{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PAZQZL3VRLAOSJDMM3XFO2SBFR","short_pith_number":"pith:PAZQZL3V","schema_version":"1.0","canonical_sha256":"78330caf758ac0e9246c66ee576a412c6fa711ece0317aa17910631f0f33a939","source":{"kind":"arxiv","id":"2406.06107","version":1},"attestation_state":"computed","paper":{"title":"EXPIL: Explanatory Predicate Invention for Learning in Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Devendra Singh Dhami, Hikaru Shindo, Jingyuan Sha, Kristian Kersting, Quentin Delfosse","submitted_at":"2024-06-10T08:46:49Z","abstract_excerpt":"Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's actions. Recent research has attempted to address this issue by using the guidance of pretrained neural agents to encode logic-based policies, allowing for interpretable decisions. A drawback of such approaches is the requirement of large amounts of predefined background knowledge in the form of predicates, limiting its applicability and scalability. In this w"},"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":"2406.06107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-10T08:46:49Z","cross_cats_sorted":[],"title_canon_sha256":"3e005f125d749117a08d2977b91094b4d969a8fcc520b572777060cc44eb3246","abstract_canon_sha256":"c4121e4e4412716cfca60010070c71285540c71d7de61614b75c629b3fed18f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:37.893521Z","signature_b64":"nFhx2rNL7KvvWZRbgmC9wL/BV1B6+D+q4dLTbw/3HHLTM33YCj8lK4qEMnJRx6oNAozjXaJCjHR7wsTUnHWADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78330caf758ac0e9246c66ee576a412c6fa711ece0317aa17910631f0f33a939","last_reissued_at":"2026-07-05T08:29:37.893102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:37.893102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EXPIL: Explanatory Predicate Invention for Learning in Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Devendra Singh Dhami, Hikaru Shindo, Jingyuan Sha, Kristian Kersting, Quentin Delfosse","submitted_at":"2024-06-10T08:46:49Z","abstract_excerpt":"Reinforcement learning (RL) has proven to be a powerful tool for training agents that excel in various games. However, the black-box nature of neural network models often hinders our ability to understand the reasoning behind the agent's actions. Recent research has attempted to address this issue by using the guidance of pretrained neural agents to encode logic-based policies, allowing for interpretable decisions. A drawback of such approaches is the requirement of large amounts of predefined background knowledge in the form of predicates, limiting its applicability and scalability. In this w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06107","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/2406.06107/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":"2406.06107","created_at":"2026-07-05T08:29:37.893156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06107v1","created_at":"2026-07-05T08:29:37.893156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06107","created_at":"2026-07-05T08:29:37.893156+00:00"},{"alias_kind":"pith_short_12","alias_value":"PAZQZL3VRLAO","created_at":"2026-07-05T08:29:37.893156+00:00"},{"alias_kind":"pith_short_16","alias_value":"PAZQZL3VRLAOSJDM","created_at":"2026-07-05T08:29:37.893156+00:00"},{"alias_kind":"pith_short_8","alias_value":"PAZQZL3V","created_at":"2026-07-05T08:29:37.893156+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/PAZQZL3VRLAOSJDMM3XFO2SBFR","json":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR.json","graph_json":"https://pith.science/api/pith-number/PAZQZL3VRLAOSJDMM3XFO2SBFR/graph.json","events_json":"https://pith.science/api/pith-number/PAZQZL3VRLAOSJDMM3XFO2SBFR/events.json","paper":"https://pith.science/paper/PAZQZL3V"},"agent_actions":{"view_html":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR","download_json":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR.json","view_paper":"https://pith.science/paper/PAZQZL3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06107&json=true","fetch_graph":"https://pith.science/api/pith-number/PAZQZL3VRLAOSJDMM3XFO2SBFR/graph.json","fetch_events":"https://pith.science/api/pith-number/PAZQZL3VRLAOSJDMM3XFO2SBFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR/action/storage_attestation","attest_author":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR/action/author_attestation","sign_citation":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR/action/citation_signature","submit_replication":"https://pith.science/pith/PAZQZL3VRLAOSJDMM3XFO2SBFR/action/replication_record"}},"created_at":"2026-07-05T08:29:37.893156+00:00","updated_at":"2026-07-05T08:29:37.893156+00:00"}