198ffa05bcfe9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:47:39Z","title_canon_sha256":"f73e3e02e53a9bf1fe4500a8d92d80d39699f300786f91b30509267ef457dcf9"},"schema_version":"1.0","source":{"id":"2505.19126","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19126","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19126v1","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19126","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"22IVXYKZWUQP","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"22IVXYKZWUQPE4M6","created_at":"2026-07-05T11:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"22IVXYKZ","created_at":"2026-07-05T11:09:25Z"}],"graph_snapshots":[{"event_id":"sha256:6af33e8395f7d928c2b7b16a20a1cf8adfdf1b166e7825fdb0a759a502f3f4c2","target":"graph","created_at":"2026-07-05T11:09:25Z","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/2505.19126/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advent of large reasoning models, such as OpenAI o1 and DeepSeek R1, has significantly advanced complex reasoning tasks. However, their capabilities in multilingual complex reasoning remain underexplored, with existing efforts largely focused on simpler tasks like MGSM. To address this gap, we introduce MMATH, a benchmark for multilingual complex reasoning spanning 374 high-quality math problems across 10 typologically diverse languages. Using MMATH, we observe that even advanced models like DeepSeek R1 exhibit substantial performance disparities across languages and suffer from a critical","authors_text":"Jing Sha, Ji-Rong Wen, Shijin Wang, Wayne Xin Zhao, Wenyang Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:47:39Z","title":"MMATH: A Multilingual Benchmark for Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19126","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":"sha256:8c71f60924d1caca5b884ac7fcbc17a882cae4ae9c37e74325ace7efa4346b7d","target":"record","created_at":"2026-07-05T11:09:25Z","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":"a0a3f3f9dde74ec7377b1b2fef176b872b14c850bb439237aff198ffa05bcfe9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:47:39Z","title_canon_sha256":"f73e3e02e53a9bf1fe4500a8d92d80d39699f300786f91b30509267ef457dcf9"},"schema_version":"1.0","source":{"id":"2505.19126","kind":"arxiv","version":1}},"canonical_sha256":"d6915be159b520f2719e0784c964944151191fba9f921f3c47eedefd51dc05bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6915be159b520f2719e0784c964944151191fba9f921f3c47eedefd51dc05bb","first_computed_at":"2026-07-05T11:09:25.335291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:25.335291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f7rdZubVHcemwfjn0XneCy6NepmHjGlwKxgGdwOcVFP4nwIo9sHex/MeBd28rTOE3M6549y0CRxdX7mmfzNZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:25.335799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19126","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c71f60924d1caca5b884ac7fcbc17a882cae4ae9c37e74325ace7efa4346b7d","sha256:6af33e8395f7d928c2b7b16a20a1cf8adfdf1b166e7825fdb0a759a502f3f4c2"],"state_sha256":"644c79a0ce7d11ab46a0429855ee569883cce4d727b31bfe20b8e01407a973c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jru1dO9mhDizTz0KtDPelxkYOQlHN6ckYbm8ko9MvKgOVyTdvkTRfp0aD4bexEgifHrwPJTvBY5DBkeBSlAlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:21:01.732046Z","bundle_sha256":"b461b9881c2323f1d90dade3a6e09016c19fa60531d6291c8143476f54df0fee"}}