{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MACCG6A4IQJDAVCN4D22XQJ5OI","short_pith_number":"pith:MACCG6A4","schema_version":"1.0","canonical_sha256":"600423781c441230544de0f5abc13d722dbe5868f52e4701544d94dceedacf63","source":{"kind":"arxiv","id":"2404.06480","version":2},"attestation_state":"computed","paper":{"title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chonghua Wang, Dahua Lin, Haodong Duan, Kai Chen, Songyang Zhang","submitted_at":"2024-04-09T17:30:48Z","abstract_excerpt":"Recently, the large language model (LLM) community has shown increasing interest in enhancing LLMs' capability to handle extremely long documents. As various long-text techniques and model architectures emerge, the precise and detailed evaluation of models' long-text capabilities has become increasingly important. Existing long-text evaluation benchmarks, such as L-Eval and LongBench, construct long-text test sets based on open-source datasets, focusing mainly on QA and summarization tasks. These datasets include test samples of varying lengths (from 2k to 32k+) entangled together, making it c"},"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":"2404.06480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T17:30:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"38b25b800cfc69e4282133e94480744097b6b07da2e774ef279345b946c80bae","abstract_canon_sha256":"6b3c60aadeb7bea197d78768477f9d15ee3e57a784ff89647b9924822bdbcd92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:29.429023Z","signature_b64":"qLUFAFFPFqXmuYoItM7wfe+9PrLiZm77hmsQKwRO2sDQcm/Jg+CnV2bXRzgkP+gwgb9eX0t0PbswL0FskbeBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"600423781c441230544de0f5abc13d722dbe5868f52e4701544d94dceedacf63","last_reissued_at":"2026-07-05T08:06:29.428546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:29.428546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chonghua Wang, Dahua Lin, Haodong Duan, Kai Chen, Songyang Zhang","submitted_at":"2024-04-09T17:30:48Z","abstract_excerpt":"Recently, the large language model (LLM) community has shown increasing interest in enhancing LLMs' capability to handle extremely long documents. As various long-text techniques and model architectures emerge, the precise and detailed evaluation of models' long-text capabilities has become increasingly important. Existing long-text evaluation benchmarks, such as L-Eval and LongBench, construct long-text test sets based on open-source datasets, focusing mainly on QA and summarization tasks. These datasets include test samples of varying lengths (from 2k to 32k+) entangled together, making it c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06480","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/2404.06480/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":"2404.06480","created_at":"2026-07-05T08:06:29.428606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06480v2","created_at":"2026-07-05T08:06:29.428606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06480","created_at":"2026-07-05T08:06:29.428606+00:00"},{"alias_kind":"pith_short_12","alias_value":"MACCG6A4IQJD","created_at":"2026-07-05T08:06:29.428606+00:00"},{"alias_kind":"pith_short_16","alias_value":"MACCG6A4IQJDAVCN","created_at":"2026-07-05T08:06:29.428606+00:00"},{"alias_kind":"pith_short_8","alias_value":"MACCG6A4","created_at":"2026-07-05T08:06:29.428606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15732","citing_title":"Accuracy Is Speed: Towards Long-Context-Aware Routing for Distributed LLM Serving","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI","json":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI.json","graph_json":"https://pith.science/api/pith-number/MACCG6A4IQJDAVCN4D22XQJ5OI/graph.json","events_json":"https://pith.science/api/pith-number/MACCG6A4IQJDAVCN4D22XQJ5OI/events.json","paper":"https://pith.science/paper/MACCG6A4"},"agent_actions":{"view_html":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI","download_json":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI.json","view_paper":"https://pith.science/paper/MACCG6A4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06480&json=true","fetch_graph":"https://pith.science/api/pith-number/MACCG6A4IQJDAVCN4D22XQJ5OI/graph.json","fetch_events":"https://pith.science/api/pith-number/MACCG6A4IQJDAVCN4D22XQJ5OI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI/action/storage_attestation","attest_author":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI/action/author_attestation","sign_citation":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI/action/citation_signature","submit_replication":"https://pith.science/pith/MACCG6A4IQJDAVCN4D22XQJ5OI/action/replication_record"}},"created_at":"2026-07-05T08:06:29.428606+00:00","updated_at":"2026-07-05T08:06:29.428606+00:00"}