{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PQZS75JVX356XAJGSJRSV4RY52","short_pith_number":"pith:PQZS75JV","canonical_record":{"source":{"id":"2410.00461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T07:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"063bb7b3d2162786ac10a242143a9916f52bc5121032c239bd4ad7f1e6c63878","abstract_canon_sha256":"8f6a9d9c8599206e7dbdc00d95ef03c7375b76bc0ebd9c07561abb81ee1ebe8f"},"schema_version":"1.0"},"canonical_sha256":"7c332ff535befbeb812692632af238eeb9a51a5ff7f612fef634aaa42c2fce2a","source":{"kind":"arxiv","id":"2410.00461","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00461","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00461v1","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00461","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"PQZS75JVX356","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"PQZS75JVX356XAJG","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"PQZS75JV","created_at":"2026-07-05T09:14:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PQZS75JVX356XAJGSJRSV4RY52","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T07:37:10Z","cross_cats_sorted":[],"title_canon_sha256":"063bb7b3d2162786ac10a242143a9916f52bc5121032c239bd4ad7f1e6c63878","abstract_canon_sha256":"8f6a9d9c8599206e7dbdc00d95ef03c7375b76bc0ebd9c07561abb81ee1ebe8f"},"schema_version":"1.0"},"canonical_sha256":"7c332ff535befbeb812692632af238eeb9a51a5ff7f612fef634aaa42c2fce2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:05.139040Z","signature_b64":"qNEo4MA1IHb3O4AQRGAeAB1GAQDUYjvAVJ0fqNZZSZ+9eK97FFxYFhoK84v8Kl72da5MJmjnXUVMeU/i1BhwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c332ff535befbeb812692632af238eeb9a51a5ff7f612fef634aaa42c2fce2a","last_reissued_at":"2026-07-05T09:14:05.138660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:05.138660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00461","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":"2026-07-05T09:14:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tw/pzNdUhFAc8YLQp2SlzaxcQu1aIeG0D0EYj9hasJmeLodvEg6C3KOeB7b1gdXd0Jr01tNQzMuMIeroIsoYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:14:10.179351Z"},"content_sha256":"6a65dc4eed4921d9ad01d9cffedc7b211d88cf09b8fdfe339dd2ab132bc375f5","schema_version":"1.0","event_id":"sha256:6a65dc4eed4921d9ad01d9cffedc7b211d88cf09b8fdfe339dd2ab132bc375f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PQZS75JVX356XAJGSJRSV4RY52","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Solution Efficiency in Reinforcement Learning: Leveraging Sub-GFlowNet and Entropy Integration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Siyi He","submitted_at":"2024-10-01T07:37:10Z","abstract_excerpt":"Traditional reinforcement learning often struggles to generate diverse, high-reward solutions, especially in domains like drug design and black-box function optimization. Markov Chain Monte Carlo (MCMC) methods provide an alternative method of RL in candidate selection but suffer from high computational costs and limited candidate diversity exploration capabilities. In response, GFlowNet, a novel neural network architecture, was introduced to model complex system dynamics and generate diverse high-reward trajectories. To further enhance this approach, this paper proposes improvements to GFlowN"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00461","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/2410.00461/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":"2026-07-05T09:14:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sADy3nRcdwKPdQY1bGkM6ow+j5Ocip1R/ePf1IcaO+O4X+HUc7qYMeDwDloRdwBszZk9PW4NH8MEfudZTcsqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:14:10.180235Z"},"content_sha256":"9caf8052f4658cd763a7a212cc0d68dc106c4060a1ab0ddb911886a4e23cc96a","schema_version":"1.0","event_id":"sha256:9caf8052f4658cd763a7a212cc0d68dc106c4060a1ab0ddb911886a4e23cc96a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQZS75JVX356XAJGSJRSV4RY52/bundle.json","state_url":"https://pith.science/pith/PQZS75JVX356XAJGSJRSV4RY52/