{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5I2EVWQPJNUWWVLF6NNUUYP4EV","short_pith_number":"pith:5I2EVWQP","canonical_record":{"source":{"id":"2111.00876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:12:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa5bdd9d1ccf7f3c343e2ced15b164742395f8752ff357376cc7e679cd1b25f3","abstract_canon_sha256":"38b308f8c60fcdbfbba0cb038d13f81d49d918af723b8798ad75b0148e8e566e"},"schema_version":"1.0"},"canonical_sha256":"ea344ada0f4b696b5565f35b4a61fc256b8a4384142aeb42d39c9c1a9ce1c219","source":{"kind":"arxiv","id":"2111.00876","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00876","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00876v2","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00876","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"5I2EVWQPJNUW","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"5I2EVWQPJNUWWVLF","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"5I2EVWQP","created_at":"2026-07-05T03:49:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5I2EVWQPJNUWWVLF6NNUUYP4EV","target":"record","payload":{"canonical_record":{"source":{"id":"2111.00876","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:12:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa5bdd9d1ccf7f3c343e2ced15b164742395f8752ff357376cc7e679cd1b25f3","abstract_canon_sha256":"38b308f8c60fcdbfbba0cb038d13f81d49d918af723b8798ad75b0148e8e566e"},"schema_version":"1.0"},"canonical_sha256":"ea344ada0f4b696b5565f35b4a61fc256b8a4384142aeb42d39c9c1a9ce1c219","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:49:23.859707Z","signature_b64":"G87fsILx25ggNi2jbN/CmPn+dvcfl9rVRi9yBrx32PFmA2rc+6nuFchxz7PrTxWAi3MBnMHvBqmf8q/q0hcAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea344ada0f4b696b5565f35b4a61fc256b8a4384142aeb42d39c9c1a9ce1c219","last_reissued_at":"2026-07-05T03:49:23.859250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:49:23.859250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.00876","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":"2026-07-05T03:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rugDEfp+5TwZ5qG5PW5luhHQ64sR96/k8ZyB6W1YKmknt6YaQKGNNk5plAjxk22TcXaTkfYkrxSdl0moj1OKAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:30:08.435572Z"},"content_sha256":"62cfb7cc6585702e9514745cd493efb7d01c7195efc12a3dc619a79da3c338b0","schema_version":"1.0","event_id":"sha256:62cfb7cc6585702e9514745cd493efb7d01c7195efc12a3dc619a79da3c338b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5I2EVWQPJNUWWVLF6NNUUYP4EV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Expressivity of Markov Reward","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anna Harutyunyan, David Abel, Doina Precup, Mark K. Ho, Michael L. Littman, Satinder Singh, Will Dabney","submitted_at":"2021-11-01T12:12:16Z","abstract_excerpt":"Reward is the driving force for reinforcement-learning agents. This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new abstract notions of \"task\" that might be desirable: (1) a set of acceptable behaviors, (2) a partial ordering over behaviors, or (3) a partial ordering over trajectories. Our main results prove that while reward can express many of these tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00876","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/2111.00876/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":"2026-07-05T03:49:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P/Xme4yAWNO7X6JVN4FqHVvsyynrIgbx1SvGf6iZ967qDY7P3snCGSs14Bj+MjDad49xCO0vnWaGxQiurL6wCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:30:08.436056Z"},"content_sha256":"2f0c3d4ff21200d289a2fa79f530a25730389368ab9c1f59232ba83a77bbed59","schema_version":"1.0","event_id":"sha256:2f0c3d4ff21200d289a2fa79f530a25730389368ab9c1f59232ba83a77bbed59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV/bundle.json","state_url":"https://pith.science/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV/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":"2026-07-06T12:30:08Z","links":{"resolver":"https://pith.science/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV","bundle":"https://pith.science/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV/bundle.json","state":"https://pith.science/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5I2EVWQPJNUWWVLF6NNUUYP4EV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5I2EVWQPJNUWWVLF6NNUUYP4EV","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":"38b308f8c60fcdbfbba0cb038d13f81d49d918af723b8798ad75b0148e8e566e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:12:16Z","title_canon_sha256":"aa5bdd9d1ccf7f3c343e2ced15b164742395f8752ff357376cc7e679cd1b25f3"},"schema_version":"1.0","source":{"id":"2111.00876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.00876","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"arxiv_version","alias_value":"2111.00876v2","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.00876","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"pith_short_12","alias_value":"5I2EVWQPJNUW","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"pith_short_16","alias_value":"5I2EVWQPJNUWWVLF","created_at":"2026-07-05T03:49:23Z"},{"alias_kind":"pith_short_8","alias_value":"5I2EVWQP","created_at":"2026-07-05T03:49:23Z"}],"graph_snapshots":[{"event_id":"sha256:2f0c3d4ff21200d289a2fa79f530a25730389368ab9c1f59232ba83a77bbed59","target":"graph","created_at":"2026-07-05T03:49:23Z","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/2111.00876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward is the driving force for reinforcement-learning agents. This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new abstract notions of \"task\" that might be desirable: (1) a set of acceptable behaviors, (2) a partial ordering over behaviors, or (3) a partial ordering over trajectories. Our main results prove that while reward can express many of these tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-t","authors_text":"Anna Harutyunyan, David Abel, Doina Precup, Mark K. Ho, Michael L. Littman, Satinder Singh, Will Dabney","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:12:16Z","title":"On the Expressivity of Markov Reward"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.00876","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":"sha256:62cfb7cc6585702e9514745cd493efb7d01c7195efc12a3dc619a79da3c338b0","target":"record","created_at":"2026-07-05T03:49:23Z","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":"38b308f8c60fcdbfbba0cb038d13f81d49d918af723b8798ad75b0148e8e566e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-01T12:12:16Z","title_canon_sha256":"aa5bdd9d1ccf7f3c343e2ced15b164742395f8752ff357376cc7e679cd1b25f3"},"schema_version":"1.0","source":{"id":"2111.00876","kind":"arxiv","version":2}},"canonical_sha256":"ea344ada0f4b696b5565f35b4a61fc256b8a4384142aeb42d39c9c1a9ce1c219","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea344ada0f4b696b5565f35b4a61fc256b8a4384142aeb42d39c9c1a9ce1c219","first_computed_at":"2026-07-05T03:49:23.859250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:49:23.859250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G87fsILx25ggNi2jbN/CmPn+dvcfl9rVRi9yBrx32PFmA2rc+6nuFchxz7PrTxWAi3MBnMHvBqmf8q/q0hcAAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:49:23.859707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.00876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62cfb7cc6585702e9514745cd493efb7d01c7195efc12a3dc619a79da3c338b0","sha256:2f0c3d4ff21200d289a2fa79f530a25730389368ab9c1f59232ba83a77bbed59"],"state_sha256":"23f10ab57a11b6a3de676a7ac0f39b683e1d618054786af1522ba364fc114106"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49gOp8jaVMk0sV2ILHFEZPZsqGU09ivEiuiWvoF0SehigYiXXNLhtkIH1rximzEQ9NMX0jgbXCtqlhIxbGRtDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:30:08.437976Z","bundle_sha256":"2b5ba79a20a70d684a3056c697851df9a1c5bae8aff4db6077cd71ff1dfd1f91"}}