{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EYZ3J6QBEPAATKDVFR3GIBAJIE","short_pith_number":"pith:EYZ3J6QB","canonical_record":{"source":{"id":"2605.14442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-05-14T06:37:55Z","cross_cats_sorted":[],"title_canon_sha256":"4659f126ca881430f8bb343cb3fc2bc10e51f67de9364f4c40c9461e089c79d9","abstract_canon_sha256":"c292b84c990268a754c46025ded6cb5ed92633e64254fadcd46ccb8f0f771312"},"schema_version":"1.0"},"canonical_sha256":"2633b4fa0123c009a8752c76640409411d6eda430848c46a09dcc369112fe41d","source":{"kind":"arxiv","id":"2605.14442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14442","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14442v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14442","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"EYZ3J6QBEPAA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EYZ3J6QBEPAATKDV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EYZ3J6QB","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EYZ3J6QBEPAATKDVFR3GIBAJIE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-05-14T06:37:55Z","cross_cats_sorted":[],"title_canon_sha256":"4659f126ca881430f8bb343cb3fc2bc10e51f67de9364f4c40c9461e089c79d9","abstract_canon_sha256":"c292b84c990268a754c46025ded6cb5ed92633e64254fadcd46ccb8f0f771312"},"schema_version":"1.0"},"canonical_sha256":"2633b4fa0123c009a8752c76640409411d6eda430848c46a09dcc369112fe41d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.006340Z","signature_b64":"1DYL1/eSDubDnJc660zXP2i97sLzxbHsMZc4R0h9+yj9iuHGvqpHVD7SJdzay5HY6J2F4pA/jin7U/AODOH+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2633b4fa0123c009a8752c76640409411d6eda430848c46a09dcc369112fe41d","last_reissued_at":"2026-05-17T23:39:07.005535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.005535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14442","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":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JFpbXPfb1+oLlQqG+GMvGgJ1cgRKaoW5EujWK9xQlNDXDjBvtcESuVXNH2ztc6OlIyKOGw5reJAkBLV8Kg50BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:16:56.996369Z"},"content_sha256":"c7b18e4bd31183cd623a99eda4044a3ea8592f6ea9fa57de27e168efde094b92","schema_version":"1.0","event_id":"sha256:c7b18e4bd31183cd623a99eda4044a3ea8592f6ea9fa57de27e168efde094b92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EYZ3J6QBEPAATKDVFR3GIBAJIE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"A 4B-parameter agent fuses frozen genome embeddings into an LLM and uses a counterfactual reward to match larger models on microbial life-boundary prediction.","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Hanbo Huang, Jing Wang, Lei Bai, Shiyu Liang, Weishu Zhao, Xiang Xiao, Xuan Gong","submitted_at":"2026-05-14T06:37:55Z","abstract_excerpt":"Characterizing the physiological life boundaries of microbial strains, including viable temperature, pH, salinity, substrate utilization, and morphology, is central to biotechnology and ecology, yet traditionally requires exhaustive in vitro screening. Existing computational approaches either treat physiological traits as isolated supervised targets or repurpose biological foundation models as static encoders, leaving the genotype-to-physiology gap largely unbridged. We formulate microbial life-boundary prediction as a unified genome-to-physiology task and address it with a genome-conditioned,"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting 4B-parameter agent matches or surpasses substantially larger frontier LLMs, with ablations confirming that genome-token fusion, dynamic tool use, and the counterfactual reward each yield distinct, significant gains.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the frozen LucaOne genome embeddings provide causally relevant information for physiological trait prediction, as measured by the counterfactual ablation against zero-gene input.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A genome-conditioned 4B LLM agent predicts microbial life boundaries and matches larger frontier models via token fusion, tool use, and a counterfactual gene-grounding reward.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A 4B-parameter agent fuses frozen genome embeddings into an LLM and uses a counterfactual reward to match larger models on microbial life-boundary prediction.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a8bec1952ebcdca5e6c4ac057ae2579590816b225eacef2b10fb6e0ef3ef6303"},"source":{"id":"2605.14442","kind":"arxiv","version":1},"verdict":{"id":"41fca67d-d967-49ef-bd01-5d34cd7ba09e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:07:48.123497Z","strongest_claim":"The resulting 4B-parameter agent matches or surpasses substantially larger frontier LLMs, with ablations confirming that genome-token fusion, dynamic tool use, and the counterfactual reward each yield distinct, significant gains.","one_line_summary":"A genome-conditioned 4B LLM agent predicts microbial life boundaries and matches larger frontier models via token fusion, tool use, and a counterfactual gene-grounding reward.