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQZS75JVX356XAJGSJRSV4RY52/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":"2026-07-07T07:14:10Z","links":{"resolver":"https://pith.science/pith/PQZS75JVX356XAJGSJRSV4RY52","bundle":"https://pith.science/pith/PQZS75JVX356XAJGSJRSV4RY52/bundle.json","state":"https://pith.science/pith/PQZS75JVX356XAJGSJRSV4RY52/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQZS75JVX356XAJGSJRSV4RY52/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PQZS75JVX356XAJGSJRSV4RY52","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":"8f6a9d9c8599206e7dbdc00d95ef03c7375b76bc0ebd9c07561abb81ee1ebe8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T07:37:10Z","title_canon_sha256":"063bb7b3d2162786ac10a242143a9916f52bc5121032c239bd4ad7f1e6c63878"},"schema_version":"1.0","source":{"id":"2410.00461","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00461","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00461v1","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00461","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"PQZS75JVX356","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"PQZS75JVX356XAJG","created_at":"2026-07-05T09:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"PQZS75JV","created_at":"2026-07-05T09:14:05Z"}],"graph_snapshots":[{"event_id":"sha256:9caf8052f4658cd763a7a212cc0d68dc106c4060a1ab0ddb911886a4e23cc96a","target":"graph","created_at":"2026-07-05T09:14:05Z","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/2410.00461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditional reinforcement learning often struggles to generate diverse, high-reward solutions, especially in domains like drug design and black-box function optimization. Markov Chain Monte Carlo (MCMC) methods provide an alternative method of RL in candidate selection but suffer from high computational costs and limited candidate diversity exploration capabilities. In response, GFlowNet, a novel neural network architecture, was introduced to model complex system dynamics and generate diverse high-reward trajectories. To further enhance this approach, this paper proposes improvements to GFlowN","authors_text":"Siyi He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T07:37:10Z","title":"Enhancing Solution Efficiency in Reinforcement Learning: Leveraging Sub-GFlowNet and Entropy Integration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00461","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":"sha256:6a65dc4eed4921d9ad01d9cffedc7b211d88cf09b8fdfe339dd2ab132bc375f5","target":"record","created_at":"2026-07-05T09:14:05Z","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":"8f6a9d9c8599206e7dbdc00d95ef03c7375b76bc0ebd9c07561abb81ee1ebe8f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T07:37:10Z","title_canon_sha256":"063bb7b3d2162786ac10a242143a9916f52bc5121032c239bd4ad7f1e6c63878"},"schema_version":"1.0","source":{"id":"2410.00461","kind":"arxiv","version":1}},"canonical_sha256":"7c332ff535befbeb812692632af238eeb9a51a5ff7f612fef634aaa42c2fce2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c332ff535befbeb812692632af238eeb9a51a5ff7f612fef634aaa42c2fce2a","first_computed_at":"2026-07-05T09:14:05.138660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:14:05.138660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNEo4MA1IHb3O4AQRGAeAB1GAQDUYjvAVJ0fqNZZSZ+9eK97FFxYFhoK84v8Kl72da5MJmjnXUVMeU/i1BhwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:14:05.139040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00461","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a65dc4eed4921d9ad01d9cffedc7b211d88cf09b8fdfe339dd2ab132bc375f5","sha256:9caf8052f4658cd763a7a212cc0d68dc106c4060a1ab0ddb911886a4e23cc96a"],"state_sha256":"72038a80b6affab5c6888e25c65fe6dc3305edcf5503e11d5e8f94ef86ad011d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCDf1aQW0kl9ZdK7KnGc0Dpkiz5xJReizNDQwiC5RelGM5tjhNQkGt2nQou+dxtGzsOyZXHhoDh1D1O/AfKCDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:14:10.183446Z","bundle_sha256":"34b47dc2398fcf4dfb7955fd91f5ea66c92c8009be9655bdc00fa999e4c40abc"}}