{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FXQBK5ARL3LILJEXSV67FAV4BM","short_pith_number":"pith:FXQBK5AR","canonical_record":{"source":{"id":"2501.07737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-13T23:00:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"179460d907a8a68232c64d9b4d9370ee9d2ae7e1861fc1ab1d9420be945ba4b2","abstract_canon_sha256":"3d8866d0d2ea4f5ef71c9ecd4a396446b755afade63fa12c531fe87586b8039d"},"schema_version":"1.0"},"canonical_sha256":"2de01574115ed685a497957df282bc0b122dcd5a37834dd5604a787bf29638bb","source":{"kind":"arxiv","id":"2501.07737","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07737","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07737v1","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07737","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"FXQBK5ARL3LI","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"FXQBK5ARL3LILJEX","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"FXQBK5AR","created_at":"2026-07-05T10:00:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FXQBK5ARL3LILJEXSV67FAV4BM","target":"record","payload":{"canonical_record":{"source":{"id":"2501.07737","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-13T23:00:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"179460d907a8a68232c64d9b4d9370ee9d2ae7e1861fc1ab1d9420be945ba4b2","abstract_canon_sha256":"3d8866d0d2ea4f5ef71c9ecd4a396446b755afade63fa12c531fe87586b8039d"},"schema_version":"1.0"},"canonical_sha256":"2de01574115ed685a497957df282bc0b122dcd5a37834dd5604a787bf29638bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:49.291244Z","signature_b64":"m0KukvsnA9Sn8y1GYTMPj+kJy9Ii3T5yJ2OOxwmlfKXYu9Q0OF8DwKosVwKd13Ra2Bpql/SHjfdpGSFtE+a7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2de01574115ed685a497957df282bc0b122dcd5a37834dd5604a787bf29638bb","last_reissued_at":"2026-07-05T10:00:49.290740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:49.290740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.07737","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":"2026-07-05T10:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKduk/zplIYdHPSWjGn5I+frUlNn41YUo5o/NPeIDbQvW5IBHfFEhY24ln8J6ECrvwiishIiytqv8s4D4FytDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:31:54.096042Z"},"content_sha256":"81ced7f7ef700d8809d8883bcc8771524d3838bd95ff25d96bfd4619b906bdcb","schema_version":"1.0","event_id":"sha256:81ced7f7ef700d8809d8883bcc8771524d3838bd95ff25d96bfd4619b906bdcb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FXQBK5ARL3LILJEXSV67FAV4BM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-megabase scale genome interpretation with genetic language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.GN","authors_text":"Andreas Georgiou, Arash Mehrjou, Bernhard Sch\\\"olkopf, Cornelia van Duijn, Debora Marks, Frederik Tr\\\"auble, Kim Branson, Lachlan Stuart, Mathieu Chevalley, Pascal Notin, Patrick Schwab, Ron Schwessinger","submitted_at":"2025-01-13T23:00:40Z","abstract_excerpt":"Understanding how molecular changes caused by genetic variation drive disease risk is crucial for deciphering disease mechanisms. However, interpreting genome sequences is challenging because of the vast size of the human genome, and because its consequences manifest across a wide range of cells, tissues and scales -- spanning from molecular to whole organism level. Here, we present Phenformer, a multi-scale genetic language model that learns to generate mechanistic hypotheses as to how differences in genome sequence lead to disease-relevant changes in expression across cell types and tissues "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07737","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/2501.07737/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":"2026-07-05T10:00:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9OOwwqJXOZqCJwxXsgYv9KW6FelcZt7X5m0Aspxb1bnZQuVgwpgwcIzdl+tGrmLdH9Liv73CT6ra4xSBQiCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:31:54.096433Z"},"content_sha256":"7c988f5650c0b79c6cb7a7acc01d4a5fde5fc64cac203396798a78e6e87d2932","schema_version":"1.0","event_id":"sha256:7c988f5650c0b79c6cb7a7acc01d4a5fde5fc64cac203396798a78e6e87d2932"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FXQBK5ARL3LILJEXSV67FAV4BM/bundle.json","state_url":"https