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the frozen LucaOne genome embeddings provide causally relevant information for physiological trait prediction, as measured by the counterfactual ablation against zero-gene input.","pith_extraction_headline":"A 4B-parameter agent fuses frozen genome embeddings into an LLM and uses a counterfactual reward to match larger models on microbial life-boundary prediction."},"references":{"count":54,"sample":[{"doi":"","year":2001,"title":"Life in extreme environments.Nature, 409(6823): 1092–1101, 2001","work_id":"73d54431-a147-4a29-b0e6-b39a536cb032","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"The limits for life under multiple extremes.Trends in microbiology, 21(4):204–212, 2013","work_id":"19ba8f10-8432-482c-ac0e-625a34ab0748","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Living at the extremes: extremophiles and the limits of life in a planetary context.Frontiers in microbiology, 10:447668, 2019","work_id":"ec5bf60d-a13c-430d-8fac-eb68bb572002","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2010,"title":"uncultivable","work_id":"6dc17e27-dfc2-43fe-b296-182cf62c23c5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Culturing the human microbiota and culturomics.Nature Reviews Microbiology, 16(9): 540–550, 2018","work_id":"c8d2632d-1994-4683-aaad-28cbc5349707","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":54,"snapshot_sha256":"e81b6169daf2b104c6a144a984ffd1eb742bc3f4220e006ed5ab6e8702e5f454","internal_anchors":7},"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":"41fca67d-d967-49ef-bd01-5d34cd7ba09e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uL72IY5RC43HfDtWe1aTBMfeI8WCZG5DWr96nRES1NLZbveWHXCcDqQF3QDT0Mv2XBCJn3IEc8Msw+CaNqQqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:16:56.996940Z"},"content_sha256":"72564523edafda01f692407a452c00f07e0353e15c88dc31184ed5d2b055f066","schema_version":"1.0","event_id":"sha256:72564523edafda01f692407a452c00f07e0353e15c88dc31184ed5d2b055f066"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE/bundle.json","state_url":"https://pith.science/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE/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":"2026-05-31T01:16:56Z","links":{"resolver":"https://pith.science/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE","bundle":"https://pith.science/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE/bundle.json","state":"https://pith.science/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EYZ3J6QBEPAATKDVFR3GIBAJIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EYZ3J6QBEPAATKDVFR3GIBAJIE","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":"c292b84c990268a754c46025ded6cb5ed92633e64254fadcd46ccb8f0f771312","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-05-14T06:37:55Z","title_canon_sha256":"4659f126ca881430f8bb343cb3fc2bc10e51f67de9364f4c40c9461e089c79d9"},"schema_version":"1.0","source":{"id":"2605.14442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14442","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14442v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14442","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"EYZ3J6QBEPAA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"EYZ3J6QBEPAATKDV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"EYZ3J6QB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:72564523edafda01f692407a452c00f07e0353e15c88dc31184ed5d2b055f066","target":"graph","created_at":"2026-05-17T23:39:07Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The resulting 4B-parameter agent matches or surpasses substantially larger frontier LLMs, with ablations confirming that genome-token fusion, dynamic tool use, and the counterfactual reward each yield distinct, significant gains."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the frozen LucaOne genome embeddings provide causally relevant information for physiological trait prediction, as measured by the counterfactual ablation against zero-gene input."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A genome-conditioned 4B LLM agent predicts microbial life boundaries and matches larger frontier models via token fusion, tool use, and a counterfactual gene-grounding reward."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A 4B-parameter agent fuses frozen genome embeddings into an LLM and uses a counterfactual reward to match larger models on microbial life-boundary prediction."