{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T2T5TCH4JQ6KHSYM3SONDCV3D4","short_pith_number":"pith:T2T5TCH4","schema_version":"1.0","canonical_sha256":"9ea7d988fc4c3ca3cb0cdc9cd18abb1f0eab78a4aa5959a79ed190014b386536","source":{"kind":"arxiv","id":"2606.01400","version":1},"attestation_state":"computed","paper":{"title":"Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ana Gjorgjevikj, Denica Kjorvezir, Gjorgjina Cenikj, Marko Djukanovi\\'c, Tome Eftimov","submitted_at":"2026-05-31T18:45:12Z","abstract_excerpt":"Evaluating large language models (LLMs) across comprehensive benchmarks is expensive and time-consuming. We propose a graph-based prompt selection framework that models each benchmark as a similarity graph -- nodes are prompts connected if their embedding-space distance falls above a configurable threshold -- and applies Maximum Independent Set (MIS) algorithms to select a maximally diverse, non-redundant subset. We evaluate four MIS solvers (CPLEX, GREEDY, Online-MIS, ReduMIS) across six embedding models, three distance measures, six percentile thresholds, and four benchmarks (GPQA, IFEval, M"},"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":"2606.01400","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T18:45:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fee4da468983e011e55efa0c2181be6b6284eeb06c9ddb94fd276fd202dce3e","abstract_canon_sha256":"cc9be42e7bcf29f6ea723c8630561931f487a628da77f9d32cc0534d2da7f48a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:32.382274Z","signature_b64":"YKtleTmnHYExF06FllD57qu1AJyCTGH+aRBFP9hkCC/YRmUwoDb7HQcvMTCFo20kKcF9jsKfFL0dbhyk6Ac0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea7d988fc4c3ca3cb0cdc9cd18abb1f0eab78a4aa5959a79ed190014b386536","last_reissued_at":"2026-06-02T02:04:32.381835Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:32.381835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistent and Distinctive: LLM Benchmark Efficiency via Maximum Independent Set Prompt Selection on Similarity Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ana Gjorgjevikj, Denica Kjorvezir, Gjorgjina Cenikj, Marko Djukanovi\\'c, Tome Eftimov","submitted_at":"2026-05-31T18:45:12Z","abstract_excerpt":"Evaluating large language models (LLMs) across comprehensive benchmarks is expensive and time-consuming. We propose a graph-based prompt selection framework that models each benchmark as a similarity graph -- nodes are prompts connected if their embedding-space distance falls above a configurable threshold -- and applies Maximum Independent Set (MIS) algorithms to select a maximally diverse, non-redundant subset. We evaluate four MIS solvers (CPLEX, GREEDY, Online-MIS, ReduMIS) across six embedding models, three distance measures, six percentile thresholds, and four benchmarks (GPQA, IFEval, M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01400","kind":"arxiv","version":1},"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/2606.01400/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":"2606.01400","created_at":"2026-06-02T02:04:32.381914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01400v1","created_at":"2026-06-02T02:04:32.381914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01400","created_at":"2026-06-02T02:04:32.381914+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2T5TCH4JQ6K","created_at":"2026-06-02T02:04:32.381914+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2T5TCH4JQ6KHSYM","created_at":"2026-06-02T02:04:32.381914+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2T5TCH4","created_at":"2026-06-02T02:04:32.381914+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/T2T5TCH4JQ6KHSYM3SONDCV3D4","json":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4.json","graph_json":"https://pith.science/api/pith-number/T2T5TCH4JQ6KHSYM3SONDCV3D4/graph.json","events_json":"https://pith.science/api/pith-number/T2T5TCH4JQ6KHSYM3SONDCV3D4/events.json","paper":"https://pith.science/paper/T2T5TCH4"},"agent_actions":{"view_html":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4","download_json":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4.json","view_paper":"https://pith.science/paper/T2T5TCH4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01400&json=true","fetch_graph":"https://pith.science/api/pith-number/T2T5TCH4JQ6KHSYM3SONDCV3D4/graph.json","fetch_events":"https://pith.science/api/pith-number/T2T5TCH4JQ6KHSYM3SONDCV3D4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4/action/storage_attestation","attest_author":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4/action/author_attestation","sign_citation":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4/action/citation_signature","submit_replication":"https://pith.science/pith/T2T5TCH4JQ6KHSYM3SONDCV3D4/action/replication_record"}},"created_at":"2026-06-02T02:04:32.381914+00:00","updated_at":"2026-06-02T02:04:32.381914+00:00"}