{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6P2E2DW3LAMIBVGHRQZQS5QI7J","short_pith_number":"pith:6P2E2DW3","canonical_record":{"source":{"id":"2502.05167","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T18:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"986acf6d4fbfc2fdfde2c45a35e4b9efaf99ed304e73678c5c725eb589e4bab8","abstract_canon_sha256":"3c50f4295312b4bb3f5d5e99c5c9bc0eb410e105d6f08718b23526dc80a60d2c"},"schema_version":"1.0"},"canonical_sha256":"f3f44d0edb581880d4c78c33097608fa690b7bbaa68e52ee26a79bc31b3acd2e","source":{"kind":"arxiv","id":"2502.05167","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05167","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05167v3","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05167","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_12","alias_value":"6P2E2DW3LAMI","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_16","alias_value":"6P2E2DW3LAMIBVGH","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_8","alias_value":"6P2E2DW3","created_at":"2026-07-05T11:34:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6P2E2DW3LAMIBVGHRQZQS5QI7J","target":"record","payload":{"canonical_record":{"source":{"id":"2502.05167","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T18:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"986acf6d4fbfc2fdfde2c45a35e4b9efaf99ed304e73678c5c725eb589e4bab8","abstract_canon_sha256":"3c50f4295312b4bb3f5d5e99c5c9bc0eb410e105d6f08718b23526dc80a60d2c"},"schema_version":"1.0"},"canonical_sha256":"f3f44d0edb581880d4c78c33097608fa690b7bbaa68e52ee26a79bc31b3acd2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:04.298877Z","signature_b64":"VQiC1KinjQW1s7g4vuDdAG86J8sXF9v3UN/UkIhsNXdZ7j70siKyiPmyEhAHrVvTpA2M6uuKmzh4U+MB3SEnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3f44d0edb581880d4c78c33097608fa690b7bbaa68e52ee26a79bc31b3acd2e","last_reissued_at":"2026-07-05T11:34:04.298389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:04.298389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.05167","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3n4CE2DfgmnzxXwKSq6Xz3A5yW76cbtPvJ09W5tObfKFnyJ2W6i04v09+OXsNsn9khNQwSqS2keH/j6pa5fgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:44:45.621951Z"},"content_sha256":"2110dacebc9d3954d258bfce6e9d3b19b8cda6b767366fb8792d77a601305c46","schema_version":"1.0","event_id":"sha256:2110dacebc9d3954d258bfce6e9d3b19b8cda6b767366fb8792d77a601305c46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6P2E2DW3LAMIBVGHRQZQS5QI7J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ali Modarressi, Franck Dernoncourt, Hanieh Deilamsalehy, Hinrich Sch\\\"utze, Ryan A. Rossi, Seunghyun Yoon, Trung Bui","submitted_at":"2025-02-07T18:49:46Z","abstract_excerpt":"Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a \"needle\" (relevant information) from a \"haystack\" (long irrelevant context). Extensions of this approach include increasing distractors, fact chaining, and in-context reasoning. However, in these benchmarks, models can exploit existing literal matches between the needle and haystack to simplify the task. To address this, we introduce NoLiMa, a benchmark extending NIAH with a carefully de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05167","kind":"arxiv","version":3},"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/2502.05167/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U7g7SohM5uaistwCcZXSeeaeQMSYURK4mJeEQfgqOEBqDK7WdQQ51w24IUx+D6yJWZPoKULlMlMybLzJPPiwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:44:45.622529Z"},"content_sha256":"9a6f22e9c23aad99b73f3c64f424a1ca6303637af89482df6951104eb5c2839b","schema_version":"1.0","event_id":"sha256:9a6f22e9c23aad99b73f3c64f424a1ca6303637af89482df6951104eb5c2839b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J/bundle.json","state_url":"https://pith.science/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T02:44:45Z","links":{"resolver":"https://pith.science/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