{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q2ZM5GCUCJQRCYVBBHX4ZRPVIF","short_pith_number":"pith:Q2ZM5GCU","canonical_record":{"source":{"id":"2410.04461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T12:22:32Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"6bbf487be07598fcf8e8047fd3ed36c19e803e1430db561c8e233867eff99484","abstract_canon_sha256":"b46d653be820f1c00fb30b721fcd2d96733ab4d4f353d00a6f55449ae8ca69fb"},"schema_version":"1.0"},"canonical_sha256":"86b2ce985412611162a109efccc5f541594184c143bc97c7b79cf7272fd9e61d","source":{"kind":"arxiv","id":"2410.04461","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04461","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04461v2","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04461","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"Q2ZM5GCUCJQR","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"Q2ZM5GCUCJQRCYVB","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"Q2ZM5GCU","created_at":"2026-07-05T11:22:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q2ZM5GCUCJQRCYVBBHX4ZRPVIF","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T12:22:32Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"6bbf487be07598fcf8e8047fd3ed36c19e803e1430db561c8e233867eff99484","abstract_canon_sha256":"b46d653be820f1c00fb30b721fcd2d96733ab4d4f353d00a6f55449ae8ca69fb"},"schema_version":"1.0"},"canonical_sha256":"86b2ce985412611162a109efccc5f541594184c143bc97c7b79cf7272fd9e61d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:32.682155Z","signature_b64":"bc7HEroFlWx0RfzvPm+XFF7iehHApT0YhHcywk8LXyuo9m8EYt4IZyz0PPa+SMWOwg9K98SLBr5HkzRagRlVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86b2ce985412611162a109efccc5f541594184c143bc97c7b79cf7272fd9e61d","last_reissued_at":"2026-07-05T11:22:32.681645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:32.681645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04461","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQFc21xwJ75446JL9ffP9Ma/GQz67TKya12WbsTEEdNjr6h4QRacRNpG8zfy4U+oKBYk56/jA2k/YahmJDsXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:31:46.016027Z"},"content_sha256":"c2ee553f1327d838f63fef9ec5716a5cb0b5f7a8a4da313301e5cfd9f2ecfe90","schema_version":"1.0","event_id":"sha256:c2ee553f1327d838f63fef9ec5716a5cb0b5f7a8a4da313301e5cfd9f2ecfe90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q2ZM5GCUCJQRCYVBBHX4ZRPVIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improved Off-policy Reinforcement Learning in Biological Sequence Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Alex Hern\\'andez-Garc\\'ia, Emmanuel Bengio, Hyeonah Kim, Jinkyoo Park, Minsu Kim, Sanghyeok Choi, Taeyoung Yun","submitted_at":"2024-10-06T12:22:32Z","abstract_excerpt":"Designing biological sequences with desired properties is challenging due to vast search spaces and limited evaluation budgets. Although reinforcement learning methods use proxy models for rapid reward evaluation, insufficient training data can cause proxy misspecification on out-of-distribution inputs. To address this, we propose a novel off-policy search, $\\delta$-Conservative Search, that enhances robustness by restricting policy exploration to reliable regions. Starting from high-score offline sequences, we inject noise by randomly masking tokens with probability $\\delta$, then denoise the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04461","kind":"arxiv","version":2},"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/2410.04461/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":"2026-07-05T11:22:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dvLs92SUfQNZ5bSgn+66EY8j3EuFTAp8owee8zdHLq97eAATt/T2RP+QgGwB/L9aWOC34rsNR0J/U0FbJkG7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:31:46.016522Z"},"content_sha256":"fecba471e8b38658d97625f65442d634557aba7fcb779532b566bd7ba376110e","schema_version":"1.0","event_id":"sha256:fecba471e8b38658d97625f65442d634557aba7fcb779532b566bd7ba376110e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF/bundle.json","state_url":"https://pith.science/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF/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