{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24LJO3P6DENFHQTH32FNXZVXXU","short_pith_number":"pith:24LJO3P6","schema_version":"1.0","canonical_sha256":"d716976dfe191a53c267de8adbe6b7bd3691454e19cd1a0b274cadd9c6ffe010","source":{"kind":"arxiv","id":"2504.05317","version":2},"attestation_state":"computed","paper":{"title":"On Synthesizing Data for Context Attribution in Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Carolin Lawrence, Chia-Chien Hung, Christopher Malon, Goran Glava\\v{s}, Gorjan Radevski, Kiril Gashteovski, Kunihiro Takeoka, Masafumi Enomoto, Masafumi Oyamada, Sebastien Nicolas, Shahbaz Syed, Timo Sztyler, Verena Heu{\\ss}er, Wiem Ben Rim","submitted_at":"2025-02-21T09:43:18Z","abstract_excerpt":"Question Answering (QA) accounts for a significant portion of LLM usage \"in the wild\". However, LLMs sometimes produce false or misleading responses, also known as \"hallucinations\". Therefore, grounding the generated answers in contextually provided information -- i.e., providing evidence for the generated text -- is paramount for LLMs' trustworthiness. Providing this information is the task of context attribution. In this paper, we systematically study LLM-based approaches for this task, namely we investigate (i) zero-shot inference, (ii) LLM ensembling, and (iii) fine-tuning of small LMs on "},"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":"2504.05317","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-02-21T09:43:18Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"639c4d808e88a56efb22c7aee12c7cb6eabdd1b698c5bb9ecf87d379d44dc772","abstract_canon_sha256":"2aceb10a5c4dfcd0cd44ccdf6756f383bbd43ec58990886a8decff3b7fbe5e57"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:18.233001Z","signature_b64":"k6+nI0XWnJ9kQ/VXI8M3eiIR98cBdlitE4/gP4fzoCU/LNJw0V/RmTFL+l2c02EgMX4k3iC3fl8FUW+Y/jthDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d716976dfe191a53c267de8adbe6b7bd3691454e19cd1a0b274cadd9c6ffe010","last_reissued_at":"2026-07-05T11:22:18.232507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:18.232507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Synthesizing Data for Context Attribution in Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Carolin Lawrence, Chia-Chien Hung, Christopher Malon, Goran Glava\\v{s}, Gorjan Radevski, Kiril Gashteovski, Kunihiro Takeoka, Masafumi Enomoto, Masafumi Oyamada, Sebastien Nicolas, Shahbaz Syed, Timo Sztyler, Verena Heu{\\ss}er, Wiem Ben Rim","submitted_at":"2025-02-21T09:43:18Z","abstract_excerpt":"Question Answering (QA) accounts for a significant portion of LLM usage \"in the wild\". However, LLMs sometimes produce false or misleading responses, also known as \"hallucinations\". Therefore, grounding the generated answers in contextually provided information -- i.e., providing evidence for the generated text -- is paramount for LLMs' trustworthiness. Providing this information is the task of context attribution. In this paper, we systematically study LLM-based approaches for this task, namely we investigate (i) zero-shot inference, (ii) LLM ensembling, and (iii) fine-tuning of small LMs on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.05317","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/2504.05317/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":"2504.05317","created_at":"2026-07-05T11:22:18.232567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.05317v2","created_at":"2026-07-05T11:22:18.232567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.05317","created_at":"2026-07-05T11:22:18.232567+00:00"},{"alias_kind":"pith_short_12","alias_value":"24LJO3P6DENF","created_at":"2026-07-05T11:22:18.232567+00:00"},{"alias_kind":"pith_short_16","alias_value":"24LJO3P6DENFHQTH","created_at":"2026-07-05T11:22:18.232567+00:00"},{"alias_kind":"pith_short_8","alias_value":"24LJO3P6","created_at":"2026-07-05T11:22:18.232567+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/24LJO3P6DENFHQTH32FNXZVXXU","json":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU.json","graph_json":"https://pith.science/api/pith-number/24LJO3P6DENFHQTH32FNXZVXXU/graph.json","events_json":"https://pith.science/api/pith-number/24LJO3P6DENFHQTH32FNXZVXXU/events.json","paper":"https://pith.science/paper/24LJO3P6"},"agent_actions":{"view_html":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU","download_json":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU.json","view_paper":"https://pith.science/paper/24LJO3P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.05317&json=true","fetch_graph":"https://pith.science/api/pith-number/24LJO3P6DENFHQTH32FNXZVXXU/graph.json","fetch_events":"https://pith.science/api/pith-number/24LJO3P6DENFHQTH32FNXZVXXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU/action/storage_attestation","attest_author":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU/action/author_attestation","sign_citation":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU/action/citation_signature","submit_replication":"https://pith.science/pith/24LJO3P6DENFHQTH32FNXZVXXU/action/replication_record"}},"created_at":"2026-07-05T11:22:18.232567+00:00","updated_at":"2026-07-05T11:22:18.232567+00:00"}