{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IQEBSB5WQR6SYMF5MRVG2Q65GA","short_pith_number":"pith:IQEBSB5W","canonical_record":{"source":{"id":"1609.01995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-07T14:27:56Z","cross_cats_sorted":[],"title_canon_sha256":"842f10194d76b1372e69a94970772c78937a4626f60c6d5ea6720ded98559ff3","abstract_canon_sha256":"53c4db219ee8865bba32256cd809588d5c933ffd634ed2f50f6e28f616db65be"},"schema_version":"1.0"},"canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","source":{"kind":"arxiv","id":"1609.01995","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.01995","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"1609.01995v4","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01995","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"IQEBSB5WQR6S","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"IQEBSB5WQR6SYMF5","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"IQEBSB5W","created_at":"2026-07-05T03:15:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IQEBSB5WQR6SYMF5MRVG2Q65GA","target":"record","payload":{"canonical_record":{"source":{"id":"1609.01995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-07T14:27:56Z","cross_cats_sorted":[],"title_canon_sha256":"842f10194d76b1372e69a94970772c78937a4626f60c6d5ea6720ded98559ff3","abstract_canon_sha256":"53c4db219ee8865bba32256cd809588d5c933ffd634ed2f50f6e28f616db65be"},"schema_version":"1.0"},"canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:24.744091Z","signature_b64":"t7cOOLSrOSXN55+3EvN/V6GkVMLXNMC1kc4w5oTIL+BSoGRWj3y7iICk9pDleZxDBnbWnm4jmjaAGA6sX30xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","last_reissued_at":"2026-07-05T03:15:24.743734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:24.743734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.01995","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fxY+gJ00qyH5iqAkH4ZrXZcCuI2/V4FQtC3mId+FrSKOd3O3kDGyJTr3PRvUPpZTWhlyz2SaobNQ7omGy0g5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:14.964343Z"},"content_sha256":"4cf0b9c6987a4fb4e9d8f5d61be34dcaec2f464e15e374028b9db697093e933e","schema_version":"1.0","event_id":"sha256:4cf0b9c6987a4fb4e9d8f5d61be34dcaec2f464e15e374028b9db697093e933e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IQEBSB5WQR6SYMF5MRVG2Q65GA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unifying task specification in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Martha White","submitted_at":"2016-09-07T14:27:56Z","abstract_excerpt":"Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01995","kind":"arxiv","version":4},"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/1609.01995/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":"2026-07-05T03:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"whGxjgBGf9LOABx7fQND8uEcgKQFaNXKX4/lvSwZvHSPTI0Ltfw1JRb8xqcq3VYcGCGCCmT7pbTNCB/XKQCjCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:16:14.965045Z"},"content_sha256":"c7a38b7fad762be32fb62b208b368078857dfba54682c23c4625e40678acb375","schema_version":"1.0","event_id":"sha256:c7a38b7fad762be32fb62b208b368078857dfba54682c23c4625e40678acb375"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/bundle.json","state_url":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/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":"2026-08-07T07:16:14Z","links":{"resolver":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA","bundle":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/bundle.json","state":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IQEBSB5WQR6SYMF5MRVG2Q65GA","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":"53c4db219ee8865bba32256cd809588d5c933ffd634ed2f50f6e28f616db65be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-07T14:27:56Z","title_canon_sha256":"842f10194d76b1372e69a94970772c78937a4626f60c6d5ea6720ded98559ff3"},"schema_version":"1.0","source":{"id":"1609.01995","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.01995","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"1609.01995v4","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01995","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"IQEBSB5WQR6S","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"IQEBSB5WQR6SYMF5","created_at":"2026-07-05T03:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"IQEBSB5W","created_at":"2026-07-05T03:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:c7a38b7fad762be32fb62b208b368078857dfba54682c23c4625e40678acb375","target":"graph","created_at":"2026-07-05T03:15:24Z","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/1609.01995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we de","authors_text":"Martha White","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-07T14:27:56Z","title":"Unifying task specification in reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01995","kind":"arxiv","version":4},"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":"sha256:4cf0b9c6987a4fb4e9d8f5d61be34dcaec2f464e15e374028b9db697093e933e","target":"record","created_at":"2026-07-05T03:15:24Z","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":"53c4db219ee8865bba32256cd809588d5c933ffd634ed2f50f6e28f616db65be","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-07T14:27:56Z","title_canon_sha256":"842f10194d76b1372e69a94970772c78937a4626f60c6d5ea6720ded98559ff3"},"schema_version":"1.0","source":{"id":"1609.01995","kind":"arxiv","version":4}},"canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","first_computed_at":"2026-07-05T03:15:24.743734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:24.743734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t7cOOLSrOSXN55+3EvN/V6GkVMLXNMC1kc4w5oTIL+BSoGRWj3y7iICk9pDleZxDBnbWnm4jmjaAGA6sX30xAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:24.744091Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.01995","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cf0b9c6987a4fb4e9d8f5d61be34dcaec2f464e15e374028b9db697093e933e","sha256:c7a38b7fad762be32fb62b208b368078857dfba54682c23c4625e40678acb375"],"state_sha256":"7f3f06440fb541beb4240b2efd7332b45553e4079a60415a8c09d70f23d24818"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgGJeMMkVmWp+kDgNFlb04OGtwc0Ma7Qlgz9r2obHMpuoOyD9NFGDSSWNduL/KYSxNlT68xYQ47zVIGHe3LJCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:16:14.969124Z","bundle_sha256":"5b55b7fd5060c3565e55d114f73e691b0a13548248010e552c62aa206eb8b73e"}}