{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EQUFQFKWCA4LSZYVDQBGLT6ZEH","short_pith_number":"pith:EQUFQFKW","schema_version":"1.0","canonical_sha256":"24285815561038b967151c0265cfd921ccd42a539bbbf4eee6c9747ba7e6b36f","source":{"kind":"arxiv","id":"2606.23543","version":1},"attestation_state":"computed","paper":{"title":"VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Can Xu, Han Hu, Haoling Li, Jie Wu, Kai Zheng, Qingfeng Sun, Yujiu Yang","submitted_at":"2026-06-22T16:17:30Z","abstract_excerpt":"Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reliable. Yet existing data pipelines scale supervision while trusting the labeller, and policy-side methods assume the underlying answers are already correct. We instead treat scaling as a verifiable data-construction problem and decouple two axes before any policy update: prompt difficulty, expanded by route-specific evolution operators, and answer reliability, enforced by offline hypothesis-test falsification. We inst"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.23543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T16:17:30Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"e12f9ce96ab0479aee7f78533955e7ec3f4aa31e168f5086f15132d133197b86","abstract_canon_sha256":"cc66d0ef89f4c09bfcf5514690653c5522253bd997982ee7833abfc44e364ecc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:29.615309Z","signature_b64":"fmspTGdQ9dqTFoQ8XdDnayGLJgRuX4g/jPocABxuGfQU2+ewZF2jy7nA87vJokB4aiMvIDHGoJAVBpfVgS34Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24285815561038b967151c0265cfd921ccd42a539bbbf4eee6c9747ba7e6b36f","last_reissued_at":"2026-06-23T03:14:29.614819Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:29.614819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Can Xu, Han Hu, Haoling Li, Jie Wu, Kai Zheng, Qingfeng Sun, Yujiu Yang","submitted_at":"2026-06-22T16:17:30Z","abstract_excerpt":"Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labels themselves must remain reliable. Yet existing data pipelines scale supervision while trusting the labeller, and policy-side methods assume the underlying answers are already correct. We instead treat scaling as a verifiable data-construction problem and decouple two axes before any policy update: prompt difficulty, expanded by route-specific evolution operators, and answer reliability, enforced by offline hypothesis-test falsification. We inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23543","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/2606.23543/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.23543","created_at":"2026-06-23T03:14:29.614885+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23543v1","created_at":"2026-06-23T03:14:29.614885+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23543","created_at":"2026-06-23T03:14:29.614885+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQUFQFKWCA4L","created_at":"2026-06-23T03:14:29.614885+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQUFQFKWCA4LSZYV","created_at":"2026-06-23T03:14:29.614885+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQUFQFKW","created_at":"2026-06-23T03:14:29.614885+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH","json":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH.json","graph_json":"https://pith.science/api/pith-number/EQUFQFKWCA4LSZYVDQBGLT6ZEH/graph.json","events_json":"https://pith.science/api/pith-number/EQUFQFKWCA4LSZYVDQBGLT6ZEH/events.json","paper":"https://pith.science/paper/EQUFQFKW"},"agent_actions":{"view_html":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH","download_json":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH.json","view_paper":"https://pith.science/paper/EQUFQFKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23543&json=true","fetch_graph":"https://pith.science/api/pith-number/EQUFQFKWCA4LSZYVDQBGLT6ZEH/graph.json","fetch_events":"https://pith.science/api/pith-number/EQUFQFKWCA4LSZYVDQBGLT6ZEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH/action/storage_attestation","attest_author":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH/action/author_attestation","sign_citation":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH/action/citation_signature","submit_replication":"https://pith.science/pith/EQUFQFKWCA4LSZYVDQBGLT6ZEH/action/replication_record"}},"created_at":"2026-06-23T03:14:29.614885+00:00","updated_at":"2026-06-23T03:14:29.614885+00:00"}