{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VIPPQC5TP22IXB77XMII7BNZ6J","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":"4cdbbdf81a62437cdddf48381cf0b3041048e2f593198c3a120a99d09bec8ef3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T17:51:33Z","title_canon_sha256":"0a16729182233b755fe1421fb7ce861453bf30410a9ebfc2a680274f095ca0bd"},"schema_version":"1.0","source":{"id":"2508.03682","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03682","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03682v4","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03682","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"pith_short_12","alias_value":"VIPPQC5TP22I","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"pith_short_16","alias_value":"VIPPQC5TP22IXB77","created_at":"2026-07-05T12:08:05Z"},{"alias_kind":"pith_short_8","alias_value":"VIPPQC5T","created_at":"2026-07-05T12:08:05Z"}],"graph_snapshots":[{"event_id":"sha256:b4b23145e68ceb3f512b77c774dc32ba1a0130a56d23eac49dc802aa6a1e48cb","target":"graph","created_at":"2026-07-05T12:08:05Z","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/2508.03682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can large language models improve without external data -- by generating their own questions and answers? We hypothesize that a pre-trained language model can improve its reasoning skills given only a single prompt specifying the topic (e.g., algebra word problems) and asking the model to generate its own questions. To do this, we propose Self-Questioning Language Models (SQLM): an asymmetric self-play framework where a proposer is given the topic and generates a question for a solver, who tries to answer it. Both the proposer and solver are trained via reinforcement learning. The proposer rec","authors_text":"Deepak Pathak, Hao Liu, Katerina Fragkiadaki, Lili Chen, Mihir Prabhudesai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T17:51:33Z","title":"Self-Questioning Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03682","kind":"arxiv","version":4},"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":"sha256:42249dc115e7a263a0a614c800adb3cb9d127e118a1e7d5f2abd094b1eaa3347","target":"record","created_at":"2026-07-05T12:08:05Z","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":"4cdbbdf81a62437cdddf48381cf0b3041048e2f593198c3a120a99d09bec8ef3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-05T17:51:33Z","title_canon_sha256":"0a16729182233b755fe1421fb7ce861453bf30410a9ebfc2a680274f095ca0bd"},"schema_version":"1.0","source":{"id":"2508.03682","kind":"arxiv","version":4}},"canonical_sha256":"aa1ef80bb37eb48b87ffbb108f85b9f26d5816c48658efe80dd9402bb2b84343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa1ef80bb37eb48b87ffbb108f85b9f26d5816c48658efe80dd9402bb2b84343","first_computed_at":"2026-07-05T12:08:05.931157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:05.931157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LN4OtY+gig6OgpF8QHMtfRQL4Uj8EYtF7dD6gE1Em98iYmW4XFd2Spo5t+/1ffiffznis8G+GaTSnx1W3XQgAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:05.931888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03682","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42249dc115e7a263a0a614c800adb3cb9d127e118a1e7d5f2abd094b1eaa3347","sha256:b4b23145e68ceb3f512b77c774dc32ba1a0130a56d23eac49dc802aa6a1e48cb"],"state_sha256":"9d71b04ce4233b55dc8b7d5cf1e414b22017dd5e1aa8aad19bcb89adafe5a7e6"}