{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RSUUTAKGC7MATVDI4RJATEZ2XA","short_pith_number":"pith:RSUUTAKG","canonical_record":{"source":{"id":"2504.17006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T18:00:08Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"edb625e0abc86afcbf1cea7d5a107ab42af3a5ef61a809d5938cc2a70e178c63","abstract_canon_sha256":"e860f88a70da26259e6e8bfb0016252a8c2ce086287147645993636c84a28763"},"schema_version":"1.0"},"canonical_sha256":"8ca949814617d809d468e45209933ab832e0d86fe124dc59557cfcd6687bee51","source":{"kind":"arxiv","id":"2504.17006","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17006","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17006v1","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17006","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_12","alias_value":"RSUUTAKGC7MA","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_16","alias_value":"RSUUTAKGC7MATVDI","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_8","alias_value":"RSUUTAKG","created_at":"2026-07-05T10:53:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RSUUTAKGC7MATVDI4RJATEZ2XA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.17006","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T18:00:08Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"edb625e0abc86afcbf1cea7d5a107ab42af3a5ef61a809d5938cc2a70e178c63","abstract_canon_sha256":"e860f88a70da26259e6e8bfb0016252a8c2ce086287147645993636c84a28763"},"schema_version":"1.0"},"canonical_sha256":"8ca949814617d809d468e45209933ab832e0d86fe124dc59557cfcd6687bee51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:20.474392Z","signature_b64":"3VBcYVT1BIN//nu92HIZr1jEreSK5HTVOdmcydGl45IhH1oUfv2oInu1OgkfEXYQt8jDdr/oUzeiv0fa13L4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ca949814617d809d468e45209933ab832e0d86fe124dc59557cfcd6687bee51","last_reissued_at":"2026-07-05T10:53:20.473858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:20.473858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.17006","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":"2026-07-05T10:53:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STEpr1EGqxWx7yLj/4w/MGQZ1+lQwt6WAZaHv4PhWDeAMTiddmRiM4nyRWFwPdcuZ+93OowgdU99CI91yNkdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:08:45.751679Z"},"content_sha256":"09f637c24dfb4395c74ed59d30749abe9e2f507c7998c71d9651d99dc9027fcc","schema_version":"1.0","event_id":"sha256:09f637c24dfb4395c74ed59d30749abe9e2f507c7998c71d9651d99dc9027fcc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RSUUTAKGC7MATVDI4RJATEZ2XA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Antoine Fagette, Cloderic Mars, Jalal Arabneydi, Matthew E. Taylor, Matthew Guzdial, Saiful Islam, Sai Krishna Gottipati, Srijita Das, William Duguay, Younes Zerouali","submitted_at":"2025-04-23T18:00:08Z","abstract_excerpt":"With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In this article, we introduce a novel multi-layered hierarchical HITL DRL algorithm that comprises three types of learning: self learning, imitation learning and transfer learning. In addition, we consider three forms of human inputs: reward, action and demonstration. Furthermore, we discuss main challenges, trade-offs and advantages of HITL in solving complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17006","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/2504.17006/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":"2026-07-05T10:53:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nD8eXmApK1Yj6VI+xhwf8021ourCJtIukVw2b97ljbl0Yu6om9EZNldpjyyV6LlINH57KjzJvuAlz0x30KAaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:08:45.752057Z"},"content_sha256":"acb6e15df14dfbe957613338fd9ad7ab8a2c754dbdc3f3cb56bc78a390dcb238","schema_version":"1.0","event_id":"sha256:acb6e15df14dfbe957613338fd9ad7ab8a2c754dbdc3f3cb56bc78a390dcb238"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSUUTAKGC7MATVDI4RJATEZ2XA/bundle.json","state_url":"https://pith.science/pith/RSUUTAKGC7MATVDI4RJATEZ2XA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSUUTAKGC7MATVDI4RJATEZ2XA/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