{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KNUD4W4YZYQX5SJSH6ROAL6AQO","short_pith_number":"pith:KNUD4W4Y","schema_version":"1.0","canonical_sha256":"53683e5b98ce217ec9323fa2e02fc0839c3446c6dc644f53ed68a2beeb15c1b4","source":{"kind":"arxiv","id":"2501.19245","version":2},"attestation_state":"computed","paper":{"title":"SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Andreas Sauter, Floris den Hengst, Frans A. Oliehoek, H\\\"useyin Ayd{\\i}n, Kevin Godin-Dubois, Kim Baraka, Libio Goncalvez Braz, Mustafa Mert \\c{C}elikok, Shihan Wang","submitted_at":"2025-01-31T15:59:50Z","abstract_excerpt":"Reinforcement learning (RL) offers a general approach for modeling and training AI agents, including human-AI interaction scenarios. In this paper, we propose SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments) to address the need for a generic framework to support experiments with RL agents and humans. Its modular design consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide var"},"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":"2501.19245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-01-31T15:59:50Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"5c138b60cd64d52de170f2b9a6da64291e6c066fee0c3e34b52a0d8cc217f4e3","abstract_canon_sha256":"7ec50a39d508f025d9d3fa0cb10c159f1578b4e44fa90954c7bac42d3ea152af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:29.544205Z","signature_b64":"ipsrn1AXobpJP6v107L1K0zrUo13O+j3J5A6tP/93TZcnEC+YuMwEHiZldwkUXfkJ88vVDxUtqGHFgr6XlvVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53683e5b98ce217ec9323fa2e02fc0839c3446c6dc644f53ed68a2beeb15c1b4","last_reissued_at":"2026-07-05T10:08:29.543702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:29.543702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SHARPIE: A Modular Framework for Reinforcement Learning and Human-AI Interaction Experiments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Andreas Sauter, Floris den Hengst, Frans A. Oliehoek, H\\\"useyin Ayd{\\i}n, Kevin Godin-Dubois, Kim Baraka, Libio Goncalvez Braz, Mustafa Mert \\c{C}elikok, Shihan Wang","submitted_at":"2025-01-31T15:59:50Z","abstract_excerpt":"Reinforcement learning (RL) offers a general approach for modeling and training AI agents, including human-AI interaction scenarios. In this paper, we propose SHARPIE (Shared Human-AI Reinforcement Learning Platform for Interactive Experiments) to address the need for a generic framework to support experiments with RL agents and humans. Its modular design consists of a versatile wrapper for RL environments and algorithm libraries, a participant-facing web interface, logging utilities, deployment on popular cloud and participant recruitment platforms. It empowers researchers to study a wide var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19245","kind":"arxiv","version":2},"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/2501.19245/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":"2501.19245","created_at":"2026-07-05T10:08:29.543766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19245v2","created_at":"2026-07-05T10:08:29.543766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19245","created_at":"2026-07-05T10:08:29.543766+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNUD4W4YZYQX","created_at":"2026-07-05T10:08:29.543766+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNUD4W4YZYQX5SJS","created_at":"2026-07-05T10:08:29.543766+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNUD4W4Y","created_at":"2026-07-05T10:08:29.543766+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/KNUD4W4YZYQX5SJSH6ROAL6AQO","json":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO.json","graph_json":"https://pith.science/api/pith-number/KNUD4W4YZYQX5SJSH6ROAL6AQO/graph.json","events_json":"https://pith.science/api/pith-number/KNUD4W4YZYQX5SJSH6ROAL6AQO/events.json","paper":"https://pith.science/paper/KNUD4W4Y"},"agent_actions":{"view_html":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO","download_json":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO.json","view_paper":"https://pith.science/paper/KNUD4W4Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19245&json=true","fetch_graph":"https://pith.science/api/pith-number/KNUD4W4YZYQX5SJSH6ROAL6AQO/graph.json","fetch_events":"https://pith.science/api/pith-number/KNUD4W4YZYQX5SJSH6ROAL6AQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO/action/storage_attestation","attest_author":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO/action/author_attestation","sign_citation":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO/action/citation_signature","submit_replication":"https://pith.science/pith/KNUD4W4YZYQX5SJSH6ROAL6AQO/action/replication_record"}},"created_at":"2026-07-05T10:08:29.543766+00:00","updated_at":"2026-07-05T10:08:29.543766+00:00"}