{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:X3P4TKVY47LSHIVUDRGBMVX36C","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":"c761da57a050be214bd517c300152d44ba93d45970b6eccf10aff6d0dc4628ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T11:42:01Z","title_canon_sha256":"7eb0c1f51e3c9c0f08782435c84d6e184259f25a95b7779f3ddddcf37b685332"},"schema_version":"1.0","source":{"id":"2606.18961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18961","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18961v1","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18961","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"X3P4TKVY47LS","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"X3P4TKVY47LSHIVU","created_at":"2026-06-19T16:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"X3P4TKVY","created_at":"2026-06-19T16:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:f0115e7ad2ae1975d94a28f88075fee409073efa87d50e1b93093b1c7c5f78e3","target":"graph","created_at":"2026-06-19T16:11:53Z","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/2606.18961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein language models (PLMs) have emerged as powerful tools for controllable biomolecular design, yet their post-training adaptation typically relies on costly wet-lab validation or curated preference datasets. To overcome this supervision bottleneck, we introduce unsupervised reward optimization of PLMs, a comprehensive framework for steerable protein generation without ground-truth labels. Our key insight is that task-agnostic rewards, which combine intrinsic model uncertainty with extrinsic semantic consistency informed by protein representation models, exhibit strong correlation with con","authors_text":"Lanqing Li, Pheng-Ann Heng, Shentong Mo, Yang Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T11:42:01Z","title":"Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18961","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":"sha256:6dcedc7ecf9d44750f314460354617108e9b733953529f617b0f23fa906b220b","target":"record","created_at":"2026-06-19T16:11:53Z","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":"c761da57a050be214bd517c300152d44ba93d45970b6eccf10aff6d0dc4628ee","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-17T11:42:01Z","title_canon_sha256":"7eb0c1f51e3c9c0f08782435c84d6e184259f25a95b7779f3ddddcf37b685332"},"schema_version":"1.0","source":{"id":"2606.18961","kind":"arxiv","version":1}},"canonical_sha256":"bedfc9aab8e7d723a2b41c4c1656fbf0ba3210c2d363e05c4fcb1fef08eaac9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bedfc9aab8e7d723a2b41c4c1656fbf0ba3210c2d363e05c4fcb1fef08eaac9f","first_computed_at":"2026-06-19T16:11:53.050530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:53.050530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2AXFA1rGXt0y78/h0RqC4dg46E7AWR0DQ5PSCj48b4K+vg6AEV/+zHBi+tAaslNVY9lM6P09Lj90Sn3WR/E5Cw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:53.050891Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dcedc7ecf9d44750f314460354617108e9b733953529f617b0f23fa906b220b","sha256:f0115e7ad2ae1975d94a28f88075fee409073efa87d50e1b93093b1c7c5f78e3"],"state_sha256":"ee87e513644e74fb469c9a421a23741b4933a16e7f21a4165fce812dce6bbe70"}