}],"snapshot_sha256":"a8bec1952ebcdca5e6c4ac057ae2579590816b225eacef2b10fb6e0ef3ef6303"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Characterizing the physiological life boundaries of microbial strains, including viable temperature, pH, salinity, substrate utilization, and morphology, is central to biotechnology and ecology, yet traditionally requires exhaustive in vitro screening. Existing computational approaches either treat physiological traits as isolated supervised targets or repurpose biological foundation models as static encoders, leaving the genotype-to-physiology gap largely unbridged. We formulate microbial life-boundary prediction as a unified genome-to-physiology task and address it with a genome-conditioned,","authors_text":"Hanbo Huang, Jing Wang, Lei Bai, Shiyu Liang, Weishu Zhao, Xiang Xiao, Xuan Gong","cross_cats":[],"headline":"A 4B-parameter agent fuses frozen genome embeddings into an LLM and uses a counterfactual reward to match larger models on microbial life-boundary prediction.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-05-14T06:37:55Z","title":"GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction"},"references":{"count":54,"internal_anchors":7,"resolved_work":54,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Life in extreme environments.Nature, 409(6823): 1092–1101, 2001","work_id":"73d54431-a147-4a29-b0e6-b39a536cb032","year":2001},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"The limits for life under multiple extremes.Trends in microbiology, 21(4):204–212, 2013","work_id":"19ba8f10-8432-482c-ac0e-625a34ab0748","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Living at the extremes: extremophiles and the limits of life in a planetary context.Frontiers in microbiology, 10:447668, 2019","work_id":"ec5bf60d-a13c-430d-8fac-eb68bb572002","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"uncultivable","work_id":"6dc17e27-dfc2-43fe-b296-182cf62c23c5","year":2010},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Culturing the human microbiota and culturomics.Nature Reviews Microbiology, 16(9): 540–550, 2018","work_id":"c8d2632d-1994-4683-aaad-28cbc5349707","year":2018}],"snapshot_sha256":"e81b6169daf2b104c6a144a984ffd1eb742bc3f4220e006ed5ab6e8702e5f454"},"source":{"id":"2605.14442","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:07:48.123497Z","id":"41fca67d-d967-49ef-bd01-5d34cd7ba09e","model_set":{"reader":"grok-4.3"},"one_line_summary":"A genome-conditioned 4B LLM agent predicts microbial life boundaries and matches larger frontier models via token fusion, tool use, and a counterfactual gene-grounding reward.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A 4B-parameter agent fuses frozen genome embeddings into an LLM and uses a counterfactual reward to match larger models on microbial life-boundary prediction.","strongest_claim":"The resulting 4B-parameter agent matches or surpasses substantially larger frontier LLMs, with ablations confirming that genome-token fusion, dynamic tool use, and the counterfactual reward each yield distinct, significant gains.","weakest_assumption":"That the frozen LucaOne genome embeddings provide causally relevant information for physiological trait prediction, as measured by the counterfactual ablation against zero-gene input."}},"verdict_id":"41fca67d-d967-49ef-bd01-5d34cd7ba09e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c7b18e4bd31183cd623a99eda4044a3ea8592f6ea9fa57de27e168efde094b92","target":"record","created_at":"2026-05-17T23:39:07Z","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":"c292b84c990268a754c46025ded6cb5ed92633e64254fadcd46ccb8f0f771312","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2026-05-14T06:37:55Z","title_canon_sha256":"4659f126ca881430f8bb343cb3fc2bc10e51f67de9364f4c40c9461e089c79d9"},"schema_version":"1.0","source":{"id":"2605.14442","kind":"arxiv","version":1}},"canonical_sha256":"2633b4fa0123c009a8752c76640409411d6eda430848c46a09dcc369112fe41d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2633b4fa0123c009a8752c76640409411d6eda430848c46a09dcc369112fe41d","first_computed_at":"2026-05-17T23:39:07.005535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.005535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1DYL1/eSDubDnJc660zXP2i97sLzxbHsMZc4R0h9+yj9iuHGvqpHVD7SJdzay5HY6J2F4pA/jin7U/AODOH+Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.006340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7b18e4bd31183cd623a99eda4044a3ea8592f6ea9fa57de27e168efde094b92","sha256:72564523edafda01f692407a452c00f07e0353e15c88dc31184ed5d2b055f066"],"state_sha256":"6d10e3a5e43056ccff86696bec79412c0bf0e5db09ddabc8c8cc91a644030f3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kAFR9ubd9ZGbq0QBcrcQt+mCdVopPDrALcW82wVpyKvv/vUQsgI4tkFf28xit3H2GpAbDbkvOFlev8dOTjaNCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:16:57.000660Z","bundle_sha256":"b12ca65f8a86918feaa5e4ddee5454964d260a04cac011e21c30044b22f1506e"}}