{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QYNIPXUCZANWIYXSQX5E67XWNP","short_pith_number":"pith:QYNIPXUC","schema_version":"1.0","canonical_sha256":"861a87de82c81b6462f285fa4f7ef66bf5c7954bb45e294ddd03c0286065bab3","source":{"kind":"arxiv","id":"2608.07370","version":1},"attestation_state":"computed","paper":{"title":"LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Xue, Di Wu, Freda Shi, Kath Choi, Krzysztof Czarnecki, Peng Shi, Songcheng Cai, Xiangrui Ke, Xuye Liu, Yimu Wang","submitted_at":"2026-08-07T16:11:52Z","abstract_excerpt":"Scientific literature is increasingly used as a knowledge source for language models, retrieval-augmented generation systems, and research assistants, but answering research questions from papers requires more than fluent generation. A reliable system must identify the relevant papers, locate the concrete evidence that supports the answer, and produce a response that is faithful to that evidence. We present LitTraceQA, a benchmark for literature-grounded question answering over scientific papers. Given a research question and a metadata pool of papers, a system must return three connected outp"},"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":"2608.07370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T16:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"57010532c2b497a8f441305b69718eae2779b1952805b75c5819533afc917083","abstract_canon_sha256":"fbde7d72828e0ff60f4fda549fa738ac644bae541aa32a9c59a943afaafb0d09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:10.689975Z","signature_b64":"rs3eChtRuS3Xvaj4JkiRyyDkGkGmx3zF6Ca5PwrVJWhUVFjmb89ulYNp/G8wNP2UKJbsrfSsuxwR5N4Cc7WcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"861a87de82c81b6462f285fa4f7ef66bf5c7954bb45e294ddd03c0286065bab3","last_reissued_at":"2026-08-10T01:15:10.687763Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:10.687763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LitTraceQA: A Benchmark for Multi-Stage Grounding and Verification in Scientific Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Xue, Di Wu, Freda Shi, Kath Choi, Krzysztof Czarnecki, Peng Shi, Songcheng Cai, Xiangrui Ke, Xuye Liu, Yimu Wang","submitted_at":"2026-08-07T16:11:52Z","abstract_excerpt":"Scientific literature is increasingly used as a knowledge source for language models, retrieval-augmented generation systems, and research assistants, but answering research questions from papers requires more than fluent generation. A reliable system must identify the relevant papers, locate the concrete evidence that supports the answer, and produce a response that is faithful to that evidence. We present LitTraceQA, a benchmark for literature-grounded question answering over scientific papers. Given a research question and a metadata pool of papers, a system must return three connected outp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07370","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/2608.07370/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":"2608.07370","created_at":"2026-08-10T01:15:10.688587+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.07370v1","created_at":"2026-08-10T01:15:10.688587+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07370","created_at":"2026-08-10T01:15:10.688587+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYNIPXUCZANW","created_at":"2026-08-10T01:15:10.688587+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYNIPXUCZANWIYXS","created_at":"2026-08-10T01:15:10.688587+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYNIPXUC","created_at":"2026-08-10T01:15:10.688587+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/QYNIPXUCZANWIYXSQX5E67XWNP","json":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP.json","graph_json":"https://pith.science/api/pith-number/QYNIPXUCZANWIYXSQX5E67XWNP/graph.json","events_json":"https://pith.science/api/pith-number/QYNIPXUCZANWIYXSQX5E67XWNP/events.json","paper":"https://pith.science/paper/QYNIPXUC"},"agent_actions":{"view_html":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP","download_json":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP.json","view_paper":"https://pith.science/paper/QYNIPXUC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.07370&json=true","fetch_graph":"https://pith.science/api/pith-number/QYNIPXUCZANWIYXSQX5E67XWNP/graph.json","fetch_events":"https://pith.science/api/pith-number/QYNIPXUCZANWIYXSQX5E67XWNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP/action/storage_attestation","attest_author":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP/action/author_attestation","sign_citation":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP/action/citation_signature","submit_replication":"https://pith.science/pith/QYNIPXUCZANWIYXSQX5E67XWNP/action/replication_record"}},"created_at":"2026-08-10T01:15:10.688587+00:00","updated_at":"2026-08-10T01:15:10.688587+00:00"}