{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GJFFNPF37MO4VCCNBSDP333SDY","short_pith_number":"pith:GJFFNPF3","schema_version":"1.0","canonical_sha256":"324a56bcbbfb1dca884d0c86fdef721e2f23da053ba69042e8e20ed1a3415d28","source":{"kind":"arxiv","id":"2505.14752","version":3},"attestation_state":"computed","paper":{"title":"LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junlin He, Lijun Sun, Menglin Kong, Tong Nie, Wei Ma, Yihong Tang","submitted_at":"2025-05-20T13:35:38Z","abstract_excerpt":"Macro-aligned micro-records are crucial for credible simulations in social science and urban studies. For example, epidemic models are only reliable when individual-level mobility and contacts mirror real behavior, while aggregates match real-world statistics like case counts or travel flows. However, collecting such fine-grained data at scale is impractical, leaving researchers with only macro-level data. LLMSynthor addresses this by turning a pretrained LLM into a macro-aware simulator that generates realistic micro-records consistent with target macro-statistics. It iteratively builds synth"},"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":"2505.14752","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-20T13:35:38Z","cross_cats_sorted":[],"title_canon_sha256":"f2673848a38931a534cf34a999c0f600c3462a152915e51be9875996138ca4f6","abstract_canon_sha256":"2e32efb0e77549cd4aebe10eac780be88ed6f695aecb868f97a9c057425cc938"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:14.715199Z","signature_b64":"XzGN9mJC6aIzRTox1xQ1eL7qF+Ap8fOjqvHpk8xcjvP4t/a1FgPxg+TYzgG46jxHCrgv6MBBdVP7QED+qKnBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"324a56bcbbfb1dca884d0c86fdef721e2f23da053ba69042e8e20ed1a3415d28","last_reissued_at":"2026-06-02T01:04:14.714827Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:14.714827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMSynthor: Macro-Aligned Micro-Records Synthesis with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junlin He, Lijun Sun, Menglin Kong, Tong Nie, Wei Ma, Yihong Tang","submitted_at":"2025-05-20T13:35:38Z","abstract_excerpt":"Macro-aligned micro-records are crucial for credible simulations in social science and urban studies. For example, epidemic models are only reliable when individual-level mobility and contacts mirror real behavior, while aggregates match real-world statistics like case counts or travel flows. However, collecting such fine-grained data at scale is impractical, leaving researchers with only macro-level data. LLMSynthor addresses this by turning a pretrained LLM into a macro-aware simulator that generates realistic micro-records consistent with target macro-statistics. It iteratively builds synth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14752","kind":"arxiv","version":3},"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/2505.14752/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":"2505.14752","created_at":"2026-06-02T01:04:14.714883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14752v3","created_at":"2026-06-02T01:04:14.714883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14752","created_at":"2026-06-02T01:04:14.714883+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJFFNPF37MO4","created_at":"2026-06-02T01:04:14.714883+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJFFNPF37MO4VCCN","created_at":"2026-06-02T01:04:14.714883+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJFFNPF3","created_at":"2026-06-02T01:04:14.714883+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/GJFFNPF37MO4VCCNBSDP333SDY","json":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY.json","graph_json":"https://pith.science/api/pith-number/GJFFNPF37MO4VCCNBSDP333SDY/graph.json","events_json":"https://pith.science/api/pith-number/GJFFNPF37MO4VCCNBSDP333SDY/events.json","paper":"https://pith.science/paper/GJFFNPF3"},"agent_actions":{"view_html":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY","download_json":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY.json","view_paper":"https://pith.science/paper/GJFFNPF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14752&json=true","fetch_graph":"https://pith.science/api/pith-number/GJFFNPF37MO4VCCNBSDP333SDY/graph.json","fetch_events":"https://pith.science/api/pith-number/GJFFNPF37MO4VCCNBSDP333SDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY/action/storage_attestation","attest_author":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY/action/author_attestation","sign_citation":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY/action/citation_signature","submit_replication":"https://pith.science/pith/GJFFNPF37MO4VCCNBSDP333SDY/action/replication_record"}},"created_at":"2026-06-02T01:04:14.714883+00:00","updated_at":"2026-06-02T01:04:14.714883+00:00"}