{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BEDJJ5VN66WDLHH3HGHWR3TL66","short_pith_number":"pith:BEDJJ5VN","schema_version":"1.0","canonical_sha256":"090694f6adf7ac359cfb398f68ee6bf7a1112dbd1b4cb6e7726c5066ef83a7b5","source":{"kind":"arxiv","id":"2605.30179","version":1},"attestation_state":"computed","paper":{"title":"iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haizhou Shi, Hao Wang, Hengguan Huang, Lingfa Meng, Samir Bhatt, Tongyuan Hu, Yang Song, Yixuan Zhang","submitted_at":"2026-05-28T16:26:06Z","abstract_excerpt":"Parameter-efficient adaptation has made LLMs practical for domain prediction, but standard LoRA still relies on a static low-rank update and does not expose the latent interactions that often drive scientific labels. We introduce iLoRA. To our knowledge, it is the first Bayesian graph-conditioned LoRA framework. It infers a latent interaction graph from the input and uses it to generate input-conditioned LoRA updates. As a result, iLoRA learns prediction and latent interaction structure jointly, rather than training a predictor and applying interaction analysis only post hoc. We instantiate th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.30179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:26:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f4c51db7ae64e23c5b656c65305f0789b0c977f46cb13470c931d2b8858062b2","abstract_canon_sha256":"472fdda84ed48cacb318d2dbf111377196196b725ddf85db0f52d478ff5e007c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:12.019658Z","signature_b64":"2Rl9TXulzt+C0EYY4UUqVUL51aqIJYEuoDFFsyVrVNJPpZ4OI6meCLxDG3YOvmZ205fXTyRe7Mc6WreVpqTIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"090694f6adf7ac359cfb398f68ee6bf7a1112dbd1b4cb6e7726c5066ef83a7b5","last_reissued_at":"2026-05-29T02:06:12.019215Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:12.019215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haizhou Shi, Hao Wang, Hengguan Huang, Lingfa Meng, Samir Bhatt, Tongyuan Hu, Yang Song, Yixuan Zhang","submitted_at":"2026-05-28T16:26:06Z","abstract_excerpt":"Parameter-efficient adaptation has made LLMs practical for domain prediction, but standard LoRA still relies on a static low-rank update and does not expose the latent interactions that often drive scientific labels. We introduce iLoRA. To our knowledge, it is the first Bayesian graph-conditioned LoRA framework. It infers a latent interaction graph from the input and uses it to generate input-conditioned LoRA updates. As a result, iLoRA learns prediction and latent interaction structure jointly, rather than training a predictor and applying interaction analysis only post hoc. We instantiate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30179","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/2605.30179/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.30179","created_at":"2026-05-29T02:06:12.019273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30179v1","created_at":"2026-05-29T02:06:12.019273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30179","created_at":"2026-05-29T02:06:12.019273+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEDJJ5VN66WD","created_at":"2026-05-29T02:06:12.019273+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEDJJ5VN66WDLHH3","created_at":"2026-05-29T02:06:12.019273+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEDJJ5VN","created_at":"2026-05-29T02:06:12.019273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66","json":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66.json","graph_json":"https://pith.science/api/pith-number/BEDJJ5VN66WDLHH3HGHWR3TL66/graph.json","events_json":"https://pith.science/api/pith-number/BEDJJ5VN66WDLHH3HGHWR3TL66/events.json","paper":"https://pith.science/paper/BEDJJ5VN"},"agent_actions":{"view_html":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66","download_json":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66.json","view_paper":"https://pith.science/paper/BEDJJ5VN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30179&json=true","fetch_graph":"https://pith.science/api/pith-number/BEDJJ5VN66WDLHH3HGHWR3TL66/graph.json","fetch_events":"https://pith.science/api/pith-number/BEDJJ5VN66WDLHH3HGHWR3TL66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66/action/storage_attestation","attest_author":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66/action/author_attestation","sign_citation":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66/action/citation_signature","submit_replication":"https://pith.science/pith/BEDJJ5VN66WDLHH3HGHWR3TL66/action/replication_record"}},"created_at":"2026-05-29T02:06:12.019273+00:00","updated_at":"2026-05-29T02:06:12.019273+00:00"}