{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TUCX5Z3THP33IN6QNBVBDGXDZY","short_pith_number":"pith:TUCX5Z3T","schema_version":"1.0","canonical_sha256":"9d057ee7733bf7b437d0686a119ae3ce1c30942ae62b52aa1898b3e9ba0989a1","source":{"kind":"arxiv","id":"2606.02867","version":1},"attestation_state":"computed","paper":{"title":"The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.PE"],"primary_cat":"cs.MA","authors_text":"Andres Colubri, Ava Keeling, Francesco Di Lauro, Jasmina Panovska-Griffiths, Lorenzo Stigliano, Petra Ferenz, Tobias O'Keefe","submitted_at":"2026-06-01T20:31:06Z","abstract_excerpt":"Human behaviour during epidemics affects infectious disease dynamics, but quantifying this remains deeply challenging. Here we introduce the Epi-LLM framework: a novel integration of agent-based modelling, real-life epigames, and large language models (LLMs) in which a synthetic society of agents reasons and adapts dynamically over an outbreak contact network. Comparing synthetic agent behaviour against a no-intervention SEIR baseline and human participant data from the AUIB epigame study, we find that LLM agents across four different architectures reduced peak active infections, with quaranti"},"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":"2606.02867","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-01T20:31:06Z","cross_cats_sorted":["cs.AI","q-bio.PE"],"title_canon_sha256":"5ce657b1a368763c84429e842bccaf43b147c3489569844ce6da345680146e5f","abstract_canon_sha256":"3295ff278ba46d8967510f9f9435d4142319c6809c3a84627b36afb441962dd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:25.019861Z","signature_b64":"NqwjAD+WRsNqteD6LvtJTPcLeVe9f4Jy/0F2HRTGBuGBTQYStqDLrhiS/tlRGNLBbJVqhSItKjdI/saWsNzBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d057ee7733bf7b437d0686a119ae3ce1c30942ae62b52aa1898b3e9ba0989a1","last_reissued_at":"2026-06-03T01:05:25.019416Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:25.019416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.PE"],"primary_cat":"cs.MA","authors_text":"Andres Colubri, Ava Keeling, Francesco Di Lauro, Jasmina Panovska-Griffiths, Lorenzo Stigliano, Petra Ferenz, Tobias O'Keefe","submitted_at":"2026-06-01T20:31:06Z","abstract_excerpt":"Human behaviour during epidemics affects infectious disease dynamics, but quantifying this remains deeply challenging. Here we introduce the Epi-LLM framework: a novel integration of agent-based modelling, real-life epigames, and large language models (LLMs) in which a synthetic society of agents reasons and adapts dynamically over an outbreak contact network. Comparing synthetic agent behaviour against a no-intervention SEIR baseline and human participant data from the AUIB epigame study, we find that LLM agents across four different architectures reduced peak active infections, with quaranti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02867","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/2606.02867/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":"2606.02867","created_at":"2026-06-03T01:05:25.019483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02867v1","created_at":"2026-06-03T01:05:25.019483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02867","created_at":"2026-06-03T01:05:25.019483+00:00"},{"alias_kind":"pith_short_12","alias_value":"TUCX5Z3THP33","created_at":"2026-06-03T01:05:25.019483+00:00"},{"alias_kind":"pith_short_16","alias_value":"TUCX5Z3THP33IN6Q","created_at":"2026-06-03T01:05:25.019483+00:00"},{"alias_kind":"pith_short_8","alias_value":"TUCX5Z3T","created_at":"2026-06-03T01:05:25.019483+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/TUCX5Z3THP33IN6QNBVBDGXDZY","json":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY.json","graph_json":"https://pith.science/api/pith-number/TUCX5Z3THP33IN6QNBVBDGXDZY/graph.json","events_json":"https://pith.science/api/pith-number/TUCX5Z3THP33IN6QNBVBDGXDZY/events.json","paper":"https://pith.science/paper/TUCX5Z3T"},"agent_actions":{"view_html":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY","download_json":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY.json","view_paper":"https://pith.science/paper/TUCX5Z3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02867&json=true","fetch_graph":"https://pith.science/api/pith-number/TUCX5Z3THP33IN6QNBVBDGXDZY/graph.json","fetch_events":"https://pith.science/api/pith-number/TUCX5Z3THP33IN6QNBVBDGXDZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY/action/storage_attestation","attest_author":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY/action/author_attestation","sign_citation":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY/action/citation_signature","submit_replication":"https://pith.science/pith/TUCX5Z3THP33IN6QNBVBDGXDZY/action/replication_record"}},"created_at":"2026-06-03T01:05:25.019483+00:00","updated_at":"2026-06-03T01:05:25.019483+00:00"}