{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SLCQWKUBFTHJ6TVB3RTNVL7VKK","short_pith_number":"pith:SLCQWKUB","canonical_record":{"source":{"id":"2504.01871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T16:24:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a15a86e59a16fc906c1dbe55bcd0dc2557574516d7033720b3e89b2282b3423","abstract_canon_sha256":"67fe64535e79cc4555adb34b1e2c481ea9220454cc247a90a7c9f43595506bf4"},"schema_version":"1.0"},"canonical_sha256":"92c50b2a812cce9f4ea1dc66daaff5528d3919d58c725cb5487d0b2a7b025a9c","source":{"kind":"arxiv","id":"2504.01871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01871","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01871v1","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01871","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"SLCQWKUBFTHJ","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"SLCQWKUBFTHJ6TVB","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"SLCQWKUB","created_at":"2026-07-05T10:43:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SLCQWKUBFTHJ6TVB3RTNVL7VKK","target":"record","payload":{"canonical_record":{"source":{"id":"2504.01871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T16:24:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a15a86e59a16fc906c1dbe55bcd0dc2557574516d7033720b3e89b2282b3423","abstract_canon_sha256":"67fe64535e79cc4555adb34b1e2c481ea9220454cc247a90a7c9f43595506bf4"},"schema_version":"1.0"},"canonical_sha256":"92c50b2a812cce9f4ea1dc66daaff5528d3919d58c725cb5487d0b2a7b025a9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:31.032773Z","signature_b64":"hwP34YaUwPVBuqpVWyztk0KFsH4ctwVXdfJ8JYy5C+HkYSWge1c+QtkUDqpOzLNXRzL6URd9O2/GniacRLOsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92c50b2a812cce9f4ea1dc66daaff5528d3919d58c725cb5487d0b2a7b025a9c","last_reissued_at":"2026-07-05T10:43:31.032298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:31.032298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.01871","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":"2026-07-05T10:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FPeXnypbsk0Xy3iHkuUucQDZtG8j2M4lvXdrYZS61ytVPnUILzc9ZSBWOr5mSbqXA/pgacL53qj48siVj7waDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:00:11.005732Z"},"content_sha256":"6f830555b1b7536491ca88cfab4f74da1d542e7d4d8a0187f2cfa58ac1e026f0","schema_version":"1.0","event_id":"sha256:6f830555b1b7536491ca88cfab4f74da1d542e7d4d8a0187f2cfa58ac1e026f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SLCQWKUBFTHJ6TVB3RTNVL7VKK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpreting Emergent Planning in Model-Free Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adri\\`a Garriga-Alonso, David Krueger, Stephen Chung, Thomas Bush, Usman Anwar","submitted_at":"2025-04-02T16:24:23Z","abstract_excerpt":"We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly used benchmark for studying planning. Specifically, we demonstrate that DRC, a generic model-free agent introduced by Guez et al. (2019), uses learned concept representations to internally formulate plans that both predict the long-term effects of actions on the environment and influence action selection. Our methodology involves: (1) probing for planning-relev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01871","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/2504.01871/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":"2026-07-05T10:43:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0rxkq5VjlyHYPv4BYd2YzWKpfQcykCJQ+sD+LTTCgwHQSN/KrW8PPoSEe6RGLyzHGNsExcJiQPEZLSqQ8a+LBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T18:00:11.007913Z"},"content_sha256":"f0e00784838d3577b3f1b3a2d530c745965ed07623514d23e6b765c35b14bb5f","schema_version":"1.0","event_id":"sha256:f0e00784838d3577b3f1b3a2d530c745965ed07623514d23e6b765c35b14bb5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK/bundle.json","state_url":"https://pith.science/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK/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":"2026-08-12T18:00:11Z","links":{"resolver":"https://pith.science/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK","bundle":"https://pith.science/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK/bundle.json","state":"https://pith.science/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLCQWKUBFTHJ6TVB3RTNVL7VKK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SLCQWKUBFTHJ6TVB3RTNVL7VKK","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":"67fe64535e79cc4555adb34b1e2c481ea9220454cc247a90a7c9f43595506bf4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T16:24:23Z","title_canon_sha256":"8a15a86e59a16fc906c1dbe55bcd0dc2557574516d7033720b3e89b2282b3423"},"schema_version":"1.0","source":{"id":"2504.01871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01871","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01871v1","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01871","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_12","alias_value":"SLCQWKUBFTHJ","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_16","alias_value":"SLCQWKUBFTHJ6TVB","created_at":"2026-07-05T10:43:31Z"},{"alias_kind":"pith_short_8","alias_value":"SLCQWKUB","created_at":"2026-07-05T10:43:31Z"}],"graph_snapshots":[{"event_id":"sha256:f0e00784838d3577b3f1b3a2d530c745965ed07623514d23e6b765c35b14bb5f","target":"graph","created_at":"2026-07-05T10:43:31Z","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/2504.01871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the first mechanistic evidence that model-free reinforcement learning agents can learn to plan. This is achieved by applying a methodology based on concept-based interpretability to a model-free agent in Sokoban -- a commonly used benchmark for studying planning. Specifically, we demonstrate that DRC, a generic model-free agent introduced by Guez et al. (2019), uses learned concept representations to internally formulate plans that both predict the long-term effects of actions on the environment and influence action selection. Our methodology involves: (1) probing for planning-relev","authors_text":"Adri\\`a Garriga-Alonso, David Krueger, Stephen Chung, Thomas Bush, Usman Anwar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T16:24:23Z","title":"Interpreting Emergent Planning in Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01871","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":"sha256:6f830555b1b7536491ca88cfab4f74da1d542e7d4d8a0187f2cfa58ac1e026f0","target":"record","created_at":"2026-07-05T10:43:31Z","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":"67fe64535e79cc4555adb34b1e2c481ea9220454cc247a90a7c9f43595506bf4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-02T16:24:23Z","title_canon_sha256":"8a15a86e59a16fc906c1dbe55bcd0dc2557574516d7033720b3e89b2282b3423"},"schema_version":"1.0","source":{"id":"2504.01871","kind":"arxiv","version":1}},"canonical_sha256":"92c50b2a812cce9f4ea1dc66daaff5528d3919d58c725cb5487d0b2a7b025a9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92c50b2a812cce9f4ea1dc66daaff5528d3919d58c725cb5487d0b2a7b025a9c","first_computed_at":"2026-07-05T10:43:31.032298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:31.032298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hwP34YaUwPVBuqpVWyztk0KFsH4ctwVXdfJ8JYy5C+HkYSWge1c+QtkUDqpOzLNXRzL6URd9O2/GniacRLOsDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:31.032773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f830555b1b7536491ca88cfab4f74da1d542e7d4d8a0187f2cfa58ac1e026f0","sha256:f0e00784838d3577b3f1b3a2d530c745965ed07623514d23e6b765c35b14bb5f"],"state_sha256":"c6a4603ac7261c38ebb271ff2c96ad9911583615f08c441711c1d546d92b7b75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PD9mB6GM3y3uiOlJzi42uA+9VmoMoO6gTXrExlhZ/s1SzWkd0cqPXKRPQKYY8fAhoUQEhUsKrXijq7JFDT1KAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T18:00:11.014999Z","bundle_sha256":"9c542c3674f4e37eb16f427a32cd7d5b9fa8373095360282636111436b78b7dd"}}