{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T7PUTPAZVCAYZA4SJ47QATZC5T","short_pith_number":"pith:T7PUTPAZ","schema_version":"1.0","canonical_sha256":"9fdf49bc19a8818c83924f3f004f22ecf6f49be2e1c0ef71c504f80bc05f32aa","source":{"kind":"arxiv","id":"2607.00895","version":1},"attestation_state":"computed","paper":{"title":"Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"\\'Ad\\'am Kov\\'acs, Bowei He, G\\'abor Recski, Istv\\'an Boros, Szilveszter T\\'oth, Xue Liu","submitted_at":"2026-07-01T13:01:42Z","abstract_excerpt":"Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generation systems increasingly rely on structured inputs: source code, developer-tool output, markdown documents, tables, and repository metadata. We introduce a unified benchmark for span-level hallucination detection over code, tool output, structured documents, and existing natural-language RAG datasets. The benchmark is built by starting from grounded correct answers, injecting localized hallucinations with exact character labels, and validating th"},"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":"2607.00895","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-01T13:01:42Z","cross_cats_sorted":[],"title_canon_sha256":"dd770e8139e194651c360701eaee957412e1708ad73a34154134f28018ef3b08","abstract_canon_sha256":"ee440859b8c1b51ca6f58b47c27cb6d68cf54518da27e04d9aee88c074e2d7c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:22.706455Z","signature_b64":"ZNAYxbze8WWdRvIWGfT0NADrlMttryj50VrDS+cabND6L3moGINxEIA90jjoXzFfS+MR4bLkq5qPVAEwjwYlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fdf49bc19a8818c83924f3f004f22ecf6f49be2e1c0ef71c504f80bc05f32aa","last_reissued_at":"2026-07-02T01:18:22.706066Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:22.706066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Document Grounding: Span-Level Hallucination Detection over Code, Tool Output, and Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"\\'Ad\\'am Kov\\'acs, Bowei He, G\\'abor Recski, Istv\\'an Boros, Szilveszter T\\'oth, Xue Liu","submitted_at":"2026-07-01T13:01:42Z","abstract_excerpt":"Hallucination detection for retrieval-augmented generation (RAG) is usually evaluated on natural-language document evidence. However, grounded generation systems increasingly rely on structured inputs: source code, developer-tool output, markdown documents, tables, and repository metadata. We introduce a unified benchmark for span-level hallucination detection over code, tool output, structured documents, and existing natural-language RAG datasets. The benchmark is built by starting from grounded correct answers, injecting localized hallucinations with exact character labels, and validating th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00895","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/2607.00895/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":"2607.00895","created_at":"2026-07-02T01:18:22.706113+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00895v1","created_at":"2026-07-02T01:18:22.706113+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00895","created_at":"2026-07-02T01:18:22.706113+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7PUTPAZVCAY","created_at":"2026-07-02T01:18:22.706113+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7PUTPAZVCAYZA4S","created_at":"2026-07-02T01:18:22.706113+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7PUTPAZ","created_at":"2026-07-02T01:18:22.706113+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/T7PUTPAZVCAYZA4SJ47QATZC5T","json":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T.json","graph_json":"https://pith.science/api/pith-number/T7PUTPAZVCAYZA4SJ47QATZC5T/graph.json","events_json":"https://pith.science/api/pith-number/T7PUTPAZVCAYZA4SJ47QATZC5T/events.json","paper":"https://pith.science/paper/T7PUTPAZ"},"agent_actions":{"view_html":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T","download_json":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T.json","view_paper":"https://pith.science/paper/T7PUTPAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00895&json=true","fetch_graph":"https://pith.science/api/pith-number/T7PUTPAZVCAYZA4SJ47QATZC5T/graph.json","fetch_events":"https://pith.science/api/pith-number/T7PUTPAZVCAYZA4SJ47QATZC5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T/action/storage_attestation","attest_author":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T/action/author_attestation","sign_citation":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T/action/citation_signature","submit_replication":"https://pith.science/pith/T7PUTPAZVCAYZA4SJ47QATZC5T/action/replication_record"}},"created_at":"2026-07-02T01:18:22.706113+00:00","updated_at":"2026-07-02T01:18:22.706113+00:00"}