{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:4B5WMF725OVD6FUYFB7P2QK6WB","short_pith_number":"pith:4B5WMF72","canonical_record":{"source":{"id":"2507.00432","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-01T05:23:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"336fa8cf47311762979f709847d68feaae704b54ee009a90a7d886f730c9f106","abstract_canon_sha256":"00e49dba5ded089212ca29a8316090a26c77a71120d21d8e1fb4f3782c9b1d57"},"schema_version":"1.0"},"canonical_sha256":"e07b6617faebaa3f1698287efd415eb07152a229e02a2863720efb48cf61a4c7","source":{"kind":"arxiv","id":"2507.00432","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00432","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00432v2","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00432","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"pith_short_12","alias_value":"4B5WMF725OVD","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"pith_short_16","alias_value":"4B5WMF725OVD6FUY","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"pith_short_8","alias_value":"4B5WMF72","created_at":"2026-05-19T00:54:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:4B5WMF725OVD6FUYFB7P2QK6WB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00432","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-01T05:23:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"336fa8cf47311762979f709847d68feaae704b54ee009a90a7d886f730c9f106","abstract_canon_sha256":"00e49dba5ded089212ca29a8316090a26c77a71120d21d8e1fb4f3782c9b1d57"},"schema_version":"1.0"},"canonical_sha256":"e07b6617faebaa3f1698287efd415eb07152a229e02a2863720efb48cf61a4c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T00:54:51.301064Z","signature_b64":"T042PHwYLa+bLXoIz24XWUob1sj3M3g+KCgS7afDizyr2opts8MK5zExWKe924gHAFo8+uPEEZXtTzkqrygoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e07b6617faebaa3f1698287efd415eb07152a229e02a2863720efb48cf61a4c7","last_reissued_at":"2026-05-19T00:54:51.297971Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T00:54:51.297971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00432","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":"2026-05-19T00:54:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ae/tnkkbhYqg0DvQbOCc6WF0vX9FhWbOhwhMfmP6xoY3L6KMwBGINPU5iU/M9pNhl2/egIjEpVnUfpeGArelCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:34:08.240016Z"},"content_sha256":"d202182cdbb7b372e76d9e8ffea05ea4a711e9061ca8bb091208f4430eec25ad","schema_version":"1.0","event_id":"sha256:d202182cdbb7b372e76d9e8ffea05ea4a711e9061ca8bb091208f4430eec25ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:4B5WMF725OVD6FUYFB7P2QK6WB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Graham Neubig, Maggie Huan, Minxin Du, Radha Poovendran, Seungone Kim, Tuney Zheng, Xiang Yue, Xiaoyu Xu, Yuetai Li","submitted_at":"2025-07-01T05:23:05Z","abstract_excerpt":"Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00432","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":""},"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":"2026-05-19T00:54:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Lwe7OJoeaUB9SOrbV0wxE8R59DIUghJiMXfPfZ+Ny+dDMALPzx5hVI12aschzjnpV2GUeSeNIwZdHYHkAFYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T05:34:08.240475Z"},"content_sha256":"63f2672198d2b1dae0e612b4afbac8b93554eb396122b62f2e4e243723126299","schema_version":"1.0","event_id":"sha256:63f2672198d2b1dae0e612b4afbac8b93554eb396122b62f2e4e243723126299"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4B5WMF725OVD6FUYFB7P2QK6WB/bundle.json","state_url":"https://pith.science/pith/4B5WMF725OVD6FUYFB7P2QK6WB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4B5WMF725OVD6FUYFB7P2QK6WB/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":"2026-05-20T05:34:08Z","links":{"resolver":"https://pith.science/pith/4B5WMF725OVD6FUYFB7P2QK6WB","bundle":"https://pith.science/pith/4B5WMF725OVD6FUYFB7P2QK6WB/bundle.json","state":"https://pith.science/pith/4B5WMF725OVD6FUYFB7P2QK6WB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4B5WMF725OVD6FUYFB7P2QK6WB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4B5WMF725OVD6FUYFB7P2QK6WB","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":"00e49dba5ded089212ca29a8316090a26c77a71120d21d8e1fb4f3782c9b1d57","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-01T05:23:05Z","title_canon_sha256":"336fa8cf47311762979f709847d68feaae704b54ee009a90a7d886f730c9f106"},"schema_version":"1.0","source":{"id":"2507.00432","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00432","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00432v2","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00432","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"pith_short_12","alias_value":"4B5WMF725OVD","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"pith_short_16","alias_value":"4B5WMF725OVD6FUY","created_at":"2026-05-19T00:54:51Z"},{"alias_kind":"pith_short_8","alias_value":"4B5WMF72","created_at":"2026-05-19T00:54:51Z"}],"graph_snapshots":[{"event_id":"sha256:63f2672198d2b1dae0e612b4afbac8b93554eb396122b62f2e4e243723126299","target":"graph","created_at":"2026-05-19T00:54:51Z","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"},"paper":{"abstract_excerpt":"Math reasoning has become the poster child of progress in large language models (LLMs), with new models rapidly surpassing human-level performance on benchmarks like MATH and AIME. But as math leaderboards improve week by week, it is worth asking: do these gains reflect broader problem-solving ability or just narrow overfitting? To answer this question, we evaluate over 20 open-weight reasoning-tuned models across a broad suite of tasks, including math, scientific QA, agent planning, coding, and standard instruction-following. We surprisingly find that most models that succeed in math fail to ","authors_text":"Graham Neubig, Maggie Huan, Minxin Du, Radha Poovendran, Seungone Kim, Tuney Zheng, Xiang Yue, Xiaoyu Xu, Yuetai Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-01T05:23:05Z","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00432","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:d202182cdbb7b372e76d9e8ffea05ea4a711e9061ca8bb091208f4430eec25ad","target":"record","created_at":"2026-05-19T00:54:51Z","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":"00e49dba5ded089212ca29a8316090a26c77a71120d21d8e1fb4f3782c9b1d57","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-01T05:23:05Z","title_canon_sha256":"336fa8cf47311762979f709847d68feaae704b54ee009a90a7d886f730c9f106"},"schema_version":"1.0","source":{"id":"2507.00432","kind":"arxiv","version":2}},"canonical_sha256":"e07b6617faebaa3f1698287efd415eb07152a229e02a2863720efb48cf61a4c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e07b6617faebaa3f1698287efd415eb07152a229e02a2863720efb48cf61a4c7","first_computed_at":"2026-05-19T00:54:51.297971Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-19T00:54:51.297971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T042PHwYLa+bLXoIz24XWUob1sj3M3g+KCgS7afDizyr2opts8MK5zExWKe924gHAFo8+uPEEZXtTzkqrygoCg==","signature_status":"signed_v1","signed_at":"2026-05-19T00:54:51.301064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00432","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d202182cdbb7b372e76d9e8ffea05ea4a711e9061ca8bb091208f4430eec25ad","sha256:63f2672198d2b1dae0e612b4afbac8b93554eb396122b62f2e4e243723126299"],"state_sha256":"2123dabcd6519e5af00653d0d260deddea2a21788d026037263503326551f41a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vIcRLAdAhVzu4IU78o5a8f/swmaY6OivizG/UNrs+n7ooPq0DcLAL94I4wnu/A4TNMeDQUs0clDVF8nXcpCNBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T05:34:08.243491Z","bundle_sha256":"692be41a3c76c6fbceb1db046cf45a94a894ff7eff2ef8269bc29aabf28b0d0e"}}