{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WN5ICM4KEVJ4OTO2VEEGHRKQTS","short_pith_number":"pith:WN5ICM4K","canonical_record":{"source":{"id":"2602.12963","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-13T14:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"70e339bb98231c91f27c3ebc23f448ddf89d6e164bcbf6a1d49de4112d4b1bc9","abstract_canon_sha256":"9ee1cf40e91034f5c1ee4979db30333239f5394739f8d18afc1e38aa2645d977"},"schema_version":"1.0"},"canonical_sha256":"b37a81338a2553c74ddaa90863c5509caa3cd20b1bfefdf779feb3242fdd1813","source":{"kind":"arxiv","id":"2602.12963","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12963","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12963v2","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12963","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"WN5ICM4KEVJ4","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"WN5ICM4KEVJ4OTO2","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"WN5ICM4K","created_at":"2026-07-15T01:21:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WN5ICM4KEVJ4OTO2VEEGHRKQTS","target":"record","payload":{"canonical_record":{"source":{"id":"2602.12963","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-13T14:29:17Z","cross_cats_sorted":[],"title_canon_sha256":"70e339bb98231c91f27c3ebc23f448ddf89d6e164bcbf6a1d49de4112d4b1bc9","abstract_canon_sha256":"9ee1cf40e91034f5c1ee4979db30333239f5394739f8d18afc1e38aa2645d977"},"schema_version":"1.0"},"canonical_sha256":"b37a81338a2553c74ddaa90863c5509caa3cd20b1bfefdf779feb3242fdd1813","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T01:21:50.381526Z","signature_b64":"/CgeOLbtd+YtgMGkkgBUJPI+Vvr/jTFfTWiBJy3XcsETjPd1uPPAQGy54wurtVqW/0ZIAL1NdhtoksgWIijnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b37a81338a2553c74ddaa90863c5509caa3cd20b1bfefdf779feb3242fdd1813","last_reissued_at":"2026-07-15T01:21:50.380706Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T01:21:50.380706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.12963","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-15T01:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"93F+pNTtghhpJKeVAdxiMcSJgnk4Pql8q4rghMHL8wNPBOiv4bGqTFNFf0st50q6xhD4TLarhWg3ReebRpCSAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:12:10.900753Z"},"content_sha256":"9d491edc30205da2d16fd00acf718105b2c2a017e6c2989c70dd43a137d10b76","schema_version":"1.0","event_id":"sha256:9d491edc30205da2d16fd00acf718105b2c2a017e6c2989c70dd43a137d10b76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WN5ICM4KEVJ4OTO2VEEGHRKQTS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Calculating Mutual Information between a Reward Maximizer and its Environment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alex Altair, Alfred Harwood, Jose Faustino","submitted_at":"2026-02-13T14:29:17Z","abstract_excerpt":"An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world. In this work, we quantify the amount of information an optimal policy provides about the underlying environment. We consider a Controlled Markov Process (CMP) with $n$ states and $m$ actions, assuming a uniform prior over the space of possible transition dynamics. We prove that observing a deterministic policy that is optimal for any non-constant reward function then conveys exactly $n \\log m$ bits of information about the environment. Specifically, we show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12963","kind":"arxiv","version":2},"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/2602.12963/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":"2026-07-15T01:21:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l9JdkFl5JvA9ybPWKAvU77C/kwpDzXZa8sfwjokdT8drBunls0oKjK4RPdiF0X8AIx2aexCyUddiaPAECfGlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:12:10.901643Z"},"content_sha256":"5eef3a619039a62b26363b945697c4034f9a246e39d12efb3a61c39aad0b46be","schema_version":"1.0","event_id":"sha256:5eef3a619039a62b26363b945697c4034f9a246e39d12efb3a61c39aad0b46be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS/bundle.json","state_url":"https://pith.science/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS/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":"2026-08-08T05:12:10Z","links":{"resolver":"https://pith.science/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS","bundle":"https://pith.science/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS/bundle.json","state":"https://pith.science/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WN5ICM4KEVJ4OTO2VEEGHRKQTS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WN5ICM4KEVJ4OTO2VEEGHRKQTS","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":"9ee1cf40e91034f5c1ee4979db30333239f5394739f8d18afc1e38aa2645d977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-13T14:29:17Z","title_canon_sha256":"70e339bb98231c91f27c3ebc23f448ddf89d6e164bcbf6a1d49de4112d4b1bc9"},"schema_version":"1.0","source":{"id":"2602.12963","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12963","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12963v2","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12963","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"WN5ICM4KEVJ4","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"WN5ICM4KEVJ4OTO2","created_at":"2026-07-15T01:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"WN5ICM4K","created_at":"2026-07-15T01:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:5eef3a619039a62b26363b945697c4034f9a246e39d12efb3a61c39aad0b46be","target":"graph","created_at":"2026-07-15T01:21:50Z","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/2602.12963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important question in the field of AI is the extent to which successful behaviour requires an internal representation of the world. In this work, we quantify the amount of information an optimal policy provides about the underlying environment. We consider a Controlled Markov Process (CMP) with $n$ states and $m$ actions, assuming a uniform prior over the space of possible transition dynamics. We prove that observing a deterministic policy that is optimal for any non-constant reward function then conveys exactly $n \\log m$ bits of information about the environment. Specifically, we show tha","authors_text":"Alex Altair, Alfred Harwood, Jose Faustino","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-13T14:29:17Z","title":"Calculating Mutual Information between a Reward Maximizer and its Environment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12963","kind":"arxiv","version":2},"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":"sha256:9d491edc30205da2d16fd00acf718105b2c2a017e6c2989c70dd43a137d10b76","target":"record","created_at":"2026-07-15T01:21:50Z","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":"9ee1cf40e91034f5c1ee4979db30333239f5394739f8d18afc1e38aa2645d977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-02-13T14:29:17Z","title_canon_sha256":"70e339bb98231c91f27c3ebc23f448ddf89d6e164bcbf6a1d49de4112d4b1bc9"},"schema_version":"1.0","source":{"id":"2602.12963","kind":"arxiv","version":2}},"canonical_sha256":"b37a81338a2553c74ddaa90863c5509caa3cd20b1bfefdf779feb3242fdd1813","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b37a81338a2553c74ddaa90863c5509caa3cd20b1bfefdf779feb3242fdd1813","first_computed_at":"2026-07-15T01:21:50.380706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-15T01:21:50.380706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/CgeOLbtd+YtgMGkkgBUJPI+Vvr/jTFfTWiBJy3XcsETjPd1uPPAQGy54wurtVqW/0ZIAL1NdhtoksgWIijnCA==","signature_status":"signed_v1","signed_at":"2026-07-15T01:21:50.381526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.12963","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d491edc30205da2d16fd00acf718105b2c2a017e6c2989c70dd43a137d10b76","sha256:5eef3a619039a62b26363b945697c4034f9a246e39d12efb3a61c39aad0b46be"],"state_sha256":"2c539449bec4efe201d7677aa73bb853094f64c61acd09e31de98f146f56e6fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PkETn8/FgFy1vlyW/asUcCd/DFWbwNnhr/xAY52vR6B6gxczi+Hj1Cxa8r/Z3ynLKuCTHFRfKWIgsrNymK0cDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:12:10.908588Z","bundle_sha256":"4f22ce61149be37c173a2c8301f351b51dc6a092fe6d0f1e0397d88160e8d148"}}