{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IUOXIBY2NNYONXBP3X5Z66DZTJ","short_pith_number":"pith:IUOXIBY2","canonical_record":{"source":{"id":"2310.08043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T05:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"b182903eec82fdd33486bf2211bb3e370f3fa3d7cf7403921b24fd18088aec92","abstract_canon_sha256":"afa7a3340fe3c81f437fe730e534ce099f8ba241c2eafb48e07133bfcf564fb0"},"schema_version":"1.0"},"canonical_sha256":"451d74071a6b70e6dc2fddfb9f78799a69fe0a3e75090551a0fd71c0180da308","source":{"kind":"arxiv","id":"2310.08043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08043","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08043v1","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08043","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"IUOXIBY2NNYO","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"IUOXIBY2NNYONXBP","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"IUOXIBY2","created_at":"2026-07-05T07:00:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IUOXIBY2NNYONXBP3X5Z66DZTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T05:33:54Z","cross_cats_sorted":[],"title_canon_sha256":"b182903eec82fdd33486bf2211bb3e370f3fa3d7cf7403921b24fd18088aec92","abstract_canon_sha256":"afa7a3340fe3c81f437fe730e534ce099f8ba241c2eafb48e07133bfcf564fb0"},"schema_version":"1.0"},"canonical_sha256":"451d74071a6b70e6dc2fddfb9f78799a69fe0a3e75090551a0fd71c0180da308","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:00.113613Z","signature_b64":"Lgy/zRicTWvotcH5ApktOztF3+wRV+qUnZaX+aBvG+M/YVEQf56S4c+KSro198Eb6xs3Uq3uIan2Ig/QftefDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"451d74071a6b70e6dc2fddfb9f78799a69fe0a3e75090551a0fd71c0180da308","last_reissued_at":"2026-07-05T07:00:00.113119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:00.113119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08043","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QEUxf7j5wRSb3YIstjwZt+O0Vynqg2Jm4SoJ1w47/b7z7oMgnhZdneqMJH0ma5BhjKfXwFOiAd5aT9TYa7NHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:17:40.974020Z"},"content_sha256":"02b53447d8f6d1375e9faaf9b284c2d9ab6ee37531a20f988ac9b3eb434a06c5","schema_version":"1.0","event_id":"sha256:02b53447d8f6d1375e9faaf9b284c2d9ab6ee37531a20f988ac9b3eb434a06c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IUOXIBY2NNYONXBP3X5Z66DZTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding and Controlling a Maze-Solving Policy Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Matt Turner, Austin Meek, Monte MacDiarmid, Mrinank Sharma, Peli Grietzer, Ulisse Mini","submitted_at":"2023-10-12T05:33:54Z","abstract_excerpt":"To understand the goals and goal representations of AI systems, we carefully study a pretrained reinforcement learning policy that solves mazes by navigating to a range of target squares. We find this network pursues multiple context-dependent goals, and we further identify circuits within the network that correspond to one of these goals. In particular, we identified eleven channels that track the location of the goal. By modifying these channels, either with hand-designed interventions or by combining forward passes, we can partially control the policy. We show that this network contains red"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08043","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.08043/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LN8YeD0kxInySAHdXkPlTX3RYITauNwEC41PswtSVCw7N0C3z4jzuJnq5aeKO3yqAapMoPgiIyWWhMiHQ4DNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:17:40.975114Z"},"content_sha256":"bc6a1e65b712ac881acc31cc8eb7e001897e3dbcef37c6f371064e5a9f3ef33f","schema_version":"1.0","event_id":"sha256:bc6a1e65b712ac881acc31cc8eb7e001897e3dbcef37c6f371064e5a9f3ef33f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ/bundle.json","state_url":"https://pith.science/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T14:17:40Z","links":{"resolver":"https://pith.science/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ","bundle":"https://pith.science/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ/bundle.json","state":"https://pith.science/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUOXIBY2NNYONXBP3X5Z66DZTJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IUOXIBY2NNYONXBP3X5Z66DZTJ","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":"afa7a3340fe3c81f437fe730e534ce099f8ba241c2eafb48e07133bfcf564fb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T05:33:54Z","title_canon_sha256":"b182903eec82fdd33486bf2211bb3e370f3fa3d7cf7403921b24fd18088aec92"},"schema_version":"1.0","source":{"id":"2310.08043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08043","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08043v1","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08043","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"IUOXIBY2NNYO","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"IUOXIBY2NNYONXBP","created_at":"2026-07-05T07:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"IUOXIBY2","created_at":"2026-07-05T07:00:00Z"}],"graph_snapshots":[{"event_id":"sha256:bc6a1e65b712ac881acc31cc8eb7e001897e3dbcef37c6f371064e5a9f3ef33f","target":"graph","created_at":"2026-07-05T07:00:00Z","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/2310.08043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To understand the goals and goal representations of AI systems, we carefully study a pretrained reinforcement learning policy that solves mazes by navigating to a range of target squares. We find this network pursues multiple context-dependent goals, and we further identify circuits within the network that correspond to one of these goals. In particular, we identified eleven channels that track the location of the goal. By modifying these channels, either with hand-designed interventions or by combining forward passes, we can partially control the policy. We show that this network contains red","authors_text":"Alexander Matt Turner, Austin Meek, Monte MacDiarmid, Mrinank Sharma, Peli Grietzer, Ulisse Mini","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T05:33:54Z","title":"Understanding and Controlling a Maze-Solving Policy Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08043","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":"sha256:02b53447d8f6d1375e9faaf9b284c2d9ab6ee37531a20f988ac9b3eb434a06c5","target":"record","created_at":"2026-07-05T07:00:00Z","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":"afa7a3340fe3c81f437fe730e534ce099f8ba241c2eafb48e07133bfcf564fb0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-12T05:33:54Z","title_canon_sha256":"b182903eec82fdd33486bf2211bb3e370f3fa3d7cf7403921b24fd18088aec92"},"schema_version":"1.0","source":{"id":"2310.08043","kind":"arxiv","version":1}},"canonical_sha256":"451d74071a6b70e6dc2fddfb9f78799a69fe0a3e75090551a0fd71c0180da308","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"451d74071a6b70e6dc2fddfb9f78799a69fe0a3e75090551a0fd71c0180da308","first_computed_at":"2026-07-05T07:00:00.113119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:00.113119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lgy/zRicTWvotcH5ApktOztF3+wRV+qUnZaX+aBvG+M/YVEQf56S4c+KSro198Eb6xs3Uq3uIan2Ig/QftefDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:00.113613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02b53447d8f6d1375e9faaf9b284c2d9ab6ee37531a20f988ac9b3eb434a06c5","sha256:bc6a1e65b712ac881acc31cc8eb7e001897e3dbcef37c6f371064e5a9f3ef33f"],"state_sha256":"32839163efa725239837ee8b49d198931d0024c8baa6c6d70d8575911ab0566e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkSGm2SiD+vZPIGcdmdR4dqBO4lKJ1hcpJmSbvHK6Y00TyHdk/fdkKRObLSmzBus49c1gS3k9LmwNAmsSP4HCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:17:40.984779Z","bundle_sha256":"1ad942319514a411e01a1f0cef7421aa1b5a1aad47136f52af37c58107334736"}}