J","bundle":"https://pith.science/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J/bundle.json","state":"https://pith.science/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6P2E2DW3LAMIBVGHRQZQS5QI7J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6P2E2DW3LAMIBVGHRQZQS5QI7J","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":"3c50f4295312b4bb3f5d5e99c5c9bc0eb410e105d6f08718b23526dc80a60d2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T18:49:46Z","title_canon_sha256":"986acf6d4fbfc2fdfde2c45a35e4b9efaf99ed304e73678c5c725eb589e4bab8"},"schema_version":"1.0","source":{"id":"2502.05167","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05167","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05167v3","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05167","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_12","alias_value":"6P2E2DW3LAMI","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_16","alias_value":"6P2E2DW3LAMIBVGH","created_at":"2026-07-05T11:34:04Z"},{"alias_kind":"pith_short_8","alias_value":"6P2E2DW3","created_at":"2026-07-05T11:34:04Z"}],"graph_snapshots":[{"event_id":"sha256:9a6f22e9c23aad99b73f3c64f424a1ca6303637af89482df6951104eb5c2839b","target":"graph","created_at":"2026-07-05T11:34:04Z","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/2502.05167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent large language models (LLMs) support long contexts ranging from 128K to 1M tokens. A popular method for evaluating these capabilities is the needle-in-a-haystack (NIAH) test, which involves retrieving a \"needle\" (relevant information) from a \"haystack\" (long irrelevant context). Extensions of this approach include increasing distractors, fact chaining, and in-context reasoning. However, in these benchmarks, models can exploit existing literal matches between the needle and haystack to simplify the task. To address this, we introduce NoLiMa, a benchmark extending NIAH with a carefully de","authors_text":"Ali Modarressi, Franck Dernoncourt, Hanieh Deilamsalehy, Hinrich Sch\\\"utze, Ryan A. Rossi, Seunghyun Yoon, Trung Bui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T18:49:46Z","title":"NoLiMa: Long-Context Evaluation Beyond Literal Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05167","kind":"arxiv","version":3},"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":"sha256:2110dacebc9d3954d258bfce6e9d3b19b8cda6b767366fb8792d77a601305c46","target":"record","created_at":"2026-07-05T11:34:04Z","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":"3c50f4295312b4bb3f5d5e99c5c9bc0eb410e105d6f08718b23526dc80a60d2c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-07T18:49:46Z","title_canon_sha256":"986acf6d4fbfc2fdfde2c45a35e4b9efaf99ed304e73678c5c725eb589e4bab8"},"schema_version":"1.0","source":{"id":"2502.05167","kind":"arxiv","version":3}},"canonical_sha256":"f3f44d0edb581880d4c78c33097608fa690b7bbaa68e52ee26a79bc31b3acd2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3f44d0edb581880d4c78c33097608fa690b7bbaa68e52ee26a79bc31b3acd2e","first_computed_at":"2026-07-05T11:34:04.298389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:04.298389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VQiC1KinjQW1s7g4vuDdAG86J8sXF9v3UN/UkIhsNXdZ7j70siKyiPmyEhAHrVvTpA2M6uuKmzh4U+MB3SEnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:04.298877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05167","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2110dacebc9d3954d258bfce6e9d3b19b8cda6b767366fb8792d77a601305c46","sha256:9a6f22e9c23aad99b73f3c64f424a1ca6303637af89482df6951104eb5c2839b"],"state_sha256":"5a3fa88c7dfb99a63b29e8d9b5b8b2142401460e6102c11c564cef41c42a7c5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WEoUeT+utftvG9Z5FU7gc4bdGMeOOvJBEdbeaTlbjJPQlE13OWvIQEPUtjJfB6tBm2EIkVD7y3QoV9+H3xpiCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:44:45.626024Z","bundle_sha256":"99198035c0a9ec1632932944d308048f18a4a5770d90ad9831252c4d406ada92"}}