{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GHKCEVMGNZGWBDYUC22R743ULU","short_pith_number":"pith:GHKCEVMG","canonical_record":{"source":{"id":"2608.07301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T14:56:11Z","cross_cats_sorted":[],"title_canon_sha256":"6dc6e166cf41afaa8d1bf5feee3fe40a363bb1af1795d4e6cbba264a5a959869","abstract_canon_sha256":"42b204579be98c2ee5830549a90ddc4218d51feccaf5689e54d003ae7a01d44c"},"schema_version":"1.0"},"canonical_sha256":"31d42255866e4d608f1416b51ff3745d137f8b272f39eea0b765c6d5e4dd5a0c","source":{"kind":"arxiv","id":"2608.07301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07301","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07301v1","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07301","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"GHKCEVMGNZGW","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"GHKCEVMGNZGWBDYU","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"GHKCEVMG","created_at":"2026-08-10T01:14:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GHKCEVMGNZGWBDYUC22R743ULU","target":"record","payload":{"canonical_record":{"source":{"id":"2608.07301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T14:56:11Z","cross_cats_sorted":[],"title_canon_sha256":"6dc6e166cf41afaa8d1bf5feee3fe40a363bb1af1795d4e6cbba264a5a959869","abstract_canon_sha256":"42b204579be98c2ee5830549a90ddc4218d51feccaf5689e54d003ae7a01d44c"},"schema_version":"1.0"},"canonical_sha256":"31d42255866e4d608f1416b51ff3745d137f8b272f39eea0b765c6d5e4dd5a0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:14:55.044820Z","signature_b64":"HN7KdkrAeQq2800OObZMMBouEdQSo0fWOxiLa5mcalMvTjbGOTz9joSrlyWOA6mW+APP6iSYpXzwN4kGK/IhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d42255866e4d608f1416b51ff3745d137f8b272f39eea0b765c6d5e4dd5a0c","last_reissued_at":"2026-08-10T01:14:55.042113Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:14:55.042113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.07301","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":"2026-08-10T01:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBIGoXuoumTmMAnr96A+coTvYxxRH949jnWl4TK2oxqPNtcB5CqwNSbQAcvIeKHCN7MbkFNmJni5ohbUof0rBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:28:44.136782Z"},"content_sha256":"731a709bd2fdfc5a402cee71f86d931acf04fcda3ab4f079283b472de933ba61","schema_version":"1.0","event_id":"sha256:731a709bd2fdfc5a402cee71f86d931acf04fcda3ab4f079283b472de933ba61"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GHKCEVMGNZGWBDYUC22R743ULU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Optimal Actions to World Models: Identifiability of Transition Kernels in Discounted MDPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Neal Batra","submitted_at":"2026-08-07T14:56:11Z","abstract_excerpt":"We study what can be recovered about the transition probabilities of a Markov decision process from optimal actions alone. This is closely related to the inverse problem considered by Letcher et al., who ask when the dynamics can be recovered from numerical \\(Q\\)-values. Here the numerical values themselves are not observed; only the optimal actions are known, for every reward in a given class.\n  For state-action rewards \\(r(s,a)\\), knowing the optimal actions for every reward also tells us how much better one action is than another when each is followed by the same fixed policy. This is still"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07301","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/2608.07301/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":"2026-08-10T01:14:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8IQsGA7QsqYYPzIHwEdEICr3PhWRBTsG6hUEmiMAYU4VDW0vw7ebdVhW0/DXccTE0BH6P7Yw3FfXwcBzGuWvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T22:28:44.137327Z"},"content_sha256":"4c4c4e89c835b326ad9d5fbfdcc8ad17bc2567829665e33bc9267182e0e093ff","schema_version":"1.0","event_id":"sha256:4c4c4e89c835b326ad9d5fbfdcc8ad17bc2567829665e33bc9267182e0e093ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHKCEVMGNZGWBDYUC22R743ULU/bundle.json","state_url":"https://pith.science/pith/GHKCEVMGNZGWBDYUC22R743ULU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHKCEVMGNZGWBDYUC22R743ULU/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":"2026-08-16T22:28:44Z","links":{"resolver":"https://pith.science/pith/GHKCEVMGNZGWBDYUC22R743ULU","bundle":"https://pith.science/pith/GHKCEVMGNZGWBDYUC22R743ULU/bundle.json","state":"https://pith.science/pith/GHKCEVMGNZGWBDYUC22R743ULU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHKCEVMGNZGWBDYUC22R743ULU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHKCEVMGNZGWBDYUC22R743ULU","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":"42b204579be98c2ee5830549a90ddc4218d51feccaf5689e54d003ae7a01d44c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T14:56:11Z","title_canon_sha256":"6dc6e166cf41afaa8d1bf5feee3fe40a363bb1af1795d4e6cbba264a5a959869"},"schema_version":"1.0","source":{"id":"2608.07301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07301","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07301v1","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07301","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"pith_short_12","alias_value":"GHKCEVMGNZGW","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"pith_short_16","alias_value":"GHKCEVMGNZGWBDYU","created_at":"2026-08-10T01:14:55Z"},{"alias_kind":"pith_short_8","alias_value":"GHKCEVMG","created_at":"2026-08-10T01:14:55Z"}],"graph_snapshots":[{"event_id":"sha256:4c4c4e89c835b326ad9d5fbfdcc8ad17bc2567829665e33bc9267182e0e093ff","target":"graph","created_at":"2026-08-10T01:14:55Z","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/2608.07301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study what can be recovered about the transition probabilities of a Markov decision process from optimal actions alone. This is closely related to the inverse problem considered by Letcher et al., who ask when the dynamics can be recovered from numerical \\(Q\\)-values. Here the numerical values themselves are not observed; only the optimal actions are known, for every reward in a given class.\n  For state-action rewards \\(r(s,a)\\), knowing the optimal actions for every reward also tells us how much better one action is than another when each is followed by the same fixed policy. This is still","authors_text":"Neal Batra","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T14:56:11Z","title":"From Optimal Actions to World Models: Identifiability of Transition Kernels in Discounted MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07301","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":"sha256:731a709bd2fdfc5a402cee71f86d931acf04fcda3ab4f079283b472de933ba61","target":"record","created_at":"2026-08-10T01:14:55Z","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":"42b204579be98c2ee5830549a90ddc4218d51feccaf5689e54d003ae7a01d44c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-07T14:56:11Z","title_canon_sha256":"6dc6e166cf41afaa8d1bf5feee3fe40a363bb1af1795d4e6cbba264a5a959869"},"schema_version":"1.0","source":{"id":"2608.07301","kind":"arxiv","version":1}},"canonical_sha256":"31d42255866e4d608f1416b51ff3745d137f8b272f39eea0b765c6d5e4dd5a0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31d42255866e4d608f1416b51ff3745d137f8b272f39eea0b765c6d5e4dd5a0c","first_computed_at":"2026-08-10T01:14:55.042113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:14:55.042113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HN7KdkrAeQq2800OObZMMBouEdQSo0fWOxiLa5mcalMvTjbGOTz9joSrlyWOA6mW+APP6iSYpXzwN4kGK/IhAw==","signature_status":"signed_v1","signed_at":"2026-08-10T01:14:55.044820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:731a709bd2fdfc5a402cee71f86d931acf04fcda3ab4f079283b472de933ba61","sha256:4c4c4e89c835b326ad9d5fbfdcc8ad17bc2567829665e33bc9267182e0e093ff"],"state_sha256":"35d20a823666f975ecea8e6aa60570bf6b6eeeb67831a9552c37bad02c2a6163"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mvoN55c1i1sAxJYdPVXaHsvQeHeJ2beZrNEsLojOyiHTXmssEZjfA4o3ULQWd2zpm1DyJPWtHPe+677VQ80OCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T22:28:44.143838Z","bundle_sha256":"5fb7ae9f5b3defc6d9f294f1c960ec0c32e64fa5bb798fd7f90737feb8c0f59b"}}