{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XLQWON36R2XIAUIGENWPWNHKZ2","short_pith_number":"pith:XLQWON36","schema_version":"1.0","canonical_sha256":"bae167377e8eae805106236cfb34eace8c49857e633110527342e48295943d59","source":{"kind":"arxiv","id":"2606.29809","version":1},"attestation_state":"computed","paper":{"title":"How Far Can You Get Without a GPU? A Systematic Benchmark of Lightweight Hallucination Detection Across Question Answering, Dialogue, and Summarisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kriti Faujdar, Smit Kadvani","submitted_at":"2026-06-29T05:43:03Z","abstract_excerpt":"Hallucination detection has become a pressing requirement for trustworthy AI deployment at scale. The most accurate detection methods depend on GPU-intensive inference, proprietary API calls, or white-box access to the generating model. This puts them out of reach for resource-constrained researchers and practitioners. In this paper, we explore a practical alternative: how well can hallucination detection perform using only lightweight, CPU-feasible methods built on publicly available models? We systematically benchmark five such methods: ROUGE-L, semantic similarity, BERTScore, a Natural Lang"},"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":"2606.29809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T05:43:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"234347a3515e6e534fba4c17ea0f016db29d800bf95b4741636acc15dd9e6dfb","abstract_canon_sha256":"743d4b904cf682d0fb70f9dcaa9a69d163fa066c5bb72ca890fb0e04c423c22d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:36.173286Z","signature_b64":"yC+oAXAZW51rwB7sRxk5Sr8q2kOJwU7AvxS96py/S3KiAkj50VbfphnZ8JR81Hbq1MZiSDQj/IrMa+1aZm5pCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bae167377e8eae805106236cfb34eace8c49857e633110527342e48295943d59","last_reissued_at":"2026-06-30T02:17:36.172695Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:36.172695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Far Can You Get Without a GPU? A Systematic Benchmark of Lightweight Hallucination Detection Across Question Answering, Dialogue, and Summarisation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kriti Faujdar, Smit Kadvani","submitted_at":"2026-06-29T05:43:03Z","abstract_excerpt":"Hallucination detection has become a pressing requirement for trustworthy AI deployment at scale. The most accurate detection methods depend on GPU-intensive inference, proprietary API calls, or white-box access to the generating model. This puts them out of reach for resource-constrained researchers and practitioners. In this paper, we explore a practical alternative: how well can hallucination detection perform using only lightweight, CPU-feasible methods built on publicly available models? We systematically benchmark five such methods: ROUGE-L, semantic similarity, BERTScore, a Natural Lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29809","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/2606.29809/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":"2606.29809","created_at":"2026-06-30T02:17:36.172781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29809v1","created_at":"2026-06-30T02:17:36.172781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29809","created_at":"2026-06-30T02:17:36.172781+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLQWON36R2XI","created_at":"2026-06-30T02:17:36.172781+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLQWON36R2XIAUIG","created_at":"2026-06-30T02:17:36.172781+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLQWON36","created_at":"2026-06-30T02:17:36.172781+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/XLQWON36R2XIAUIGENWPWNHKZ2","json":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2.json","graph_json":"https://pith.science/api/pith-number/XLQWON36R2XIAUIGENWPWNHKZ2/graph.json","events_json":"https://pith.science/api/pith-number/XLQWON36R2XIAUIGENWPWNHKZ2/events.json","paper":"https://pith.science/paper/XLQWON36"},"agent_actions":{"view_html":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2","download_json":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2.json","view_paper":"https://pith.science/paper/XLQWON36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29809&json=true","fetch_graph":"https://pith.science/api/pith-number/XLQWON36R2XIAUIGENWPWNHKZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/XLQWON36R2XIAUIGENWPWNHKZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2/action/storage_attestation","attest_author":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2/action/author_attestation","sign_citation":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2/action/citation_signature","submit_replication":"https://pith.science/pith/XLQWON36R2XIAUIGENWPWNHKZ2/action/replication_record"}},"created_at":"2026-06-30T02:17:36.172781+00:00","updated_at":"2026-06-30T02:17:36.172781+00:00"}