{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LQDKL3VXME5UMUNBNKCRVOUXA2","short_pith_number":"pith:LQDKL3VX","canonical_record":{"source":{"id":"2407.00264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-28T23:31:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"72e232a23d04ddd40ce3b348a3c2559da3a14778d975c27d5db736d3eda5a790","abstract_canon_sha256":"6eb9eb041f8830ced591795c51393d740004657aaa10fd2b69e0a32f45948f81"},"schema_version":"1.0"},"canonical_sha256":"5c06a5eeb7613b4651a16a851aba9706a423fa259b429eb7b96f5ffca66c913e","source":{"kind":"arxiv","id":"2407.00264","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00264","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00264v1","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00264","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"pith_short_12","alias_value":"LQDKL3VXME5U","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"pith_short_16","alias_value":"LQDKL3VXME5UMUNB","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"pith_short_8","alias_value":"LQDKL3VX","created_at":"2026-07-05T08:38:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LQDKL3VXME5UMUNBNKCRVOUXA2","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-28T23:31:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"72e232a23d04ddd40ce3b348a3c2559da3a14778d975c27d5db736d3eda5a790","abstract_canon_sha256":"6eb9eb041f8830ced591795c51393d740004657aaa10fd2b69e0a32f45948f81"},"schema_version":"1.0"},"canonical_sha256":"5c06a5eeb7613b4651a16a851aba9706a423fa259b429eb7b96f5ffca66c913e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:40.125216Z","signature_b64":"morQRjWb7OqwmY4T6YPlb4Sh8I+1gJ+SnYY6Lk9vubJzGw+KvlAdtEMjoEIwv4Z7fiTevB90pEr5ykz3Q0OnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c06a5eeb7613b4651a16a851aba9706a423fa259b429eb7b96f5ffca66c913e","last_reissued_at":"2026-07-05T08:38:40.124832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:40.124832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00264","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":"2026-07-05T08:38:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ye2UvOOsBKsKdA04aXqPQVpOBe4EcxuypK+LnRVlZWdYT9BqjaLnnJqsm0bt+WXzCHFbxWrn87+dYoll9q2fAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:23:22.022878Z"},"content_sha256":"fef5c7b7098f156448c696fd372d869a8652cf46d2a2d20d24f4c5cef5278d2a","schema_version":"1.0","event_id":"sha256:fef5c7b7098f156448c696fd372d869a8652cf46d2a2d20d24f4c5cef5278d2a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LQDKL3VXME5UMUNBNKCRVOUXA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jonathan Balloch, Julia Kim, Mark Riedl, Rishav Bhagat, Zhiyu Lin","submitted_at":"2024-06-28T23:31:22Z","abstract_excerpt":"Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks with learning about how changes may affect their understanding of the world. This is possible by choosing to solve tasks in ways that are interesting and generally informative beyond just the current task. Motivated by this, we propose an agent influence framework for RL agents to improve the adaptation efficiency of external models in changing environments wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00264","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/2407.00264/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":"2026-07-05T08:38:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ItDduOa+/pW6lsEuWba2HYYCPV2jtS6gRmIWJaapRNQ6Wtk9+8a2FENgLIDqe3Y8dxTwVRoVV+zW3F8OIknVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T05:23:22.023267Z"},"content_sha256":"bb7086bf1fa3ccf26fe525c1fdb79cad74f6b688352beb56337be8cd36bb66dc","schema_version":"1.0","event_id":"sha256:bb7086bf1fa3ccf26fe525c1fdb79cad74f6b688352beb56337be8cd36bb66dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LQDKL3VXME5UMUNBNKCRVOUXA2/bundle.json","state_url":"https://pith.science/pith/LQDKL3VXME5UMUNBNKCRVOUXA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LQDKL3VXME5UMUNBNKCRVOUXA2/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":"2026-08-04T05:23:22Z","links":{"resolver":"https://pith.science/pith/LQDKL3VXME5UMUNBNKCRVOUXA2","bundle":"https://pith.science/pith/LQDKL3VXME5UMUNBNKCRVOUXA2/bundle.json","state":"https://pith.science/pith/LQDKL3VXME5UMUNBNKCRVOUXA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LQDKL3VXME5UMUNBNKCRVOUXA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LQDKL3VXME5UMUNBNKCRVOUXA2","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":"6eb9eb041f8830ced591795c51393d740004657aaa10fd2b69e0a32f45948f81","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-28T23:31:22Z","title_canon_sha256":"72e232a23d04ddd40ce3b348a3c2559da3a14778d975c27d5db736d3eda5a790"},"schema_version":"1.0","source":{"id":"2407.00264","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00264","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00264v1","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00264","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"pith_short_12","alias_value":"LQDKL3VXME5U","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"pith_short_16","alias_value":"LQDKL3VXME5UMUNB","created_at":"2026-07-05T08:38:40Z"},{"alias_kind":"pith_short_8","alias_value":"LQDKL3VX","created_at":"2026-07-05T08:38:40Z"}],"graph_snapshots":[{"event_id":"sha256:bb7086bf1fa3ccf26fe525c1fdb79cad74f6b688352beb56337be8cd36bb66dc","target":"graph","created_at":"2026-07-05T08:38:40Z","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/2407.00264/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks with learning about how changes may affect their understanding of the world. This is possible by choosing to solve tasks in ways that are interesting and generally informative beyond just the current task. Motivated by this, we propose an agent influence framework for RL agents to improve the adaptation efficiency of external models in changing environments wi","authors_text":"Jonathan Balloch, Julia Kim, Mark Riedl, Rishav Bhagat, Zhiyu Lin","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-28T23:31:22Z","title":"External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00264","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:fef5c7b7098f156448c696fd372d869a8652cf46d2a2d20d24f4c5cef5278d2a","target":"record","created_at":"2026-07-05T08:38:40Z","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":"6eb9eb041f8830ced591795c51393d740004657aaa10fd2b69e0a32f45948f81","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-28T23:31:22Z","title_canon_sha256":"72e232a23d04ddd40ce3b348a3c2559da3a14778d975c27d5db736d3eda5a790"},"schema_version":"1.0","source":{"id":"2407.00264","kind":"arxiv","version":1}},"canonical_sha256":"5c06a5eeb7613b4651a16a851aba9706a423fa259b429eb7b96f5ffca66c913e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c06a5eeb7613b4651a16a851aba9706a423fa259b429eb7b96f5ffca66c913e","first_computed_at":"2026-07-05T08:38:40.124832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:40.124832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"morQRjWb7OqwmY4T6YPlb4Sh8I+1gJ+SnYY6Lk9vubJzGw+KvlAdtEMjoEIwv4Z7fiTevB90pEr5ykz3Q0OnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:40.125216Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00264","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fef5c7b7098f156448c696fd372d869a8652cf46d2a2d20d24f4c5cef5278d2a","sha256:bb7086bf1fa3ccf26fe525c1fdb79cad74f6b688352beb56337be8cd36bb66dc"],"state_sha256":"1fef5bd394fd41f57f5e543bcebdeb7c9f2c14c35f2772a5f9ac8977191ac6d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+ZuIAmK/3g4jBnHmD4LhSPal33zwks58Hb+ZlEGPDZjLv+y4hqVTZL0cpoQ0VfGTxFZSH2giJhMrpMeTdz2Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T05:23:22.026331Z","bundle_sha256":"5c795b732dfbe34c08a3e1f6b3642e66695e7adab478cde767c0990405a75aa6"}}