://pith.science/pith/FXQBK5ARL3LILJEXSV67FAV4BM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FXQBK5ARL3LILJEXSV67FAV4BM/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":"2026-07-06T14:31:54Z","links":{"resolver":"https://pith.science/pith/FXQBK5ARL3LILJEXSV67FAV4BM","bundle":"https://pith.science/pith/FXQBK5ARL3LILJEXSV67FAV4BM/bundle.json","state":"https://pith.science/pith/FXQBK5ARL3LILJEXSV67FAV4BM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FXQBK5ARL3LILJEXSV67FAV4BM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FXQBK5ARL3LILJEXSV67FAV4BM","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":"3d8866d0d2ea4f5ef71c9ecd4a396446b755afade63fa12c531fe87586b8039d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-13T23:00:40Z","title_canon_sha256":"179460d907a8a68232c64d9b4d9370ee9d2ae7e1861fc1ab1d9420be945ba4b2"},"schema_version":"1.0","source":{"id":"2501.07737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07737","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07737v1","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07737","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_12","alias_value":"FXQBK5ARL3LI","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_16","alias_value":"FXQBK5ARL3LILJEX","created_at":"2026-07-05T10:00:49Z"},{"alias_kind":"pith_short_8","alias_value":"FXQBK5AR","created_at":"2026-07-05T10:00:49Z"}],"graph_snapshots":[{"event_id":"sha256:7c988f5650c0b79c6cb7a7acc01d4a5fde5fc64cac203396798a78e6e87d2932","target":"graph","created_at":"2026-07-05T10:00:49Z","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/2501.07737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding how molecular changes caused by genetic variation drive disease risk is crucial for deciphering disease mechanisms. However, interpreting genome sequences is challenging because of the vast size of the human genome, and because its consequences manifest across a wide range of cells, tissues and scales -- spanning from molecular to whole organism level. Here, we present Phenformer, a multi-scale genetic language model that learns to generate mechanistic hypotheses as to how differences in genome sequence lead to disease-relevant changes in expression across cell types and tissues ","authors_text":"Andreas Georgiou, Arash Mehrjou, Bernhard Sch\\\"olkopf, Cornelia van Duijn, Debora Marks, Frederik Tr\\\"auble, Kim Branson, Lachlan Stuart, Mathieu Chevalley, Pascal Notin, Patrick Schwab, Ron Schwessinger","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-13T23:00:40Z","title":"Multi-megabase scale genome interpretation with genetic language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07737","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":"sha256:81ced7f7ef700d8809d8883bcc8771524d3838bd95ff25d96bfd4619b906bdcb","target":"record","created_at":"2026-07-05T10:00:49Z","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":"3d8866d0d2ea4f5ef71c9ecd4a396446b755afade63fa12c531fe87586b8039d","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-13T23:00:40Z","title_canon_sha256":"179460d907a8a68232c64d9b4d9370ee9d2ae7e1861fc1ab1d9420be945ba4b2"},"schema_version":"1.0","source":{"id":"2501.07737","kind":"arxiv","version":1}},"canonical_sha256":"2de01574115ed685a497957df282bc0b122dcd5a37834dd5604a787bf29638bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2de01574115ed685a497957df282bc0b122dcd5a37834dd5604a787bf29638bb","first_computed_at":"2026-07-05T10:00:49.290740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:49.290740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m0KukvsnA9Sn8y1GYTMPj+kJy9Ii3T5yJ2OOxwmlfKXYu9Q0OF8DwKosVwKd13Ra2Bpql/SHjfdpGSFtE+a7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:49.291244Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81ced7f7ef700d8809d8883bcc8771524d3838bd95ff25d96bfd4619b906bdcb","sha256:7c988f5650c0b79c6cb7a7acc01d4a5fde5fc64cac203396798a78e6e87d2932"],"state_sha256":"e72acc87ff8ebcbdd09efbae556e6a80d3fc41dbf727a4d429dd4613831eec40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u107oF4ex4AQ+BaUMFbvpvwhtGsZPbsSjaH8mop8ygHqCsMtTYybfFqel8JzkBSqr/z9Opq5vpXxCcC0nU1rBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:31:54.098350Z","bundle_sha256":"1dca940faa2670de846a6aa07b8fa71f22b22ba588bc900947cbcb0a6146a050"}}