{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQHSZWNBDMSI3FIPHSUBR6EZBT","short_pith_number":"pith:ZQHSZWNB","schema_version":"1.0","canonical_sha256":"cc0f2cd9a11b248d950f3ca818f8990cdf2ce8d0419e39224cca511eab4ecaf0","source":{"kind":"arxiv","id":"2506.12366","version":1},"attestation_state":"computed","paper":{"title":"Ghost Policies: A New Paradigm for Understanding and Learning from Failure in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xabier Olaz","submitted_at":"2025-06-14T05:56:42Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) agents often exhibit intricate failure modes that are difficult to understand, debug, and learn from. This opacity hinders their reliable deployment in real-world applications. To address this critical gap, we introduce ``Ghost Policies,'' a concept materialized through Arvolution, a novel Augmented Reality (AR) framework. Arvolution renders an agent's historical failed policy trajectories as semi-transparent ``ghosts'' that coexist spatially and temporally with the active agent, enabling an intuitive visualization of policy divergence. Arvolution uniquely int"},"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":"2506.12366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-14T05:56:42Z","cross_cats_sorted":[],"title_canon_sha256":"754d77a82602f2c10121e3a86cfddb53ee77e5ea84e877093590995c899cda5a","abstract_canon_sha256":"d8d669ba5eabdc5f4c8872b6aba34d9b404654ce36d2f45c0de7f869e9e808a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:52.105074Z","signature_b64":"QTtYQ0xpUoJ7BoZ7pTAGvmT47SrJt+MLTnfxpGHAWE8Wktt9h8Z6dO9ASRfWH9pNZU81YPGmXtFZqbTCZAvyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc0f2cd9a11b248d950f3ca818f8990cdf2ce8d0419e39224cca511eab4ecaf0","last_reissued_at":"2026-07-05T11:21:52.104600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:52.104600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ghost Policies: A New Paradigm for Understanding and Learning from Failure in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xabier Olaz","submitted_at":"2025-06-14T05:56:42Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) agents often exhibit intricate failure modes that are difficult to understand, debug, and learn from. This opacity hinders their reliable deployment in real-world applications. To address this critical gap, we introduce ``Ghost Policies,'' a concept materialized through Arvolution, a novel Augmented Reality (AR) framework. Arvolution renders an agent's historical failed policy trajectories as semi-transparent ``ghosts'' that coexist spatially and temporally with the active agent, enabling an intuitive visualization of policy divergence. Arvolution uniquely int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12366","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/2506.12366/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":"2506.12366","created_at":"2026-07-05T11:21:52.104658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12366v1","created_at":"2026-07-05T11:21:52.104658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12366","created_at":"2026-07-05T11:21:52.104658+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQHSZWNBDMSI","created_at":"2026-07-05T11:21:52.104658+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQHSZWNBDMSI3FIP","created_at":"2026-07-05T11:21:52.104658+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQHSZWNB","created_at":"2026-07-05T11:21:52.104658+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/ZQHSZWNBDMSI3FIPHSUBR6EZBT","json":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT.json","graph_json":"https://pith.science/api/pith-number/ZQHSZWNBDMSI3FIPHSUBR6EZBT/graph.json","events_json":"https://pith.science/api/pith-number/ZQHSZWNBDMSI3FIPHSUBR6EZBT/events.json","paper":"https://pith.science/paper/ZQHSZWNB"},"agent_actions":{"view_html":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT","download_json":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT.json","view_paper":"https://pith.science/paper/ZQHSZWNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12366&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQHSZWNBDMSI3FIPHSUBR6EZBT/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQHSZWNBDMSI3FIPHSUBR6EZBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT/action/storage_attestation","attest_author":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT/action/author_attestation","sign_citation":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT/action/citation_signature","submit_replication":"https://pith.science/pith/ZQHSZWNBDMSI3FIPHSUBR6EZBT/action/replication_record"}},"created_at":"2026-07-05T11:21:52.104658+00:00","updated_at":"2026-07-05T11:21:52.104658+00:00"}