{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AUOM5ZVB4D5BQSEF6TGBSWI3OY","short_pith_number":"pith:AUOM5ZVB","schema_version":"1.0","canonical_sha256":"051ccee6a1e0fa184885f4cc19591b7616a1dd3d2d95b62375d620e699a900a7","source":{"kind":"arxiv","id":"2507.09506","version":2},"attestation_state":"computed","paper":{"title":"Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Dit-Yan Yeung, Gefei Gu, Junjie Wu, Yanan Zheng","submitted_at":"2025-07-13T06:17:53Z","abstract_excerpt":"Long-context language models (LCLMs) have exhibited impressive capabilities in long-context understanding tasks. Among these, long-context referencing -- a crucial task that requires LCLMs to attribute items of interest to specific parts of long-context data -- remains underexplored. To bridge this gap, this paper proposes Referencing Evaluation for Long-context Language Models (Ref-Long), a novel benchmark designed to assess the long-context referencing capability of LCLMs. Specifically, Ref-Long requires LCLMs to identify the indexes of documents that reference a specific key, emphasizing co"},"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":"2507.09506","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-13T06:17:53Z","cross_cats_sorted":[],"title_canon_sha256":"6b35ec210c7e1b0266f54af62adc6f1e53679d45b29d26923c0fa8996087e6af","abstract_canon_sha256":"93999540a02bcbad1445745b947b991ebee4bbcf216da4205b9c8b1d8ca64c9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:25.942879Z","signature_b64":"ir53c8WTARuTykb/+rMaYLH6kCGgxT2FHb2nW8C9SnmEkJ1PUhLAHHKUDxQMB66V714ry45Sd8DHTE+sCqK4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"051ccee6a1e0fa184885f4cc19591b7616a1dd3d2d95b62375d620e699a900a7","last_reissued_at":"2026-07-05T11:47:25.942392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:25.942392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arman Cohan, Dit-Yan Yeung, Gefei Gu, Junjie Wu, Yanan Zheng","submitted_at":"2025-07-13T06:17:53Z","abstract_excerpt":"Long-context language models (LCLMs) have exhibited impressive capabilities in long-context understanding tasks. Among these, long-context referencing -- a crucial task that requires LCLMs to attribute items of interest to specific parts of long-context data -- remains underexplored. To bridge this gap, this paper proposes Referencing Evaluation for Long-context Language Models (Ref-Long), a novel benchmark designed to assess the long-context referencing capability of LCLMs. Specifically, Ref-Long requires LCLMs to identify the indexes of documents that reference a specific key, emphasizing co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09506","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/2507.09506/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":"2507.09506","created_at":"2026-07-05T11:47:25.942453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09506v2","created_at":"2026-07-05T11:47:25.942453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09506","created_at":"2026-07-05T11:47:25.942453+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUOM5ZVB4D5B","created_at":"2026-07-05T11:47:25.942453+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUOM5ZVB4D5BQSEF","created_at":"2026-07-05T11:47:25.942453+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUOM5ZVB","created_at":"2026-07-05T11:47:25.942453+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/AUOM5ZVB4D5BQSEF6TGBSWI3OY","json":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY.json","graph_json":"https://pith.science/api/pith-number/AUOM5ZVB4D5BQSEF6TGBSWI3OY/graph.json","events_json":"https://pith.science/api/pith-number/AUOM5ZVB4D5BQSEF6TGBSWI3OY/events.json","paper":"https://pith.science/paper/AUOM5ZVB"},"agent_actions":{"view_html":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY","download_json":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY.json","view_paper":"https://pith.science/paper/AUOM5ZVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09506&json=true","fetch_graph":"https://pith.science/api/pith-number/AUOM5ZVB4D5BQSEF6TGBSWI3OY/graph.json","fetch_events":"https://pith.science/api/pith-number/AUOM5ZVB4D5BQSEF6TGBSWI3OY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY/action/storage_attestation","attest_author":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY/action/author_attestation","sign_citation":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY/action/citation_signature","submit_replication":"https://pith.science/pith/AUOM5ZVB4D5BQSEF6TGBSWI3OY/action/replication_record"}},"created_at":"2026-07-05T11:47:25.942453+00:00","updated_at":"2026-07-05T11:47:25.942453+00:00"}