{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:C22KGP3BHML2AYTNILYENGH74A","short_pith_number":"pith:C22KGP3B","schema_version":"1.0","canonical_sha256":"16b4a33f613b17a0626d42f04698ffe017a73472be3ea7faeeb17230580483cd","source":{"kind":"arxiv","id":"2206.03944","version":3},"attestation_state":"computed","paper":{"title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anna L. Trella, Finale Doshi-Velez, Inbal Nahum-Shani, Kelly W. Zhang, Susan A. Murphy, Vivek Shetty","submitted_at":"2022-06-08T15:05:28Z","abstract_excerpt":"Online reinforcement learning (RL) algorithms are increasingly used to personalize digital interventions in the fields of mobile health and online education. Common challenges in designing and testing an RL algorithm in these settings include ensuring the RL algorithm can learn and run stably under real-time constraints, and accounting for the complexity of the environment, e.g., a lack of accurate mechanistic models for the user dynamics. To guide how one can tackle these challenges, we extend the PCS (Predictability, Computability, Stability) framework, a data science framework that incorpor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.03944","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T15:05:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1c89872a881dffa9e9be4e6aa7537f11683c4c25eff6b10442ab0ed442b812b","abstract_canon_sha256":"d815bf3710fd83c85cbfe54a90e97ab2a019b88ad349c7596854ae0f7ce7696e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:28.798876Z","signature_b64":"ldJQ5zXkyiH2HZVAnx9IX/1D3pfUsJVVl7YEYXpr6/ZrL88chLoDauYd9AYegRV6bQibKp9NQmHVZiHD56BdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16b4a33f613b17a0626d42f04698ffe017a73472be3ea7faeeb17230580483cd","last_reissued_at":"2026-07-05T04:53:28.798522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:28.798522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Anna L. Trella, Finale Doshi-Velez, Inbal Nahum-Shani, Kelly W. Zhang, Susan A. Murphy, Vivek Shetty","submitted_at":"2022-06-08T15:05:28Z","abstract_excerpt":"Online reinforcement learning (RL) algorithms are increasingly used to personalize digital interventions in the fields of mobile health and online education. Common challenges in designing and testing an RL algorithm in these settings include ensuring the RL algorithm can learn and run stably under real-time constraints, and accounting for the complexity of the environment, e.g., a lack of accurate mechanistic models for the user dynamics. To guide how one can tackle these challenges, we extend the PCS (Predictability, Computability, Stability) framework, a data science framework that incorpor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.03944","kind":"arxiv","version":3},"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/2206.03944/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.03944","created_at":"2026-07-05T04:53:28.798583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.03944v3","created_at":"2026-07-05T04:53:28.798583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.03944","created_at":"2026-07-05T04:53:28.798583+00:00"},{"alias_kind":"pith_short_12","alias_value":"C22KGP3BHML2","created_at":"2026-07-05T04:53:28.798583+00:00"},{"alias_kind":"pith_short_16","alias_value":"C22KGP3BHML2AYTN","created_at":"2026-07-05T04:53:28.798583+00:00"},{"alias_kind":"pith_short_8","alias_value":"C22KGP3B","created_at":"2026-07-05T04:53:28.798583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A","json":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A.json","graph_json":"https://pith.science/api/pith-number/C22KGP3BHML2AYTNILYENGH74A/graph.json","events_json":"https://pith.science/api/pith-number/C22KGP3BHML2AYTNILYENGH74A/events.json","paper":"https://pith.science/paper/C22KGP3B"},"agent_actions":{"view_html":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A","download_json":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A.json","view_paper":"https://pith.science/paper/C22KGP3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.03944&json=true","fetch_graph":"https://pith.science/api/pith-number/C22KGP3BHML2AYTNILYENGH74A/graph.json","fetch_events":"https://pith.science/api/pith-number/C22KGP3BHML2AYTNILYENGH74A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A/action/storage_attestation","attest_author":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A/action/author_attestation","sign_citation":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A/action/citation_signature","submit_replication":"https://pith.science/pith/C22KGP3BHML2AYTNILYENGH74A/action/replication_record"}},"created_at":"2026-07-05T04:53:28.798583+00:00","updated_at":"2026-07-05T04:53:28.798583+00:00"}