{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AFJRPC5HJPMVY6OJHKPGCMINC7","short_pith_number":"pith:AFJRPC5H","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"},"canonical_sha256":"0153178ba74bd95c79c93a9e61310d17c8883b50745becdf9e2cff824394aec7","source":{"kind":"arxiv","id":"2311.02104","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02104","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02104v1","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02104","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"AFJRPC5HJPMV","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"pith_short_16","alias_value":"AFJRPC5HJPMVY6OJ","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"pith_short_8","alias_value":"AFJRPC5H","created_at":"2026-07-05T07:09:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AFJRPC5HJPMVY6OJHKPGCMINC7","target":"record","payload":{"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"},"canonical_sha256":"0153178ba74bd95c79c93a9e61310d17c8883b50745becdf9e2cff824394aec7","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"},"source_kind":"arxiv","source_id":"2311.02104","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":"2026-07-05T07:09:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1T7v3u/m9dSynRxOM9cJzgsbt4K+fr/6AVfDwY9LWW19febJH37ZPExOQ2HXBQPhKFUnifBQuflQbQFHdUmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:26:44.919719Z"},"content_sha256":"f01a74d98388968b04e7d3fbd4ac044ba6f26ec4cf069f02cc8cdf4c6daa6bf5","schema_version":"1.0","event_id":"sha256:f01a74d98388968b04e7d3fbd4ac044ba6f26ec4cf069f02cc8cdf4c6daa6bf5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AFJRPC5HJPMVY6OJHKPGCMINC7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:09:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7MB78psP4nl8eIH1LhykkOUcqzxSL23e/RRARCZRlFLMUkWCxBF9VBbheWwmdP8b0swlW8ozmm+fgmp9cO9BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:26:44.920089Z"},"content_sha256":"25567097f5f008976d83143410e86e44c8d4dbeac05834add7e953ee386d6e45","schema_version":"1.0","event_id":"sha256:25567097f5f008976d83143410e86e44c8d4dbeac05834add7e953ee386d6e45"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/bundle.json","state_url":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/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":"2026-07-07T09:26:44Z","links":{"resolver":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7","bundle":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/bundle.json","state":"https://pith.science/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AFJRPC5HJPMVY6OJHKPGCMINC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AFJRPC5HJPMVY6OJHKPGCMINC7","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":"be26171f93a238cd4aad0a81777d75e6fa489fed2fa2ed5909657d8e57331439","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T03:27:51Z","title_canon_sha256":"f1c79a0005f609cded603fc73313c6ce2d671d58a57d2844d92b877fa445e634"},"schema_version":"1.0","source":{"id":"2311.02104","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02104","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02104v1","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02104","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"pith_short_12","alias_value":"AFJRPC5HJPMV","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"pith_short_16","alias_value":"AFJRPC5HJPMVY6OJ","created_at":"2026-07-05T07:09:05Z"},{"alias_kind":"pith_short_8","alias_value":"AFJRPC5H","created_at":"2026-07-05T07:09:05Z"}],"graph_snapshots":[{"event_id":"sha256:25567097f5f008976d83143410e86e44c8d4dbeac05834add7e953ee386d6e45","target":"graph","created_at":"2026-07-05T07:09:05Z","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/2311.02104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Xing Hu, Xishan Zhang, Yunji Chen, Zidong Du","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T03:27:51Z","title":"Efficient Symbolic Policy Learning with Differentiable Symbolic Expression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02104","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:f01a74d98388968b04e7d3fbd4ac044ba6f26ec4cf069f02cc8cdf4c6daa6bf5","target":"record","created_at":"2026-07-05T07:09:05Z","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":"be26171f93a238cd4aad0a81777d75e6fa489fed2fa2ed5909657d8e57331439","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-02T03:27:51Z","title_canon_sha256":"f1c79a0005f609cded603fc73313c6ce2d671d58a57d2844d92b877fa445e634"},"schema_version":"1.0","source":{"id":"2311.02104","kind":"arxiv","version":1}},"canonical_sha256":"0153178ba74bd95c79c93a9e61310d17c8883b50745becdf9e2cff824394aec7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0153178ba74bd95c79c93a9e61310d17c8883b50745becdf9e2cff824394aec7","first_computed_at":"2026-07-05T07:09:05.336863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:09:05.336863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jouO71X+BxyoZy03B336bP0f/Bvaouz4TYkqig9VCh/BIDwmZOBTsYwNjmzdr8gNGi0MtnjNDOZJb78UdRKNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:09:05.337413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02104","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f01a74d98388968b04e7d3fbd4ac044ba6f26ec4cf069f02cc8cdf4c6daa6bf5","sha256:25567097f5f008976d83143410e86e44c8d4dbeac05834add7e953ee386d6e45"],"state_sha256":"8106a25e6ec9b23556560d5fb62fdfd212f096369c738b79e1d55e3af8b5b136"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Izc5idjnRDLFFRMs53pQaeAp+8hAErXBslNtmIjbGpU5w8hPn/kaERrF7kIbguIb30v9BzRaEHVc2ccSKO7jAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:26:44.922017Z","bundle_sha256":"c07aa3e3c4d0a876f8622600b018eaad2b1b149e4393fbdbf2411f06a9d2f76a"}}