{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RLL7D3WE2TCFKKWDEMUFT4CHRI","short_pith_number":"pith:RLL7D3WE","schema_version":"1.0","canonical_sha256":"8ad7f1eec4d4c4552ac3232859f0478a3173095b1d97c6b0190ecd585bb3ebb2","source":{"kind":"arxiv","id":"2401.17139","version":2},"attestation_state":"computed","paper":{"title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Chenghai Li, Jindong Wang, Lai Wei, Weiran Huang, Zhiquan Tan","submitted_at":"2024-01-30T16:19:55Z","abstract_excerpt":"Large Language Models (LLMs) have transformed natural language processing and extended their powerful capabilities to multi-modal domains. As LLMs continue to advance, it is crucial to develop diverse and appropriate metrics for their evaluation. In this paper, we introduce a novel rank-based metric, Diff-eRank, grounded in information theory and geometry principles. Diff-eRank assesses LLMs by analyzing their hidden representations, providing a quantitative measure of how efficiently they eliminate redundant information during training. We demonstrate the applicability of Diff-eRank in both s"},"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":"2401.17139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-30T16:19:55Z","cross_cats_sorted":["cs.AI","cs.CL","cs.IT","math.IT"],"title_canon_sha256":"e0939ff32a5c1a8a33be2b11daa968f4ab358e0c8d00301f2b457e2f7a9e14ea","abstract_canon_sha256":"c261efa7e39147e953334b2e4887ceabb07d0b5eb65129b4a910bb24e21c9e80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:53.844028Z","signature_b64":"zs5VZ/DEniXHeyv4Mw9ym0sdcfaTw6QjLHgc365J3exrFI9L4J7LY3KwNioyPLSQsx7QVE4xanJzNxbpIx3OAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ad7f1eec4d4c4552ac3232859f0478a3173095b1d97c6b0190ecd585bb3ebb2","last_reissued_at":"2026-07-05T09:19:53.843614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:53.843614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Chenghai Li, Jindong Wang, Lai Wei, Weiran Huang, Zhiquan Tan","submitted_at":"2024-01-30T16:19:55Z","abstract_excerpt":"Large Language Models (LLMs) have transformed natural language processing and extended their powerful capabilities to multi-modal domains. As LLMs continue to advance, it is crucial to develop diverse and appropriate metrics for their evaluation. In this paper, we introduce a novel rank-based metric, Diff-eRank, grounded in information theory and geometry principles. Diff-eRank assesses LLMs by analyzing their hidden representations, providing a quantitative measure of how efficiently they eliminate redundant information during training. We demonstrate the applicability of Diff-eRank in both s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17139","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/2401.17139/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":"2401.17139","created_at":"2026-07-05T09:19:53.843672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17139v2","created_at":"2026-07-05T09:19:53.843672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17139","created_at":"2026-07-05T09:19:53.843672+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLL7D3WE2TCF","created_at":"2026-07-05T09:19:53.843672+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLL7D3WE2TCFKKWD","created_at":"2026-07-05T09:19:53.843672+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLL7D3WE","created_at":"2026-07-05T09:19:53.843672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22873","citing_title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","ref_index":230,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI","json":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI.json","graph_json":"https://pith.science/api/pith-number/RLL7D3WE2TCFKKWDEMUFT4CHRI/graph.json","events_json":"https://pith.science/api/pith-number/RLL7D3WE2TCFKKWDEMUFT4CHRI/events.json","paper":"https://pith.science/paper/RLL7D3WE"},"agent_actions":{"view_html":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI","download_json":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI.json","view_paper":"https://pith.science/paper/RLL7D3WE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17139&json=true","fetch_graph":"https://pith.science/api/pith-number/RLL7D3WE2TCFKKWDEMUFT4CHRI/graph.json","fetch_events":"https://pith.science/api/pith-number/RLL7D3WE2TCFKKWDEMUFT4CHRI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI/action/storage_attestation","attest_author":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI/action/author_attestation","sign_citation":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI/action/citation_signature","submit_replication":"https://pith.science/pith/RLL7D3WE2TCFKKWDEMUFT4CHRI/action/replication_record"}},"created_at":"2026-07-05T09:19:53.843672+00:00","updated_at":"2026-07-05T09:19:53.843672+00:00"}