":"2026-08-10T09:31:46Z","links":{"resolver":"https://pith.science/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF","bundle":"https://pith.science/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF/bundle.json","state":"https://pith.science/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q2ZM5GCUCJQRCYVBBHX4ZRPVIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q2ZM5GCUCJQRCYVBBHX4ZRPVIF","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":"b46d653be820f1c00fb30b721fcd2d96733ab4d4f353d00a6f55449ae8ca69fb","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T12:22:32Z","title_canon_sha256":"6bbf487be07598fcf8e8047fd3ed36c19e803e1430db561c8e233867eff99484"},"schema_version":"1.0","source":{"id":"2410.04461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04461","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04461v2","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04461","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"pith_short_12","alias_value":"Q2ZM5GCUCJQR","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"pith_short_16","alias_value":"Q2ZM5GCUCJQRCYVB","created_at":"2026-07-05T11:22:32Z"},{"alias_kind":"pith_short_8","alias_value":"Q2ZM5GCU","created_at":"2026-07-05T11:22:32Z"}],"graph_snapshots":[{"event_id":"sha256:fecba471e8b38658d97625f65442d634557aba7fcb779532b566bd7ba376110e","target":"graph","created_at":"2026-07-05T11:22:32Z","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/2410.04461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing biological sequences with desired properties is challenging due to vast search spaces and limited evaluation budgets. Although reinforcement learning methods use proxy models for rapid reward evaluation, insufficient training data can cause proxy misspecification on out-of-distribution inputs. To address this, we propose a novel off-policy search, $\\delta$-Conservative Search, that enhances robustness by restricting policy exploration to reliable regions. Starting from high-score offline sequences, we inject noise by randomly masking tokens with probability $\\delta$, then denoise the","authors_text":"Alex Hern\\'andez-Garc\\'ia, Emmanuel Bengio, Hyeonah Kim, Jinkyoo Park, Minsu Kim, Sanghyeok Choi, Taeyoung Yun","cross_cats":["q-bio.BM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T12:22:32Z","title":"Improved Off-policy Reinforcement Learning in Biological Sequence Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04461","kind":"arxiv","version":2},"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:c2ee553f1327d838f63fef9ec5716a5cb0b5f7a8a4da313301e5cfd9f2ecfe90","target":"record","created_at":"2026-07-05T11:22:32Z","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":"b46d653be820f1c00fb30b721fcd2d96733ab4d4f353d00a6f55449ae8ca69fb","cross_cats_sorted":["q-bio.BM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T12:22:32Z","title_canon_sha256":"6bbf487be07598fcf8e8047fd3ed36c19e803e1430db561c8e233867eff99484"},"schema_version":"1.0","source":{"id":"2410.04461","kind":"arxiv","version":2}},"canonical_sha256":"86b2ce985412611162a109efccc5f541594184c143bc97c7b79cf7272fd9e61d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86b2ce985412611162a109efccc5f541594184c143bc97c7b79cf7272fd9e61d","first_computed_at":"2026-07-05T11:22:32.681645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:32.681645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bc7HEroFlWx0RfzvPm+XFF7iehHApT0YhHcywk8LXyuo9m8EYt4IZyz0PPa+SMWOwg9K98SLBr5HkzRagRlVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:32.682155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2ee553f1327d838f63fef9ec5716a5cb0b5f7a8a4da313301e5cfd9f2ecfe90","sha256:fecba471e8b38658d97625f65442d634557aba7fcb779532b566bd7ba376110e"],"state_sha256":"e5135ba4557cb3299ee4618e374b9585b5fdd59b3a317fbdfed3a7a9082a0531"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"riqfsoBmoPRiA6LVGv1yrSe/ei1vFJxpPjoXAD4vaHWGrt3vPlBc6tH+4i7J3VZc4CbhiVSxj61qUEf7zxlnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:31:46.020390Z","bundle_sha256":"239c78165c29c87ed26301a89d92cce3990b0d99bc1f7db769ae1a558131308d"}}