{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PURKXMCYXDHM2J3ANXUD2R6SFP","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":"f54b3354ee05ed6f3ff0bf8694f7e470cc397578948bb366643585e916de5b5a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-03T18:44:43Z","title_canon_sha256":"c98abbec4ae7ca782495aa8bee996d0c33246a6e3df4495622186a710878ec2b"},"schema_version":"1.0","source":{"id":"2501.02045","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.02045","created_at":"2026-07-05T09:57:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.02045v1","created_at":"2026-07-05T09:57:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.02045","created_at":"2026-07-05T09:57:00Z"},{"alias_kind":"pith_short_12","alias_value":"PURKXMCYXDHM","created_at":"2026-07-05T09:57:00Z"},{"alias_kind":"pith_short_16","alias_value":"PURKXMCYXDHM2J3A","created_at":"2026-07-05T09:57:00Z"},{"alias_kind":"pith_short_8","alias_value":"PURKXMCY","created_at":"2026-07-05T09:57:00Z"}],"graph_snapshots":[{"event_id":"sha256:b7d8674d9f196b7148fe17f28d4331a87b3396c11ef5b65aaddc7c6530074dab","target":"graph","created_at":"2026-07-05T09:57:00Z","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/2501.02045/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We pretrain METAGENE-1, a 7-billion-parameter autoregressive transformer model, which we refer to as a metagenomic foundation model, on a novel corpus of diverse metagenomic DNA and RNA sequences comprising over 1.5 trillion base pairs. This dataset is sourced from a large collection of human wastewater samples, processed and sequenced using deep metagenomic (next-generation) sequencing methods. Unlike genomic models that focus on individual genomes or curated sets of specific species, the aim of METAGENE-1 is to capture the full distribution of genomic information present within this wastewat","authors_text":"Jason Wiemels, Jeff Kaufman, Johannes Hagemann, Ollie Liu, Sami Jaghouar, Shangshang Wang, Willie Neiswanger","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-03T18:44:43Z","title":"METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.02045","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":"sha256:8b348a7ad5ad6e7bbc41029776b8360c281209365a5aa1566e089db7c6135714","target":"record","created_at":"2026-07-05T09:57:00Z","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":"f54b3354ee05ed6f3ff0bf8694f7e470cc397578948bb366643585e916de5b5a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.GN","submitted_at":"2025-01-03T18:44:43Z","title_canon_sha256":"c98abbec4ae7ca782495aa8bee996d0c33246a6e3df4495622186a710878ec2b"},"schema_version":"1.0","source":{"id":"2501.02045","kind":"arxiv","version":1}},"canonical_sha256":"7d22abb058b8cecd27606de83d47d22bccd734f4b8cc120dc08e8c4e73e74db8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d22abb058b8cecd27606de83d47d22bccd734f4b8cc120dc08e8c4e73e74db8","first_computed_at":"2026-07-05T09:57:00.896408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:57:00.896408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g7CN0NHG5BaJ99X+0cD0C7ClONMvMsSqXxLLwzwppsWLlJh54GnY4bjM/vPJ1bAsFTYOrJ+/QaG5iyq5HiFBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:57:00.896835Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.02045","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b348a7ad5ad6e7bbc41029776b8360c281209365a5aa1566e089db7c6135714","sha256:b7d8674d9f196b7148fe17f28d4331a87b3396c11ef5b65aaddc7c6530074dab"],"state_sha256":"4e30484f6567ebccbc01fde96bcf9bba332dec288dd14a9f975271e209f37687"}