{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VIRSTAIBQ5GXYVVMRY5XT33CZP","short_pith_number":"pith:VIRSTAIB","canonical_record":{"source":{"id":"2506.17766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-21T17:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"37e698352df3c0aa781c2baf6b0cc92e4f3142402f77767b04de29ff1a10d72b","abstract_canon_sha256":"06c58f6e7fc15c788fa9e6d30ba36f82789102c4c52278439616083e28527738"},"schema_version":"1.0"},"canonical_sha256":"aa23298101874d7c56ac8e3b79ef62cbe337d9c48306a55bad0bd8cad1b16786","source":{"kind":"arxiv","id":"2506.17766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17766","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17766v1","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17766","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"VIRSTAIBQ5GX","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_16","alias_value":"VIRSTAIBQ5GXYVVM","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_8","alias_value":"VIRSTAIB","created_at":"2026-07-05T11:25:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VIRSTAIBQ5GXYVVMRY5XT33CZP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-21T17:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"37e698352df3c0aa781c2baf6b0cc92e4f3142402f77767b04de29ff1a10d72b","abstract_canon_sha256":"06c58f6e7fc15c788fa9e6d30ba36f82789102c4c52278439616083e28527738"},"schema_version":"1.0"},"canonical_sha256":"aa23298101874d7c56ac8e3b79ef62cbe337d9c48306a55bad0bd8cad1b16786","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:22.893788Z","signature_b64":"0fbPcQsXxKzq8aFPzLYd9ScVvs3GWhVTO9wWhineXr0UQQbmn4D7rxvJy2lqcjUeDdZV6Z1CMnpwwa0KWpFIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa23298101874d7c56ac8e3b79ef62cbe337d9c48306a55bad0bd8cad1b16786","last_reissued_at":"2026-07-05T11:25:22.893401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:22.893401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17766","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":"2026-07-05T11:25:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8DYLkMHOazjf0HNj6LcutpVbufNKGRso3K5FogIQx4lFNw18nJs5FPDyy7oj//ykctkCKjZRHJFusqisrUYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:11:53.858419Z"},"content_sha256":"257ee6ef8dd5053e0b1f485e97917df675ada6fb25a38921fe01bee59aa62cca","schema_version":"1.0","event_id":"sha256:257ee6ef8dd5053e0b1f485e97917df675ada6fb25a38921fe01bee59aa62cca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VIRSTAIBQ5GXYVVMRY5XT33CZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Genomic Models via Task-Specific Self-Pretraining","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.GN","authors_text":"Parameswari Krishnamurthy, Ratish Puduppully, Sohan Mupparapu","submitted_at":"2025-06-21T17:19:21Z","abstract_excerpt":"Pretraining DNA language models (DNALMs) on the full human genome is resource-intensive, yet often considered necessary for strong downstream performance. Inspired by recent findings in NLP and long-context modeling, we explore an alternative: self-pretraining on task-specific, unlabeled data. Using the BEND benchmark, we show that DNALMs trained with self-pretraining match or exceed the performance of models trained from scratch under identical compute. While genome-scale pretraining may still offer higher absolute performance, task-specific self-pretraining provides a practical and compute-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17766","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/2506.17766/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":"2026-07-05T11:25:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wJdM/EgzE+lIHAxfF1imGGiOA/RSEOBmdzPndqtAo5vH8FkyCmCAYBIsRLj974lwYxrULFtRa3RYIpbQQWXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:11:53.859177Z"},"content_sha256":"4de8303b6eaa11e5e37b2077cf9958fb1a2276604865a6d013add71db9d1bd89","schema_version":"1.0","event_id":"sha256:4de8303b6eaa11e5e37b2077cf9958fb1a2276604865a6d013add71db9d1bd89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP/bundle.json","state_url":"https://pith.science/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP/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":"2026-08-22T23:11:53Z","links":{"resolver":"https://pith.science/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP","bundle":"https://pith.science/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP/bundle.json","state":"https://pith.science/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VIRSTAIBQ5GXYVVMRY5XT33CZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VIRSTAIBQ5GXYVVMRY5XT33CZP","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":"06c58f6e7fc15c788fa9e6d30ba36f82789102c4c52278439616083e28527738","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-21T17:19:21Z","title_canon_sha256":"37e698352df3c0aa781c2baf6b0cc92e4f3142402f77767b04de29ff1a10d72b"},"schema_version":"1.0","source":{"id":"2506.17766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17766","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17766v1","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17766","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_12","alias_value":"VIRSTAIBQ5GX","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_16","alias_value":"VIRSTAIBQ5GXYVVM","created_at":"2026-07-05T11:25:22Z"},{"alias_kind":"pith_short_8","alias_value":"VIRSTAIB","created_at":"2026-07-05T11:25:22Z"}],"graph_snapshots":[{"event_id":"sha256:4de8303b6eaa11e5e37b2077cf9958fb1a2276604865a6d013add71db9d1bd89","target":"graph","created_at":"2026-07-05T11:25:22Z","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/2506.17766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining DNA language models (DNALMs) on the full human genome is resource-intensive, yet often considered necessary for strong downstream performance. Inspired by recent findings in NLP and long-context modeling, we explore an alternative: self-pretraining on task-specific, unlabeled data. Using the BEND benchmark, we show that DNALMs trained with self-pretraining match or exceed the performance of models trained from scratch under identical compute. While genome-scale pretraining may still offer higher absolute performance, task-specific self-pretraining provides a practical and compute-e","authors_text":"Parameswari Krishnamurthy, Ratish Puduppully, Sohan Mupparapu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-21T17:19:21Z","title":"Improving Genomic Models via Task-Specific Self-Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17766","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":"sha256:257ee6ef8dd5053e0b1f485e97917df675ada6fb25a38921fe01bee59aa62cca","target":"record","created_at":"2026-07-05T11:25:22Z","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":"06c58f6e7fc15c788fa9e6d30ba36f82789102c4c52278439616083e28527738","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-06-21T17:19:21Z","title_canon_sha256":"37e698352df3c0aa781c2baf6b0cc92e4f3142402f77767b04de29ff1a10d72b"},"schema_version":"1.0","source":{"id":"2506.17766","kind":"arxiv","version":1}},"canonical_sha256":"aa23298101874d7c56ac8e3b79ef62cbe337d9c48306a55bad0bd8cad1b16786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa23298101874d7c56ac8e3b79ef62cbe337d9c48306a55bad0bd8cad1b16786","first_computed_at":"2026-07-05T11:25:22.893401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:22.893401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0fbPcQsXxKzq8aFPzLYd9ScVvs3GWhVTO9wWhineXr0UQQbmn4D7rxvJy2lqcjUeDdZV6Z1CMnpwwa0KWpFIDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:22.893788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257ee6ef8dd5053e0b1f485e97917df675ada6fb25a38921fe01bee59aa62cca","sha256:4de8303b6eaa11e5e37b2077cf9958fb1a2276604865a6d013add71db9d1bd89"],"state_sha256":"5e65b6b25fc0003da6f5c19a3ef4c8b5b42a96a7b3a70f7670e490e169d1d8a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jo4bgKAHIH3HjmXuphUu1sU34q7uhLsGuHbjnhcvAZY7X7XPdRrfHgJLo5sJ6sMUuIXHNe1mqsyno2rQHjtAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:11:53.864360Z","bundle_sha256":"ce18bfa8a4de32df55ce62bc320fcde53b1e3732c40de232f29993a186a15e2f"}}