{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SXR7SSYPXCOTN73Y4XGCEUTSLE","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":"bb6942f5038ef922085012268de61b6ea228d33aba153923f99be360835e462f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-05-24T20:01:33Z","title_canon_sha256":"42fcf4c7d638c0b4411cb9b9e164d26e27266ca316e6cafb6d73d65fb72dd399"},"schema_version":"1.0","source":{"id":"2605.25242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25242","created_at":"2026-05-26T02:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25242v1","created_at":"2026-05-26T02:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25242","created_at":"2026-05-26T02:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"SXR7SSYPXCOT","created_at":"2026-05-26T02:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"SXR7SSYPXCOTN73Y","created_at":"2026-05-26T02:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"SXR7SSYP","created_at":"2026-05-26T02:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:82c7c22d84bbe357b8331023b91add47b0c345ef112108ea9e32b54fdbd87cc0","target":"graph","created_at":"2026-05-26T02:04:24Z","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/2605.25242/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the increasing scale of genome language models (gLMs), their ability to decode the function of regulatory sequences remains unclear. gLM pretraining relies on sequence reconstruction, which may struggle due to the noisy, rapidly evolving nature of regulatory DNA. Self-supervised contrastive approaches provide a promising alternative. Inspired by language-image architectures like CLIP, we introduce contrastive promoter-protein pretraining (C3P). By learning to align promoters to their corresponding proteins, we leverage the rich representations of proteins learned by protein language mo","authors_text":"Alan M. Moses, Cameron Dufault, Scott Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-05-24T20:01:33Z","title":"C3P: Contrastive promoter-protein pretraining yields representations capturing bacterial gene regulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25242","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":"sha256:25e8bad43ac67309b5a9b6cc7ebd02489a4cc93a2334890602a2c22999c7fa36","target":"record","created_at":"2026-05-26T02:04:24Z","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":"bb6942f5038ef922085012268de61b6ea228d33aba153923f99be360835e462f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-05-24T20:01:33Z","title_canon_sha256":"42fcf4c7d638c0b4411cb9b9e164d26e27266ca316e6cafb6d73d65fb72dd399"},"schema_version":"1.0","source":{"id":"2605.25242","kind":"arxiv","version":1}},"canonical_sha256":"95e3f94b0fb89d36ff78e5cc225272591b6e775bd5ea2f69dfb53819ca3e8492","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95e3f94b0fb89d36ff78e5cc225272591b6e775bd5ea2f69dfb53819ca3e8492","first_computed_at":"2026-05-26T02:04:24.899401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:24.899401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a/i6wXClaBTpoAKYUmIqva4PZTM7vN4oKWsXXRxoNCKsRwf6mXsnzDh7CoKHSXn5Ip5vWv6LdVuDKLvj06ORAQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:24.900192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25e8bad43ac67309b5a9b6cc7ebd02489a4cc93a2334890602a2c22999c7fa36","sha256:82c7c22d84bbe357b8331023b91add47b0c345ef112108ea9e32b54fdbd87cc0"],"state_sha256":"4199f5a4e4d9fb211c894f221f302e81afa86542a6311844594dc9fddbcf207d"}