{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GBLK4RNCMQ74EZV3UZGOMUW6K2","short_pith_number":"pith:GBLK4RNC","schema_version":"1.0","canonical_sha256":"3056ae45a2643fc266bba64ce652de56a44b911acbaee1788c76b2632b814c3c","source":{"kind":"arxiv","id":"2602.19591","version":3},"attestation_state":"computed","paper":{"title":"Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanzhe Guo, Yijiashun Qi, Yijiazhen Qi","submitted_at":"2026-02-23T08:35:55Z","abstract_excerpt":"Small and Medium Enterprises (SMEs) constitute 99.9% of U.S. businesses and generate 44% of economic activity, yet systematically identifying high-potential SMEs remains an open challenge. We introduce SME-HGT, a Heterogeneous Graph Transformer framework that predicts which SBIR Phase I awardees will advance to Phase II funding using exclusively public data. We construct a heterogeneous graph with 32,268 company nodes, 124 research topic nodes, and 13 government agency nodes connected by approximately 99,000 edges across three semantic relation types. SME-HGT achieves an AUPRC of 0.621 0.003 o"},"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":"2602.19591","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-23T08:35:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b16440bbc5c82eb3f9e0fdd27db69baef433819c9ab7c90a9521651db954539a","abstract_canon_sha256":"bc9b56859a8ac0e29bf402225506e34e85e0b1adc0c369af2d819cd453b634a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:21.062732Z","signature_b64":"PncFGSKSjNGECGAYRtyq6c7tVAxt3caY8ItT/2dl90Nbu6ljD3jvJ1tHmlfx+LJckUnMm84qDcKSW+TkRL5lBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3056ae45a2643fc266bba64ce652de56a44b911acbaee1788c76b2632b814c3c","last_reissued_at":"2026-06-19T16:11:21.062249Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:21.062249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Detecting High-Potential SMEs with Heterogeneous Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hanzhe Guo, Yijiashun Qi, Yijiazhen Qi","submitted_at":"2026-02-23T08:35:55Z","abstract_excerpt":"Small and Medium Enterprises (SMEs) constitute 99.9% of U.S. businesses and generate 44% of economic activity, yet systematically identifying high-potential SMEs remains an open challenge. We introduce SME-HGT, a Heterogeneous Graph Transformer framework that predicts which SBIR Phase I awardees will advance to Phase II funding using exclusively public data. We construct a heterogeneous graph with 32,268 company nodes, 124 research topic nodes, and 13 government agency nodes connected by approximately 99,000 edges across three semantic relation types. SME-HGT achieves an AUPRC of 0.621 0.003 o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19591","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/2602.19591/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":"2602.19591","created_at":"2026-06-19T16:11:21.062305+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19591v3","created_at":"2026-06-19T16:11:21.062305+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19591","created_at":"2026-06-19T16:11:21.062305+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBLK4RNCMQ74","created_at":"2026-06-19T16:11:21.062305+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBLK4RNCMQ74EZV3","created_at":"2026-06-19T16:11:21.062305+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBLK4RNC","created_at":"2026-06-19T16:11:21.062305+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.23398","citing_title":"When Corrective Hints Hurt: Prompt Design in Reasoner-Guided Repair of LLM Overcaution on Entailed Negations under OWL~2~DL","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2","json":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2.json","graph_json":"https://pith.science/api/pith-number/GBLK4RNCMQ74EZV3UZGOMUW6K2/graph.json","events_json":"https://pith.science/api/pith-number/GBLK4RNCMQ74EZV3UZGOMUW6K2/events.json","paper":"https://pith.science/paper/GBLK4RNC"},"agent_actions":{"view_html":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2","download_json":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2.json","view_paper":"https://pith.science/paper/GBLK4RNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19591&json=true","fetch_graph":"https://pith.science/api/pith-number/GBLK4RNCMQ74EZV3UZGOMUW6K2/graph.json","fetch_events":"https://pith.science/api/pith-number/GBLK4RNCMQ74EZV3UZGOMUW6K2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2/action/storage_attestation","attest_author":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2/action/author_attestation","sign_citation":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2/action/citation_signature","submit_replication":"https://pith.science/pith/GBLK4RNCMQ74EZV3UZGOMUW6K2/action/replication_record"}},"created_at":"2026-06-19T16:11:21.062305+00:00","updated_at":"2026-06-19T16:11:21.062305+00:00"}