{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R37X2X5WLDE7ZQF5G5DPOT5LGC","short_pith_number":"pith:R37X2X5W","canonical_record":{"source":{"id":"2502.03499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-02-05T09:20:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"014ddc3265daf509b7da104909e23ee0daf2c86ede9d2eba42edf89f631da7c6","abstract_canon_sha256":"8b2f83f1dbd1ae7708fbedcfb29914fa6e868df7ac08792548201cc843de1ec1"},"schema_version":"1.0"},"canonical_sha256":"8eff7d5fb658c9fcc0bd3746f74fab308bb9b87514e0dd037ddcd0ec004f8e11","source":{"kind":"arxiv","id":"2502.03499","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03499","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03499v1","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03499","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"R37X2X5WLDE7","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"R37X2X5WLDE7ZQF5","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"R37X2X5W","created_at":"2026-07-05T10:10:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R37X2X5WLDE7ZQF5G5DPOT5LGC","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-02-05T09:20:52Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"014ddc3265daf509b7da104909e23ee0daf2c86ede9d2eba42edf89f631da7c6","abstract_canon_sha256":"8b2f83f1dbd1ae7708fbedcfb29914fa6e868df7ac08792548201cc843de1ec1"},"schema_version":"1.0"},"canonical_sha256":"8eff7d5fb658c9fcc0bd3746f74fab308bb9b87514e0dd037ddcd0ec004f8e11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:11.241963Z","signature_b64":"RH3yUaZ51PYz/Cz2mDEkvXp1seHMF49seFblE0jH6C7EcMyf6/wex2bOUMzeWxE3JcMdgsMaqzOj+v+Pxxm+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eff7d5fb658c9fcc0bd3746f74fab308bb9b87514e0dd037ddcd0ec004f8e11","last_reissued_at":"2026-07-05T10:10:11.241575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:11.241575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03499","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":"2026-07-05T10:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2EJd2TFaqHuhhahqpvQUnGo7eAZ4w8eBwZLNm56h7SIFXNggY3qRcjy7GA6nOCRxDUWhKT3iYwcOhGk0mjmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:13:30.114568Z"},"content_sha256":"6b9a0a864b4c6de99cc4f04014b285a9f5716c282f09fca47215f840627385e9","schema_version":"1.0","event_id":"sha256:6b9a0a864b4c6de99cc4f04014b285a9f5716c282f09fca47215f840627385e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R37X2X5WLDE7ZQF5G5DPOT5LGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Omni-DNA: A Unified Genomic Foundation Model for Cross-Modal and Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Caihua Shan, Dongsheng Li, Guy-Bart Stan, Vallijah Subasri, Yifei Shen, Yiren Zhao, Zehui Li","submitted_at":"2025-02-05T09:20:52Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable generalizability across diverse tasks, yet genomic foundation models (GFMs) still require separate finetuning for each downstream application, creating significant overhead as model sizes grow. Moreover, existing GFMs are constrained by rigid output formats, limiting their applicability to various genomic tasks. In this work, we revisit the transformer-based auto-regressive models and introduce Omni-DNA, a family of cross-modal multi-task models ranging from 20 million to 1 billion parameters. Our approach consists of two stages: (i) pretrain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03499","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/2502.03499/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":"2026-07-05T10:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jfmz4PN1l8XjTdUWcmEouio+lcSvarcoOuAqKfsRVasa74JbN3p0cOQGvx+hATDPGFoftPmhBgXfp3NbmOwrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T00:13:30.115058Z"},"content_sha256":"24aa2e79e7b8b1d1d6dc92728df44914c210a35bc6d7c642af9f74c4a025aa92","schema_version":"1.0","event_id":"sha256:24aa2e79e7b8b1d1d6dc92728df44914c210a35bc6d7c642af9f74c4a025aa92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC/bundle.json","state_url":"https://pith.science/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC/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":"2026-08-10T00:13:30Z","links":{"resolver":"https://pith.science/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC","bundle":"https://pith.science/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC/bundle.json","state":"https://pith.science/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R37X2X5WLDE7ZQF5G5DPOT5LGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R37X2X5WLDE7ZQF5G5DPOT5LGC","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":"8b2f83f1dbd1ae7708fbedcfb29914fa6e868df7ac08792548201cc843de1ec1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-02-05T09:20:52Z","title_canon_sha256":"014ddc3265daf509b7da104909e23ee0daf2c86ede9d2eba42edf89f631da7c6"},"schema_version":"1.0","source":{"id":"2502.03499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03499","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03499v1","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03499","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"R37X2X5WLDE7","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"R37X2X5WLDE7ZQF5","created_at":"2026-07-05T10:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"R37X2X5W","created_at":"2026-07-05T10:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:24aa2e79e7b8b1d1d6dc92728df44914c210a35bc6d7c642af9f74c4a025aa92","target":"graph","created_at":"2026-07-05T10:10:11Z","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/2502.03499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable generalizability across diverse tasks, yet genomic foundation models (GFMs) still require separate finetuning for each downstream application, creating significant overhead as model sizes grow. Moreover, existing GFMs are constrained by rigid output formats, limiting their applicability to various genomic tasks. In this work, we revisit the transformer-based auto-regressive models and introduce Omni-DNA, a family of cross-modal multi-task models ranging from 20 million to 1 billion parameters. Our approach consists of two stages: (i) pretrain","authors_text":"Caihua Shan, Dongsheng Li, Guy-Bart Stan, Vallijah Subasri, Yifei Shen, Yiren Zhao, Zehui Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-02-05T09:20:52Z","title":"Omni-DNA: A Unified Genomic Foundation Model for Cross-Modal and Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03499","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":"sha256:6b9a0a864b4c6de99cc4f04014b285a9f5716c282f09fca47215f840627385e9","target":"record","created_at":"2026-07-05T10:10:11Z","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":"8b2f83f1dbd1ae7708fbedcfb29914fa6e868df7ac08792548201cc843de1ec1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-02-05T09:20:52Z","title_canon_sha256":"014ddc3265daf509b7da104909e23ee0daf2c86ede9d2eba42edf89f631da7c6"},"schema_version":"1.0","source":{"id":"2502.03499","kind":"arxiv","version":1}},"canonical_sha256":"8eff7d5fb658c9fcc0bd3746f74fab308bb9b87514e0dd037ddcd0ec004f8e11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eff7d5fb658c9fcc0bd3746f74fab308bb9b87514e0dd037ddcd0ec004f8e11","first_computed_at":"2026-07-05T10:10:11.241575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:11.241575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RH3yUaZ51PYz/Cz2mDEkvXp1seHMF49seFblE0jH6C7EcMyf6/wex2bOUMzeWxE3JcMdgsMaqzOj+v+Pxxm+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:11.241963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b9a0a864b4c6de99cc4f04014b285a9f5716c282f09fca47215f840627385e9","sha256:24aa2e79e7b8b1d1d6dc92728df44914c210a35bc6d7c642af9f74c4a025aa92"],"state_sha256":"da6f76d37e83f23b9a1d7aa3b51dc3645ebddc42743df3fb0cb420302bc9ca45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5dMvI0pgz2Nr3XPQj+miBwckfSeT4ju0S9nUNNkgZXLEJ0emd32rLT4S+6rFeF45VbmxQ5aZzIfP0MHItBoVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T00:13:30.118590Z","bundle_sha256":"6b680f52a33ca5f82e507c96dbbaba0d33739fa705a40715fe739dea5974d3ef"}}