{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZEM5MXWFGPM5QVV5L5KXMEBWPI","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":"26a9f52116e1791cd42a5f48b4524db778b412d52c2e51ef460ae284d945e2d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T21:32:57Z","title_canon_sha256":"e518fb33c1f9c16f76e49578c0a6cdffae87d9db41a7d8933744b1a9f6f7ee26"},"schema_version":"1.0","source":{"id":"2605.26343","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26343","created_at":"2026-05-27T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26343v1","created_at":"2026-05-27T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26343","created_at":"2026-05-27T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZEM5MXWFGPM5","created_at":"2026-05-27T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZEM5MXWFGPM5QVV5","created_at":"2026-05-27T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZEM5MXWF","created_at":"2026-05-27T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:2bf83282da69251307791b7160340a40c7ae52508ebffcd49a650735fb863b99","target":"graph","created_at":"2026-05-27T01:05:13Z","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/2605.26343/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recovering these circuits typically requires a bespoke analytical pipeline for each new task. We recast circuit discovery as a reinforcement-learning problem. An agent operates over the 144 attention heads of GPT-2 small as a discrete action space; each action triggers a zero-ablation and a contrastive reward that subtracts the ablation's damage to general next-token prediction from its damage to the target task. A single PPO policy, trained on two ta","authors_text":"Barsat Khadka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T21:32:57Z","title":"MechRL: Reinforcement Learning Agents Perform Circuit Discovery for Mechanistic Interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26343","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:c36bc3cc5ddcbed8f7c50f6836b56b699700df9767960853b8d772f94e6b5d2d","target":"record","created_at":"2026-05-27T01:05:13Z","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":"26a9f52116e1791cd42a5f48b4524db778b412d52c2e51ef460ae284d945e2d5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T21:32:57Z","title_canon_sha256":"e518fb33c1f9c16f76e49578c0a6cdffae87d9db41a7d8933744b1a9f6f7ee26"},"schema_version":"1.0","source":{"id":"2605.26343","kind":"arxiv","version":1}},"canonical_sha256":"c919d65ec533d9d856bd5f557610367a0862cc6df2033dca676ac0429a64e04f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c919d65ec533d9d856bd5f557610367a0862cc6df2033dca676ac0429a64e04f","first_computed_at":"2026-05-27T01:05:13.043278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:13.043278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rDzODZmjVBbyWbf4cKDXIz/A3Zf/HxY9EpSMwRq2mfk7AdgxIL/uSIGhS8E8d6LGZSbleCDgArX1S2REF55+BQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:13.043964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26343","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c36bc3cc5ddcbed8f7c50f6836b56b699700df9767960853b8d772f94e6b5d2d","sha256:2bf83282da69251307791b7160340a40c7ae52508ebffcd49a650735fb863b99"],"state_sha256":"cc5c4a464e11073c2fc5a35d5ecede2887a25fa8d657072bae2b0224f3ccc2c3"}