":"2026-07-07T07:08:45Z","links":{"resolver":"https://pith.science/pith/RSUUTAKGC7MATVDI4RJATEZ2XA","bundle":"https://pith.science/pith/RSUUTAKGC7MATVDI4RJATEZ2XA/bundle.json","state":"https://pith.science/pith/RSUUTAKGC7MATVDI4RJATEZ2XA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSUUTAKGC7MATVDI4RJATEZ2XA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RSUUTAKGC7MATVDI4RJATEZ2XA","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":"e860f88a70da26259e6e8bfb0016252a8c2ce086287147645993636c84a28763","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T18:00:08Z","title_canon_sha256":"edb625e0abc86afcbf1cea7d5a107ab42af3a5ef61a809d5938cc2a70e178c63"},"schema_version":"1.0","source":{"id":"2504.17006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17006","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17006v1","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17006","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_12","alias_value":"RSUUTAKGC7MA","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_16","alias_value":"RSUUTAKGC7MATVDI","created_at":"2026-07-05T10:53:20Z"},{"alias_kind":"pith_short_8","alias_value":"RSUUTAKG","created_at":"2026-07-05T10:53:20Z"}],"graph_snapshots":[{"event_id":"sha256:acb6e15df14dfbe957613338fd9ad7ab8a2c754dbdc3f3cb56bc78a390dcb238","target":"graph","created_at":"2026-07-05T10:53:20Z","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/2504.17006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the growing popularity of deep reinforcement learning (DRL), human-in-the-loop (HITL) approach has the potential to revolutionize the way we approach decision-making problems and create new opportunities for human-AI collaboration. In this article, we introduce a novel multi-layered hierarchical HITL DRL algorithm that comprises three types of learning: self learning, imitation learning and transfer learning. In addition, we consider three forms of human inputs: reward, action and demonstration. Furthermore, we discuss main challenges, trade-offs and advantages of HITL in solving complex ","authors_text":"Antoine Fagette, Cloderic Mars, Jalal Arabneydi, Matthew E. Taylor, Matthew Guzdial, Saiful Islam, Sai Krishna Gottipati, Srijita Das, William Duguay, Younes Zerouali","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T18:00:08Z","title":"A Systematic Approach to Design Real-World Human-in-the-Loop Deep Reinforcement Learning: Salient Features, Challenges and Trade-offs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17006","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":"sha256:09f637c24dfb4395c74ed59d30749abe9e2f507c7998c71d9651d99dc9027fcc","target":"record","created_at":"2026-07-05T10:53:20Z","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":"e860f88a70da26259e6e8bfb0016252a8c2ce086287147645993636c84a28763","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-23T18:00:08Z","title_canon_sha256":"edb625e0abc86afcbf1cea7d5a107ab42af3a5ef61a809d5938cc2a70e178c63"},"schema_version":"1.0","source":{"id":"2504.17006","kind":"arxiv","version":1}},"canonical_sha256":"8ca949814617d809d468e45209933ab832e0d86fe124dc59557cfcd6687bee51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ca949814617d809d468e45209933ab832e0d86fe124dc59557cfcd6687bee51","first_computed_at":"2026-07-05T10:53:20.473858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:20.473858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3VBcYVT1BIN//nu92HIZr1jEreSK5HTVOdmcydGl45IhH1oUfv2oInu1OgkfEXYQt8jDdr/oUzeiv0fa13L4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:20.474392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f637c24dfb4395c74ed59d30749abe9e2f507c7998c71d9651d99dc9027fcc","sha256:acb6e15df14dfbe957613338fd9ad7ab8a2c754dbdc3f3cb56bc78a390dcb238"],"state_sha256":"f724c72fae4959ed545814cbfed3bd78fc08b1c37f847a5bba8763d045664766"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VzdJ66Y9yLmN2fagjEeg2M2AkMDj7/eMjqw7lXTcsYoASLiOSbMJWxl7j6dr9VzRHELdFRu01EimetJFl0rpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:08:45.754160Z","bundle_sha256":"d691a75045f10344596ce7deaa895e80f178adce70a32ed65ea15e4aada8d1b6"}}