{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RNVMWOMWB7T2JUSKFW3LKRRRX6","short_pith_number":"pith:RNVMWOMW","schema_version":"1.0","canonical_sha256":"8b6acb39960fe7a4d24a2db6b54631bf89a90942331557ced56afc782bcc4eae","source":{"kind":"arxiv","id":"2403.11802","version":5},"attestation_state":"computed","paper":{"title":"Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingyang Song, Xuan Luo","submitted_at":"2024-03-18T14:01:45Z","abstract_excerpt":"Despite recent efforts to develop large language models with robust long-context capabilities, the lack of long-context benchmarks means that relatively little is known about their performance. To alleviate this gap, in this paper, we propose \\textbf{Counting-Stars}, a multi-evidence, position-aware, and scalable benchmark designed to evaluate the multi-evidence retrieval capabilities of long-context LLMs. \\textbf{Counting-Stars} comprises two counting-based multiple pieces of evidence retrieval sub-tasks: searching and reasoning. Using Counting-Stars, we conduct experiments to evaluate severa"},"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":"2403.11802","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T14:01:45Z","cross_cats_sorted":[],"title_canon_sha256":"14f69e611354f39897a0ec0df6a0b8a37f58e1f37f5953e12867120682cfd009","abstract_canon_sha256":"06f3ff959c2f9f36005a70735d48563080b34e52cce59de531833799f0311361"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:40.519843Z","signature_b64":"1WXeazKJee4DVCpZIsNdWp2k8ahMRbFxsYvqlHyWZMaDUHnzNF9rNbjx7XPSvwO18R+ZfOHfQwxM/xSdXFStBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b6acb39960fe7a4d24a2db6b54631bf89a90942331557ced56afc782bcc4eae","last_reissued_at":"2026-07-05T09:53:40.519359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:40.519359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mao Zheng, Mingyang Song, Xuan Luo","submitted_at":"2024-03-18T14:01:45Z","abstract_excerpt":"Despite recent efforts to develop large language models with robust long-context capabilities, the lack of long-context benchmarks means that relatively little is known about their performance. To alleviate this gap, in this paper, we propose \\textbf{Counting-Stars}, a multi-evidence, position-aware, and scalable benchmark designed to evaluate the multi-evidence retrieval capabilities of long-context LLMs. \\textbf{Counting-Stars} comprises two counting-based multiple pieces of evidence retrieval sub-tasks: searching and reasoning. Using Counting-Stars, we conduct experiments to evaluate severa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11802","kind":"arxiv","version":5},"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/2403.11802/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":"2403.11802","created_at":"2026-07-05T09:53:40.519417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11802v5","created_at":"2026-07-05T09:53:40.519417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11802","created_at":"2026-07-05T09:53:40.519417+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNVMWOMWB7T2","created_at":"2026-07-05T09:53:40.519417+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNVMWOMWB7T2JUSK","created_at":"2026-07-05T09:53:40.519417+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNVMWOMW","created_at":"2026-07-05T09:53:40.519417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23170","citing_title":"Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6","json":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6.json","graph_json":"https://pith.science/api/pith-number/RNVMWOMWB7T2JUSKFW3LKRRRX6/graph.json","events_json":"https://pith.science/api/pith-number/RNVMWOMWB7T2JUSKFW3LKRRRX6/events.json","paper":"https://pith.science/paper/RNVMWOMW"},"agent_actions":{"view_html":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6","download_json":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6.json","view_paper":"https://pith.science/paper/RNVMWOMW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11802&json=true","fetch_graph":"https://pith.science/api/pith-number/RNVMWOMWB7T2JUSKFW3LKRRRX6/graph.json","fetch_events":"https://pith.science/api/pith-number/RNVMWOMWB7T2JUSKFW3LKRRRX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6/action/storage_attestation","attest_author":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6/action/author_attestation","sign_citation":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6/action/citation_signature","submit_replication":"https://pith.science/pith/RNVMWOMWB7T2JUSKFW3LKRRRX6/action/replication_record"}},"created_at":"2026-07-05T09:53:40.519417+00:00","updated_at":"2026-07-05T09:53:40.519417+00:00"}