{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RNVMWOMWB7T2JUSKFW3LKRRRX6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"06f3ff959c2f9f36005a70735d48563080b34e52cce59de531833799f0311361","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T14:01:45Z","title_canon_sha256":"14f69e611354f39897a0ec0df6a0b8a37f58e1f37f5953e12867120682cfd009"},"schema_version":"1.0","source":{"id":"2403.11802","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11802","created_at":"2026-07-05T09:53:40Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11802v5","created_at":"2026-07-05T09:53:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11802","created_at":"2026-07-05T09:53:40Z"},{"alias_kind":"pith_short_12","alias_value":"RNVMWOMWB7T2","created_at":"2026-07-05T09:53:40Z"},{"alias_kind":"pith_short_16","alias_value":"RNVMWOMWB7T2JUSK","created_at":"2026-07-05T09:53:40Z"},{"alias_kind":"pith_short_8","alias_value":"RNVMWOMW","created_at":"2026-07-05T09:53:40Z"}],"graph_snapshots":[{"event_id":"sha256:a6a7e0b70b4f4a7fa7754f33b08a7c3730c5a42c93ece3090b3fc09d72c20178","target":"graph","created_at":"2026-07-05T09:53:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.11802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mao Zheng, Mingyang Song, Xuan Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T14:01:45Z","title":"Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11802","kind":"arxiv","version":5},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:191cceb3cebe15c5d0f55f8b8271ada064de31e720b5c7e40dfddb745d511eec","target":"record","created_at":"2026-07-05T09:53:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"06f3ff959c2f9f36005a70735d48563080b34e52cce59de531833799f0311361","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T14:01:45Z","title_canon_sha256":"14f69e611354f39897a0ec0df6a0b8a37f58e1f37f5953e12867120682cfd009"},"schema_version":"1.0","source":{"id":"2403.11802","kind":"arxiv","version":5}},"canonical_sha256":"8b6acb39960fe7a4d24a2db6b54631bf89a90942331557ced56afc782bcc4eae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b6acb39960fe7a4d24a2db6b54631bf89a90942331557ced56afc782bcc4eae","first_computed_at":"2026-07-05T09:53:40.519359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:40.519359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1WXeazKJee4DVCpZIsNdWp2k8ahMRbFxsYvqlHyWZMaDUHnzNF9rNbjx7XPSvwO18R+ZfOHfQwxM/xSdXFStBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:40.519843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11802","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:191cceb3cebe15c5d0f55f8b8271ada064de31e720b5c7e40dfddb745d511eec","sha256:a6a7e0b70b4f4a7fa7754f33b08a7c3730c5a42c93ece3090b3fc09d72c20178"],"state_sha256":"097fdd852d424038f0282a6c944d6885a014b0fa05a1797e249f3ed3a01b2d40"}