{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TCKAWUFM5XT4D4KL5LCXWWHZQF","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":"0017fd9eac80f58cad592ba99b2e7c5fd888b0ff94ca3938dc1774ae97f9b216","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T09:51:35Z","title_canon_sha256":"9d020ae80ca738df6fb6b68254d7fbe6ae229bc2c5f58e80186502df46b3e636"},"schema_version":"1.0","source":{"id":"2606.13125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13125","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13125v1","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13125","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"TCKAWUFM5XT4","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"TCKAWUFM5XT4D4KL","created_at":"2026-06-12T01:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"TCKAWUFM","created_at":"2026-06-12T01:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:6a30738ac2e1155b30af067ba7b7ccb815ff3dc3b875bf11ac17b8613118bf56","target":"graph","created_at":"2026-06-12T01:09:41Z","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/2606.13125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has rapidly emerged as a key component in the training of reasoning and coding models, yet it remains poorly understood from a mechanistic perspective. We study how and through what underlying processes capabilities are acquired or enhanced via reinforcement learning post-training. Our analysis, based on controlled math reasoning experiments with Qwen-2.5-1.5B, reveals two core mechanisms: strategy selection and strategy improvement. Our results highlight the role of SFT data and reinforcement learning data in activating these mechanisms, in particular showing how superv","authors_text":"Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T09:51:35Z","title":"Select and Improve: Understanding the Mechanics of Post-Training for Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13125","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":"sha256:2f4833777d8f581f5c79edafa3818c2547eb4e36b6bc23f4fedb9cd554a3d365","target":"record","created_at":"2026-06-12T01:09:41Z","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":"0017fd9eac80f58cad592ba99b2e7c5fd888b0ff94ca3938dc1774ae97f9b216","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-11T09:51:35Z","title_canon_sha256":"9d020ae80ca738df6fb6b68254d7fbe6ae229bc2c5f58e80186502df46b3e636"},"schema_version":"1.0","source":{"id":"2606.13125","kind":"arxiv","version":1}},"canonical_sha256":"98940b50acede7c1f14beac57b58f981719a1b90811677f6c265cde73d244356","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98940b50acede7c1f14beac57b58f981719a1b90811677f6c265cde73d244356","first_computed_at":"2026-06-12T01:09:41.635994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:09:41.635994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tt2Pz1X5Hm/9TRaRfpLdc1L1YKGyDiQouamMn2VO7qytNmhrWQEoxx6HKn5b3Nbo8yajQ8cks7tS0JMbeQeQCw==","signature_status":"signed_v1","signed_at":"2026-06-12T01:09:41.636884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f4833777d8f581f5c79edafa3818c2547eb4e36b6bc23f4fedb9cd554a3d365","sha256:6a30738ac2e1155b30af067ba7b7ccb815ff3dc3b875bf11ac17b8613118bf56"],"state_sha256":"9398dc43edc49882c8b426bfcf4d8135c50a6ec41e1d6130cf52f4c420a06d0b"}