{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WTPQTGNRMKWTTOY56JEIITKGPV","short_pith_number":"pith:WTPQTGNR","canonical_record":{"source":{"id":"2407.10583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T10:03:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"557e6ca246a356f3ca77236abfd37e0090850a7cec27569a9011068af7b2e8b6","abstract_canon_sha256":"6f51ec7f6e52ee14c1964c198d758bf90cc4ec60cc96ec75a7aac157f043cdc0"},"schema_version":"1.0"},"canonical_sha256":"b4df0999b162ad39bb1df248844d467d5be18bbad71d31d8502b96ff4ca6d296","source":{"kind":"arxiv","id":"2407.10583","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10583","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10583v1","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10583","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"pith_short_12","alias_value":"WTPQTGNRMKWT","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"pith_short_16","alias_value":"WTPQTGNRMKWTTOY5","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"pith_short_8","alias_value":"WTPQTGNR","created_at":"2026-07-05T08:44:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WTPQTGNRMKWTTOY56JEIITKGPV","target":"record","payload":{"canonical_record":{"source":{"id":"2407.10583","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T10:03:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"557e6ca246a356f3ca77236abfd37e0090850a7cec27569a9011068af7b2e8b6","abstract_canon_sha256":"6f51ec7f6e52ee14c1964c198d758bf90cc4ec60cc96ec75a7aac157f043cdc0"},"schema_version":"1.0"},"canonical_sha256":"b4df0999b162ad39bb1df248844d467d5be18bbad71d31d8502b96ff4ca6d296","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:01.395786Z","signature_b64":"gulYmbznIdGr6rfd0NEfTozsogSsmfydrDx+2MmFwBhKi1hqlnkdpmpkZ1UFIeGvoOsGwPlNShkHs0w8HKmUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4df0999b162ad39bb1df248844d467d5be18bbad71d31d8502b96ff4ca6d296","last_reissued_at":"2026-07-05T08:44:01.395410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:01.395410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.10583","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":"2026-07-05T08:44:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CiM3ImH1NmDo3N2JPL5CpWqmsRhw03LzG62ROxdqWS8SdLOm47O4O+T28jZb02uJDHIpcTMPjJRUMEYBdmL+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:00:41.209104Z"},"content_sha256":"3c441e7c0b5d2acc1f0f421f43edc51c099025e4fbb24bff21ade2a6c0491d31","schema_version":"1.0","event_id":"sha256:3c441e7c0b5d2acc1f0f421f43edc51c099025e4fbb24bff21ade2a6c0491d31"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WTPQTGNRMKWTTOY56JEIITKGPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Three Dogmas of Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Anna Harutyunyan, David Abel, Mark K. Ho","submitted_at":"2024-07-15T10:03:24Z","abstract_excerpt":"Modern reinforcement learning has been conditioned by at least three dogmas. The first is the environment spotlight, which refers to our tendency to focus on modeling environments rather than agents. The second is our treatment of learning as finding the solution to a task, rather than adaptation. The third is the reward hypothesis, which states that all goals and purposes can be well thought of as maximization of a reward signal. These three dogmas shape much of what we think of as the science of reinforcement learning. While each of the dogmas have played an important role in developing the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10583","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/2407.10583/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":"2026-07-05T08:44:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j3USVPE8voVu9XiD4aFlBXYd1nQk3gokMwfPLBYqOvtoMrG/JvwyJhF3rtzrOH7SJOnFo5TzAbmDqUlN9o6ABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:00:41.209625Z"},"content_sha256":"229aaa5cfae38f7bed1a4feb85d7415d8a732c080a0a3043acf7b6a882c101e4","schema_version":"1.0","event_id":"sha256:229aaa5cfae38f7bed1a4feb85d7415d8a732c080a0a3043acf7b6a882c101e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTPQTGNRMKWTTOY56JEIITKGPV/bundle.json","state_url":"https://pith.science/pith