{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WHLC7VVVFXVCVHYNKVH2LWXFXF","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":"a34607b231414803ca59e95114fcd1b0db860b48bd88c686d2012673282f6d10","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T20:40:13Z","title_canon_sha256":"a822b4003a94d07ea42d042ad26514677d0f5b63af0485c7275afe4ba02de4e9"},"schema_version":"1.0","source":{"id":"2506.12217","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.12217","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.12217v1","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12217","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"pith_short_12","alias_value":"WHLC7VVVFXVC","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"pith_short_16","alias_value":"WHLC7VVVFXVCVHYN","created_at":"2026-07-05T11:21:23Z"},{"alias_kind":"pith_short_8","alias_value":"WHLC7VVV","created_at":"2026-07-05T11:21:23Z"}],"graph_snapshots":[{"event_id":"sha256:03afbd6c54212a345caa3e615405b7f99531e4893846cecdd4e0fc8e7cab95d9","target":"graph","created_at":"2026-07-05T11:21:23Z","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/2506.12217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforcement learning with verifiable rewards (RLVR). While self-reflection correlates with improved reasoning accuracy, its origin and underlying mechanisms remain poorly understood. In this work, {\\it we first show that self-reflection is not exclusive to RLVR fine-tuned models: it already emerges, albeit rarely, in pretrained models}. To probe this latent ability, we introduce Reflection-Inducing Probing, a method that i","authors_text":"Jiachen Jiang, Mohammad Mahdi Khalili, Xudong Zhu, Zhihui Zhu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T20:40:13Z","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12217","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":"sha256:6ed9ac00ebb7d551a447f9a29d5f0f13e08fad11f10a063abae3eaf54d1bc905","target":"record","created_at":"2026-07-05T11:21:23Z","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":"a34607b231414803ca59e95114fcd1b0db860b48bd88c686d2012673282f6d10","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-13T20:40:13Z","title_canon_sha256":"a822b4003a94d07ea42d042ad26514677d0f5b63af0485c7275afe4ba02de4e9"},"schema_version":"1.0","source":{"id":"2506.12217","kind":"arxiv","version":1}},"canonical_sha256":"b1d62fd6b52dea2a9f0d554fa5dae5b956b88d962c44487eb79e7541acf2eec3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1d62fd6b52dea2a9f0d554fa5dae5b956b88d962c44487eb79e7541acf2eec3","first_computed_at":"2026-07-05T11:21:23.427156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:23.427156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4gYJwkGjUNYhkQfHWSwQ1aXMa7kmxE2HSZoSOyTbDY03jau8PgMDm6lvVVuVW8fwDxUU74cf6SYfXME6IylMBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:23.427574Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.12217","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ed9ac00ebb7d551a447f9a29d5f0f13e08fad11f10a063abae3eaf54d1bc905","sha256:03afbd6c54212a345caa3e615405b7f99531e4893846cecdd4e0fc8e7cab95d9"],"state_sha256":"ba5bc0171194a6c1c50257e9d71e78434261d7c0edad1a49e3886f92ccb2e2a3"}