{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2X4G4LALNI46YHEY7XNRPKORQG","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":"7f920255c97b215b8c8a72d49d9661b3f7bcf369944c62595c29f4ea2ee7ab24","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-11T04:51:43Z","title_canon_sha256":"57d2a215a8e77ead83a8fa12920f43783414abae8ab09c14215482a5a5e3054b"},"schema_version":"1.0","source":{"id":"2508.07616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07616","created_at":"2026-07-05T11:57:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07616v2","created_at":"2026-07-05T11:57:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07616","created_at":"2026-07-05T11:57:00Z"},{"alias_kind":"pith_short_12","alias_value":"2X4G4LALNI46","created_at":"2026-07-05T11:57:00Z"},{"alias_kind":"pith_short_16","alias_value":"2X4G4LALNI46YHEY","created_at":"2026-07-05T11:57:00Z"},{"alias_kind":"pith_short_8","alias_value":"2X4G4LAL","created_at":"2026-07-05T11:57:00Z"}],"graph_snapshots":[{"event_id":"sha256:683ce7ab2d51a1119b46349c75e97caa038140bf1aedb15ceb03d4302fee8148","target":"graph","created_at":"2026-07-05T11:57:00Z","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/2508.07616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in test-time scaling have led to the emergence of thinking LLMs that exhibit self-reflective behaviors and multi-step reasoning. While RL drives this self-improvement paradigm, a recent study (Gandhi et al., 2025) shows that RL alone does not truly instill these new reasoning abilities - it merely draws out behaviors already present in the base models. This raises a question: How can we train the models that don't exhibit such thinking behavior to develop it in the first place? To this end, we propose ThinkTuning, a GRPO-based interactive training approach where we augment the ","authors_text":"Aswin RRV, Ben Zhou, Chitta Baral, Divij Handa, Jacob Dineen, Md Nayem Uddin, Mihir Parmar","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-11T04:51:43Z","title":"ThinkTuning: Instilling Cognitive Reflections without Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07616","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":"sha256:3b3fc79184ee90aa5ab3ceda272bc7923a824d301cc4a04de3a0e9e8d0e325e8","target":"record","created_at":"2026-07-05T11:57:00Z","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":"7f920255c97b215b8c8a72d49d9661b3f7bcf369944c62595c29f4ea2ee7ab24","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-11T04:51:43Z","title_canon_sha256":"57d2a215a8e77ead83a8fa12920f43783414abae8ab09c14215482a5a5e3054b"},"schema_version":"1.0","source":{"id":"2508.07616","kind":"arxiv","version":2}},"canonical_sha256":"d5f86e2c0b6a39ec1c98fddb17a9d181be75692972af1c7ee1f95c9028732f92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5f86e2c0b6a39ec1c98fddb17a9d181be75692972af1c7ee1f95c9028732f92","first_computed_at":"2026-07-05T11:57:00.970717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:00.970717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s72p6Gm2Uzngg+f57dT3U8BXWNLL+9HWFE81Zd48al3Q/txiVRG30uxAeuqVEUN34grZdyPlDIDW/jo2NN+dDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:00.971174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b3fc79184ee90aa5ab3ceda272bc7923a824d301cc4a04de3a0e9e8d0e325e8","sha256:683ce7ab2d51a1119b46349c75e97caa038140bf1aedb15ceb03d4302fee8148"],"state_sha256":"6969af70a63fe7d34ea7822167e3501018b00fd9a0ea6fb4b256b4d5aa85d584"}