/WTPQTGNRMKWTTOY56JEIITKGPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTPQTGNRMKWTTOY56JEIITKGPV/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":"2026-08-20T06:00:41Z","links":{"resolver":"https://pith.science/pith/WTPQTGNRMKWTTOY56JEIITKGPV","bundle":"https://pith.science/pith/WTPQTGNRMKWTTOY56JEIITKGPV/bundle.json","state":"https://pith.science/pith/WTPQTGNRMKWTTOY56JEIITKGPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTPQTGNRMKWTTOY56JEIITKGPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WTPQTGNRMKWTTOY56JEIITKGPV","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":"6f51ec7f6e52ee14c1964c198d758bf90cc4ec60cc96ec75a7aac157f043cdc0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T10:03:24Z","title_canon_sha256":"557e6ca246a356f3ca77236abfd37e0090850a7cec27569a9011068af7b2e8b6"},"schema_version":"1.0","source":{"id":"2407.10583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.10583","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"arxiv_version","alias_value":"2407.10583v1","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10583","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"pith_short_12","alias_value":"WTPQTGNRMKWT","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"pith_short_16","alias_value":"WTPQTGNRMKWTTOY5","created_at":"2026-07-05T08:44:01Z"},{"alias_kind":"pith_short_8","alias_value":"WTPQTGNR","created_at":"2026-07-05T08:44:01Z"}],"graph_snapshots":[{"event_id":"sha256:229aaa5cfae38f7bed1a4feb85d7415d8a732c080a0a3043acf7b6a882c101e4","target":"graph","created_at":"2026-07-05T08:44:01Z","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/2407.10583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern reinforcement learning has been conditioned by at least three dogmas. The first is the environment spotlight, which refers to our tendency to focus on modeling environments rather than agents. The second is our treatment of learning as finding the solution to a task, rather than adaptation. The third is the reward hypothesis, which states that all goals and purposes can be well thought of as maximization of a reward signal. These three dogmas shape much of what we think of as the science of reinforcement learning. While each of the dogmas have played an important role in developing the ","authors_text":"Anna Harutyunyan, David Abel, Mark K. Ho","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T10:03:24Z","title":"Three Dogmas of Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10583","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":"sha256:3c441e7c0b5d2acc1f0f421f43edc51c099025e4fbb24bff21ade2a6c0491d31","target":"record","created_at":"2026-07-05T08:44:01Z","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":"6f51ec7f6e52ee14c1964c198d758bf90cc4ec60cc96ec75a7aac157f043cdc0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-15T10:03:24Z","title_canon_sha256":"557e6ca246a356f3ca77236abfd37e0090850a7cec27569a9011068af7b2e8b6"},"schema_version":"1.0","source":{"id":"2407.10583","kind":"arxiv","version":1}},"canonical_sha256":"b4df0999b162ad39bb1df248844d467d5be18bbad71d31d8502b96ff4ca6d296","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4df0999b162ad39bb1df248844d467d5be18bbad71d31d8502b96ff4ca6d296","first_computed_at":"2026-07-05T08:44:01.395410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:01.395410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gulYmbznIdGr6rfd0NEfTozsogSsmfydrDx+2MmFwBhKi1hqlnkdpmpkZ1UFIeGvoOsGwPlNShkHs0w8HKmUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:01.395786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.10583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c441e7c0b5d2acc1f0f421f43edc51c099025e4fbb24bff21ade2a6c0491d31","sha256:229aaa5cfae38f7bed1a4feb85d7415d8a732c080a0a3043acf7b6a882c101e4"],"state_sha256":"7c94d03deaa0bea85013166348fa9ef04aebc21e89bfcc2803159e886d7e344e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2EHRxsXu1Axf0vDRsc+DXrRPJxILXGgY2ptH4iYFh6f7xuL7V1tEPClQG/0mjUZqHOcuKNpnCXD9RZD31zTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:00:41.214327Z","bundle_sha256":"3cfab1ab72b8ff277f7ed6c147f62eaba30d552ef9766579a7e72c203c3ae898"}}