{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SMH5JMUSIF7VBDDQBODFOAUV2H","short_pith_number":"pith:SMH5JMUS","canonical_record":{"source":{"id":"2307.11044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:27:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c6a4d8d476f3d0e2df7f3aa0b2e5060871f286ef4b8ba69e0fcda990638e084","abstract_canon_sha256":"c8c27cb7c13f2550075c6ba58a9b08d693dc6533f34214b37f8edfd179cdcca4"},"schema_version":"1.0"},"canonical_sha256":"930fd4b292417f508c700b86570295d1f6e70533cac2fbfefdd5634b49fe58ac","source":{"kind":"arxiv","id":"2307.11044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11044","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11044v1","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11044","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"pith_short_12","alias_value":"SMH5JMUSIF7V","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"pith_short_16","alias_value":"SMH5JMUSIF7VBDDQ","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"pith_short_8","alias_value":"SMH5JMUS","created_at":"2026-07-05T06:33:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SMH5JMUSIF7VBDDQBODFOAUV2H","target":"record","payload":{"canonical_record":{"source":{"id":"2307.11044","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:27:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c6a4d8d476f3d0e2df7f3aa0b2e5060871f286ef4b8ba69e0fcda990638e084","abstract_canon_sha256":"c8c27cb7c13f2550075c6ba58a9b08d693dc6533f34214b37f8edfd179cdcca4"},"schema_version":"1.0"},"canonical_sha256":"930fd4b292417f508c700b86570295d1f6e70533cac2fbfefdd5634b49fe58ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:14.614389Z","signature_b64":"3QItw+8ryukUT2ABi98ICXu9W8IPOuM5qoJ5edjo8jBziPs2aeaK1AP8Gkr8LeCPwri41xsf0w4HK0AtRt34CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"930fd4b292417f508c700b86570295d1f6e70533cac2fbfefdd5634b49fe58ac","last_reissued_at":"2026-07-05T06:33:14.613915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:14.613915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.11044","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":"2026-07-05T06:33:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QG40KcPaVYYbqMW79EVEedvUJcyOMsdZjMtVpWrEzYyrZFFXnEpF7q6lDzYjdhJsc3EPS2xUwlncn0PnJV3HCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:50:01.996343Z"},"content_sha256":"668280c8a2585e8046799d36ad10b70465f4fa26dc82e0ad128b8bfead42a593","schema_version":"1.0","event_id":"sha256:668280c8a2585e8046799d36ad10b70465f4fa26dc82e0ad128b8bfead42a593"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SMH5JMUSIF7VBDDQBODFOAUV2H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Convergence of Bounded Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Benjamin Van Roy, David Abel, Doina Precup, Hado van Hasselt, Satinder Singh","submitted_at":"2023-07-20T17:27:29Z","abstract_excerpt":"When has an agent converged? Standard models of the reinforcement learning problem give rise to a straightforward definition of convergence: An agent converges when its behavior or performance in each environment state stops changing. However, as we shift the focus of our learning problem from the environment's state to the agent's state, the concept of an agent's convergence becomes significantly less clear. In this paper, we propose two complementary accounts of agent convergence in a framing of the reinforcement learning problem that centers around bounded agents. The first view says that a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11044","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/2307.11044/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":"2026-07-05T06:33:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yA7p/TPBlhBA40LryY39YSyR/bT/ks363m0TpBpZXXAJMzSlbUC9dvPIEN7l9ZxWCQz14BaEH6GQlBsu4RECAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:50:01.997073Z"},"content_sha256":"d4f57f131c93f1801776454c97f682425fdb1e1d8badd16a88258b6a888f1c3c","schema_version":"1.0","event_id":"sha256:d4f57f131c93f1801776454c97f682425fdb1e1d8badd16a88258b6a888f1c3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMH5JMUSIF7VBDDQBODFOAUV2H/bundle.json","state_url":"https://pith.science/pith/SMH5JMUSIF7VBDDQBODFOAUV2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMH5JMUSIF7VBDDQBODFOAUV2H/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":"2026-08-06T07:50:02Z","links":{"resolver":"https://pith.science/pith/SMH5JMUSIF7VBDDQBODFOAUV2H","bundle":"https://pith.science/pith/SMH5JMUSIF7VBDDQBODFOAUV2H/bundle.json","state":"https://pith.science/pith/SMH5JMUSIF7VBDDQBODFOAUV2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMH5JMUSIF7VBDDQBODFOAUV2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SMH5JMUSIF7VBDDQBODFOAUV2H","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":"c8c27cb7c13f2550075c6ba58a9b08d693dc6533f34214b37f8edfd179cdcca4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:27:29Z","title_canon_sha256":"0c6a4d8d476f3d0e2df7f3aa0b2e5060871f286ef4b8ba69e0fcda990638e084"},"schema_version":"1.0","source":{"id":"2307.11044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.11044","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"arxiv_version","alias_value":"2307.11044v1","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11044","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"pith_short_12","alias_value":"SMH5JMUSIF7V","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"pith_short_16","alias_value":"SMH5JMUSIF7VBDDQ","created_at":"2026-07-05T06:33:14Z"},{"alias_kind":"pith_short_8","alias_value":"SMH5JMUS","created_at":"2026-07-05T06:33:14Z"}],"graph_snapshots":[{"event_id":"sha256:d4f57f131c93f1801776454c97f682425fdb1e1d8badd16a88258b6a888f1c3c","target":"graph","created_at":"2026-07-05T06:33:14Z","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/2307.11044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When has an agent converged? Standard models of the reinforcement learning problem give rise to a straightforward definition of convergence: An agent converges when its behavior or performance in each environment state stops changing. However, as we shift the focus of our learning problem from the environment's state to the agent's state, the concept of an agent's convergence becomes significantly less clear. In this paper, we propose two complementary accounts of agent convergence in a framing of the reinforcement learning problem that centers around bounded agents. The first view says that a","authors_text":"Andr\\'e Barreto, Benjamin Van Roy, David Abel, Doina Precup, Hado van Hasselt, Satinder Singh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:27:29Z","title":"On the Convergence of Bounded Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11044","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":"sha256:668280c8a2585e8046799d36ad10b70465f4fa26dc82e0ad128b8bfead42a593","target":"record","created_at":"2026-07-05T06:33:14Z","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":"c8c27cb7c13f2550075c6ba58a9b08d693dc6533f34214b37f8edfd179cdcca4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-20T17:27:29Z","title_canon_sha256":"0c6a4d8d476f3d0e2df7f3aa0b2e5060871f286ef4b8ba69e0fcda990638e084"},"schema_version":"1.0","source":{"id":"2307.11044","kind":"arxiv","version":1}},"canonical_sha256":"930fd4b292417f508c700b86570295d1f6e70533cac2fbfefdd5634b49fe58ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"930fd4b292417f508c700b86570295d1f6e70533cac2fbfefdd5634b49fe58ac","first_computed_at":"2026-07-05T06:33:14.613915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:14.613915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3QItw+8ryukUT2ABi98ICXu9W8IPOuM5qoJ5edjo8jBziPs2aeaK1AP8Gkr8LeCPwri41xsf0w4HK0AtRt34CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:14.614389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.11044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:668280c8a2585e8046799d36ad10b70465f4fa26dc82e0ad128b8bfead42a593","sha256:d4f57f131c93f1801776454c97f682425fdb1e1d8badd16a88258b6a888f1c3c"],"state_sha256":"d338de487bc4be84aa69ca31dff6eb3e84772abb94043b38ebf80a1ee287ab7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EHlrlDbc1VcQi6LX8mDeQvASfW5eNOdgEt1zLmjGuQ7Skj+iFRan+UhR+d8OaKMDAORPuASbflAxNR+hI5QgDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:50:02.002883Z","bundle_sha256":"ce5a6dfdad296e04d71eb08b5e6e0e581d2b6984edf9f8c382b611244c97cc2c"}}