{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F4EY2RBXDUC63EZNA6VT4J3BSO","short_pith_number":"pith:F4EY2RBX","schema_version":"1.0","canonical_sha256":"2f098d44371d05ed932d07ab3e276193908590849a196fea0328da838f90265b","source":{"kind":"arxiv","id":"2605.30018","version":1},"attestation_state":"computed","paper":{"title":"Latent Performance Profiling of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amlan Chakrabarti, Ayan Sengupta, Lipika Dey, Mayank Vatsa, Partha Pratim Chakrabarti, Partha Pratim Das, Richa Singh, Suparna Bhattacharya, Supratik Chakraborty, Tanmoy Chakraborty","submitted_at":"2026-05-28T14:41:26Z","abstract_excerpt":"Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data contamination, narrow task scope, and weak alignment with real-world reliability. Benchmark-based evaluations such as MMLU PRO, BBH, or IFEval primarily capture \\textit{what} a model outputs on fixed test sets, not \\textit{how} it processes information, calibrates uncertainty, or structures internal knowledge. In this article, we advocate for a shift from b"},"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":"2605.30018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:41:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"66aa47242350e30a8d22b2598d3385efffcd5da3c6c9ae842865774c597387dc","abstract_canon_sha256":"17cda22fb0a124536c416cf4cd0e462de0efaa9c07340d481f11f628ccdcceb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:07.202392Z","signature_b64":"n0H9O/zz406Bt+pz7NvuS3qBF+2oqRHWNuVXEPtR3llwFt+oZ40I1xZIFHlhpDBnjwY7tZKW85WDuhTKmnGEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f098d44371d05ed932d07ab3e276193908590849a196fea0328da838f90265b","last_reissued_at":"2026-05-29T02:06:07.201647Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:07.201647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Performance Profiling of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Amlan Chakrabarti, Ayan Sengupta, Lipika Dey, Mayank Vatsa, Partha Pratim Chakrabarti, Partha Pratim Das, Richa Singh, Suparna Bhattacharya, Supratik Chakraborty, Tanmoy Chakraborty","submitted_at":"2026-05-28T14:41:26Z","abstract_excerpt":"Large language models (LLMs) frequently achieve impressive scores on standardized benchmarks, yet accuracy alone offers a limited view of their capabilities. Evaluating open-source LLMs through leaderboards faces persistent issues like data contamination, narrow task scope, and weak alignment with real-world reliability. Benchmark-based evaluations such as MMLU PRO, BBH, or IFEval primarily capture \\textit{what} a model outputs on fixed test sets, not \\textit{how} it processes information, calibrates uncertainty, or structures internal knowledge. In this article, we advocate for a shift from b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30018","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/2605.30018/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":"2605.30018","created_at":"2026-05-29T02:06:07.201756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30018v1","created_at":"2026-05-29T02:06:07.201756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30018","created_at":"2026-05-29T02:06:07.201756+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4EY2RBXDUC6","created_at":"2026-05-29T02:06:07.201756+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4EY2RBXDUC63EZN","created_at":"2026-05-29T02:06:07.201756+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4EY2RBX","created_at":"2026-05-29T02:06:07.201756+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/F4EY2RBXDUC63EZNA6VT4J3BSO","json":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO.json","graph_json":"https://pith.science/api/pith-number/F4EY2RBXDUC63EZNA6VT4J3BSO/graph.json","events_json":"https://pith.science/api/pith-number/F4EY2RBXDUC63EZNA6VT4J3BSO/events.json","paper":"https://pith.science/paper/F4EY2RBX"},"agent_actions":{"view_html":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO","download_json":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO.json","view_paper":"https://pith.science/paper/F4EY2RBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30018&json=true","fetch_graph":"https://pith.science/api/pith-number/F4EY2RBXDUC63EZNA6VT4J3BSO/graph.json","fetch_events":"https://pith.science/api/pith-number/F4EY2RBXDUC63EZNA6VT4J3BSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/action/storage_attestation","attest_author":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/action/author_attestation","sign_citation":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/action/citation_signature","submit_replication":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/action/replication_record"}},"created_at":"2026-05-29T02:06:07.201756+00:00","updated_at":"2026-05-29T02:06:07.201756+00:00"}