{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTY5XKHNX6TAVEDK3UXTPNBFOK","short_pith_number":"pith:YTY5XKHN","schema_version":"1.0","canonical_sha256":"c4f1dba8edbfa60a906add2f37b42572ba63096e60b9b8d82bc3e3d87467baf2","source":{"kind":"arxiv","id":"2510.16152","version":2},"attestation_state":"computed","paper":{"title":"Mapping Scientific Literature with Large Language Models and Topic Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DL","authors_text":"Lev Khazanovich, Mason Smetana","submitted_at":"2025-10-17T18:57:11Z","abstract_excerpt":"Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science. This study introduces a large language model (LLM)-driven framework for mapping scientific literature from a topic modeling perspective. The approach is demonstrated on a 20-year corpus of more than 1,500 engineering-related articles published in the Proceedings of the National Academy of Sciences (PNAS). A two-stage classification pipeline first assigns a primary thematic category "},"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":"2510.16152","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2025-10-17T18:57:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"c3956a5c0b2e29687bc778395a58b25848cb832ebbd9c32f13a6980cb1c389a0","abstract_canon_sha256":"35ef68e5bb0957da0e7245596d28e5375421b0fa236bbd7723c26cf5cadd2c8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:20.397794Z","signature_b64":"BV8pRCJpPX/PXi6CB1IyGOAcumX9TGSOE/c3IoWHj643s/EBgYsmcnGBdnaCLP/ThqIm0I83a79/7EOgUsckAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f1dba8edbfa60a906add2f37b42572ba63096e60b9b8d82bc3e3d87467baf2","last_reissued_at":"2026-06-11T01:09:20.396762Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:20.396762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mapping Scientific Literature with Large Language Models and Topic Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.DL","authors_text":"Lev Khazanovich, Mason Smetana","submitted_at":"2025-10-17T18:57:11Z","abstract_excerpt":"Scientific literature is increasingly fragmented by disciplinary boundaries, specialized terminology, and potentially sparse keyword systems, making it difficult to capture the evolving structure of modern science. This study introduces a large language model (LLM)-driven framework for mapping scientific literature from a topic modeling perspective. The approach is demonstrated on a 20-year corpus of more than 1,500 engineering-related articles published in the Proceedings of the National Academy of Sciences (PNAS). A two-stage classification pipeline first assigns a primary thematic category "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.16152","kind":"arxiv","version":2},"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/2510.16152/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":"2510.16152","created_at":"2026-06-11T01:09:20.396904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.16152v2","created_at":"2026-06-11T01:09:20.396904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.16152","created_at":"2026-06-11T01:09:20.396904+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTY5XKHNX6TA","created_at":"2026-06-11T01:09:20.396904+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTY5XKHNX6TAVEDK","created_at":"2026-06-11T01:09:20.396904+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTY5XKHN","created_at":"2026-06-11T01:09:20.396904+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/YTY5XKHNX6TAVEDK3UXTPNBFOK","json":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK.json","graph_json":"https://pith.science/api/pith-number/YTY5XKHNX6TAVEDK3UXTPNBFOK/graph.json","events_json":"https://pith.science/api/pith-number/YTY5XKHNX6TAVEDK3UXTPNBFOK/events.json","paper":"https://pith.science/paper/YTY5XKHN"},"agent_actions":{"view_html":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK","download_json":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK.json","view_paper":"https://pith.science/paper/YTY5XKHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.16152&json=true","fetch_graph":"https://pith.science/api/pith-number/YTY5XKHNX6TAVEDK3UXTPNBFOK/graph.json","fetch_events":"https://pith.science/api/pith-number/YTY5XKHNX6TAVEDK3UXTPNBFOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK/action/storage_attestation","attest_author":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK/action/author_attestation","sign_citation":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK/action/citation_signature","submit_replication":"https://pith.science/pith/YTY5XKHNX6TAVEDK3UXTPNBFOK/action/replication_record"}},"created_at":"2026-06-11T01:09:20.396904+00:00","updated_at":"2026-06-11T01:09:20.396904+00:00"}