{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AFJRPC5HJPMVY6OJHKPGCMINC7","short_pith_number":"pith:AFJRPC5H","schema_version":"1.0","canonical_sha256":"0153178ba74bd95c79c93a9e61310d17c8883b50745becdf9e2cff824394aec7","source":{"kind":"arxiv","id":"2311.02104","version":1},"attestation_state":"computed","paper":{"title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Xishan Zhang, Yunji Chen, Zidong Du","submitted_at":"2023-11-02T03:27:51Z","abstract_excerpt":"Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to understand and deploy with limited computational resources. Currently, employing compact symbolic expressions as symbolic policies is a promising strategy to obtain simple and interpretable policies. Previous symbolic policy methods usually involve complex training processes and pre-trained neural network policies, which are inefficient and limit the application of symbolic policies. In this paper, we propose an effi"},"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":"2311.02104","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T03:27:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f1c79a0005f609cded603fc73313c6ce2d671d58a57d2844d92b877fa445e634","abstract_canon_sha256":"be26171f93a238cd4aad0a81777d75e6fa489fed2fa2ed5909657d8e57331439"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:05.337413Z","signature_b64":"jouO71X+BxyoZy03B336bP0f/Bvaouz4TYkqig9VCh/BIDwmZOBTsYwNjmzdr8gNGi0MtnjNDOZJb78UdRKNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0153178ba74bd95c79c93a9e61310d17c8883b50745becdf9e2cff824394aec7","last_reissued_at":"2026-07-05T07:09:05.336863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:05.336863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Xishan Zhang, Yunji Chen, Zidong Du","submitted_at":"2023-11-02T03:27:51Z","abstract_excerpt":"Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to understand and deploy with limited computational resources. Currently, employing compact symbolic expressions as symbolic policies is a promising strategy to obtain simple and interpretable policies. Previous symbolic policy methods usually involve complex training processes and pre-trained neural network policies, which are inefficient and limit the application of symbolic policies. In this paper, we propose an effi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02104","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/2311.02104/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":"2311.02104","created_at":"2026-07-05T07:09:05.336936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02104v1","created_at":"2026-07-05T07:09:05.336936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02104","created_at":"2026-07-05T07:09:05.336936+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFJRPC5HJPMV","created_at":"2026-07-05T07:09:05.336936+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFJRPC5HJPMVY6OJ","created_at":"2026-07-05T07:09:05.336936+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFJRPC5H","created_at":"2026-07-05T07:09:05.336936+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/AFJRPC5HJPMVY6OJHKPGCMINC7","json":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7.json","graph_json":"https://pith.science/api/pith-number/AFJRPC5HJPMVY6OJHKPGCMINC7/graph.json","events_json":"https://pith.science/api/pith-number/AFJRPC5HJPMVY6OJHKPGCMINC7/events.json","paper":"https://pith.science/paper/AFJRPC5H"},"agent_actions":{"view_html":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7","download_json":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7.json","view_paper":"https://pith.science/paper/AFJRPC5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02104&json=true","fetch_graph":"https://pith.science/api/pith-number/AFJRPC5HJPMVY6OJHKPGCMINC7/graph.json","fetch_events":"https://pith.science/api/pith-number/AFJRPC5HJPMVY6OJHKPGCMINC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/action/storage_attestation","attest_author":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/action/author_attestation","sign_citation":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/action/citation_signature","submit_replication":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/action/replication_record"}},"created_at":"2026-07-05T07:09:05.336936+00:00","updated_at":"2026-07-05T07:09:05.336936+00:00"}