{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6XQQMOASISK5JSC6LFWG237AY6","short_pith_number":"pith:6XQQMOAS","canonical_record":{"source":{"id":"2111.06025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-11T02:21:08Z","cross_cats_sorted":[],"title_canon_sha256":"cefc046bf2a7b801fe0989b8152975c768ca6cbb95623fbd4bdf1da384321c80","abstract_canon_sha256":"97bd032acd94bf75d34c2d2bb9ace5569501e10653255a7fb141debe5e2283da"},"schema_version":"1.0"},"canonical_sha256":"f5e10638124495d4c85e596c6d6fe0c7b6d2f9453ea080ec8cc56726b2367d61","source":{"kind":"arxiv","id":"2111.06025","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.06025","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.06025v1","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06025","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"6XQQMOASISK5","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"6XQQMOASISK5JSC6","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"6XQQMOAS","created_at":"2026-07-05T03:30:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6XQQMOASISK5JSC6LFWG237AY6","target":"record","payload":{"canonical_record":{"source":{"id":"2111.06025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-11T02:21:08Z","cross_cats_sorted":[],"title_canon_sha256":"cefc046bf2a7b801fe0989b8152975c768ca6cbb95623fbd4bdf1da384321c80","abstract_canon_sha256":"97bd032acd94bf75d34c2d2bb9ace5569501e10653255a7fb141debe5e2283da"},"schema_version":"1.0"},"canonical_sha256":"f5e10638124495d4c85e596c6d6fe0c7b6d2f9453ea080ec8cc56726b2367d61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:57.278908Z","signature_b64":"iMVK4ruMOGI6NlelDv2qeoFSeET9VH7VShoF/g5xk/b83ilHCu45b6CrUYeV9HMtqVYfdSWh6m7FYtkMiECfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5e10638124495d4c85e596c6d6fe0c7b6d2f9453ea080ec8cc56726b2367d61","last_reissued_at":"2026-07-05T03:30:57.278516Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:57.278516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.06025","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":"2026-07-05T03:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+P+uLkhvOPyrlNWxUCEX/9BGBSU7LF/JzPDL3PIJM6oRv15rQk/YwwINsYih++Zf3EgIsm5KU7GFe/5gf/POAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T06:52:20.263604Z"},"content_sha256":"e2f0a65b678d32b23921beb6a6c0fec46b14f6cdc506b3afc598cb234f5fa471","schema_version":"1.0","event_id":"sha256:e2f0a65b678d32b23921beb6a6c0fec46b14f6cdc506b3afc598cb234f5fa471"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6XQQMOASISK5JSC6LFWG237AY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Costas Spanos, Lucas Spangher, Tarang Srivastava, Utkarsha Agwan, William Arnold","submitted_at":"2021-11-11T02:21:08Z","abstract_excerpt":"Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments. We propose a reinforcement learning controller with surprise minimizing modifications in its architecture. We suggest that surprise minimization can be used to improve learning speed, taking advantage of predictability in peoples' energy usage. Our architecture performs well in a simulation of energy demand response. We propose this modification to improve functionality and save in a large scale experiment."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06025","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/2111.06025/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":"2026-07-05T03:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0iVN06IvpGOwkJl1aDDRNfa5gCIX0Rsxh7qpFJjMYskcj6pZPpxehJZHw4UBUvyIWTCUQBkKa9MUwTKt1HRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T06:52:20.263977Z"},"content_sha256":"6ce42cae25894784ba85a2631410c091005b28d04cacba4117b5b05616dd3373","schema_version":"1.0","event_id":"sha256:6ce42cae25894784ba85a2631410c091005b28d04cacba4117b5b05616dd3373"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XQQMOASISK5JSC6LFWG237AY6/bundle.json","state_url":"https://pith.science/pith/6XQQMOASISK5JSC6LFWG237AY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XQQMOASISK5JSC6LFWG237AY6/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":"2026-07-26T06:52:20Z","links":{"resolver":"https://pith.science/pith/6XQQMOASISK5JSC6LFWG237AY6","bundle":"https://pith.science/pith/6XQQMOASISK5JSC6LFWG237AY6/bundle.json","state":"https://pith.science/pith/6XQQMOASISK5JSC6LFWG237AY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XQQMOASISK5JSC6LFWG237AY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6XQQMOASISK5JSC6LFWG237AY6","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":"97bd032acd94bf75d34c2d2bb9ace5569501e10653255a7fb141debe5e2283da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-11T02:21:08Z","title_canon_sha256":"cefc046bf2a7b801fe0989b8152975c768ca6cbb95623fbd4bdf1da384321c80"},"schema_version":"1.0","source":{"id":"2111.06025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.06025","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"2111.06025v1","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.06025","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"6XQQMOASISK5","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"pith_short_16","alias_value":"6XQQMOASISK5JSC6","created_at":"2026-07-05T03:30:57Z"},{"alias_kind":"pith_short_8","alias_value":"6XQQMOAS","created_at":"2026-07-05T03:30:57Z"}],"graph_snapshots":[{"event_id":"sha256:6ce42cae25894784ba85a2631410c091005b28d04cacba4117b5b05616dd3373","target":"graph","created_at":"2026-07-05T03:30:57Z","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/2111.06025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimizing prices for energy demand response requires a flexible controller with ability to navigate complex environments. We propose a reinforcement learning controller with surprise minimizing modifications in its architecture. We suggest that surprise minimization can be used to improve learning speed, taking advantage of predictability in peoples' energy usage. Our architecture performs well in a simulation of energy demand response. We propose this modification to improve functionality and save in a large scale experiment.","authors_text":"Costas Spanos, Lucas Spangher, Tarang Srivastava, Utkarsha Agwan, William Arnold","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-11T02:21:08Z","title":"Adapting Surprise Minimizing Reinforcement Learning Techniques for Transactive Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.06025","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:e2f0a65b678d32b23921beb6a6c0fec46b14f6cdc506b3afc598cb234f5fa471","target":"record","created_at":"2026-07-05T03:30:57Z","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":"97bd032acd94bf75d34c2d2bb9ace5569501e10653255a7fb141debe5e2283da","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-11T02:21:08Z","title_canon_sha256":"cefc046bf2a7b801fe0989b8152975c768ca6cbb95623fbd4bdf1da384321c80"},"schema_version":"1.0","source":{"id":"2111.06025","kind":"arxiv","version":1}},"canonical_sha256":"f5e10638124495d4c85e596c6d6fe0c7b6d2f9453ea080ec8cc56726b2367d61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5e10638124495d4c85e596c6d6fe0c7b6d2f9453ea080ec8cc56726b2367d61","first_computed_at":"2026-07-05T03:30:57.278516Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:30:57.278516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iMVK4ruMOGI6NlelDv2qeoFSeET9VH7VShoF/g5xk/b83ilHCu45b6CrUYeV9HMtqVYfdSWh6m7FYtkMiECfBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:30:57.278908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.06025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2f0a65b678d32b23921beb6a6c0fec46b14f6cdc506b3afc598cb234f5fa471","sha256:6ce42cae25894784ba85a2631410c091005b28d04cacba4117b5b05616dd3373"],"state_sha256":"67355a4382fdcba2825e644721e90816805fdb44d86b9739bd27fc5130a2a7fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IBB3t8AiVj4KE5adMSAqhozboIR4p+oyx93vZNDyAaDQ2W94jddPIm/WxsQUOINsjvDf/JUbItqCEoZ/OqsgBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T06:52:20.266191Z","bundle_sha256":"050d1ad7cfb0b76db00daec9f56ce315c52ac1e6e1d5bcd92e0200f889641adc"}}