{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F4EY2RBXDUC63EZNA6VT4J3BSO","short_pith_number":"pith:F4EY2RBX","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"},"canonical_sha256":"2f098d44371d05ed932d07ab3e276193908590849a196fea0328da838f90265b","source":{"kind":"arxiv","id":"2605.30018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30018","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30018v1","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30018","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"F4EY2RBXDUC6","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"F4EY2RBXDUC63EZN","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"F4EY2RBX","created_at":"2026-05-29T02:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F4EY2RBXDUC63EZNA6VT4J3BSO","target":"record","payload":{"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"},"canonical_sha256":"2f098d44371d05ed932d07ab3e276193908590849a196fea0328da838f90265b","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"},"source_kind":"arxiv","source_id":"2605.30018","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ixmF0ynXZHf+iQAQaXilUbgUOYnipiTOMEgNrdMjGfEpSJrVtmzhwA8b3WqcUmR58TUDPxvgeBqU3w3CVK4EDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:32:30.860524Z"},"content_sha256":"9038ed1dae6955219b3c65d4925de0917fb0e0128adc3bfb2f8c02d21c9aa23a","schema_version":"1.0","event_id":"sha256:9038ed1dae6955219b3c65d4925de0917fb0e0128adc3bfb2f8c02d21c9aa23a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F4EY2RBXDUC63EZNA6VT4J3BSO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"por7CK1k7yEgYaeuZpxF5yfsEB9zUwpWKzWHV3RlnO4EEZtP9JGXRaxpaLZnzUV9Fq+/xuvh/O1PbrWs0r6bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:32:30.860945Z"},"content_sha256":"1b9d4cb6924ac8a0fd221cf630a644ab67b8b5d8bc89646d5400ec095ccc4ae8","schema_version":"1.0","event_id":"sha256:1b9d4cb6924ac8a0fd221cf630a644ab67b8b5d8bc89646d5400ec095ccc4ae8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/bundle.json","state_url":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/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":"2026-06-04T15:32:30Z","links":{"resolver":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO","bundle":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/bundle.json","state":"https://pith.science/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4EY2RBXDUC63EZNA6VT4J3BSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F4EY2RBXDUC63EZNA6VT4J3BSO","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":"17cda22fb0a124536c416cf4cd0e462de0efaa9c07340d481f11f628ccdcceb4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:41:26Z","title_canon_sha256":"66aa47242350e30a8d22b2598d3385efffcd5da3c6c9ae842865774c597387dc"},"schema_version":"1.0","source":{"id":"2605.30018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30018","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30018v1","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30018","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"F4EY2RBXDUC6","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"F4EY2RBXDUC63EZN","created_at":"2026-05-29T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"F4EY2RBX","created_at":"2026-05-29T02:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:1b9d4cb6924ac8a0fd221cf630a644ab67b8b5d8bc89646d5400ec095ccc4ae8","target":"graph","created_at":"2026-05-29T02:06:07Z","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/2605.30018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Amlan Chakrabarti, Ayan Sengupta, Lipika Dey, Mayank Vatsa, Partha Pratim Chakrabarti, Partha Pratim Das, Richa Singh, Suparna Bhattacharya, Supratik Chakraborty, Tanmoy Chakraborty","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:41:26Z","title":"Latent Performance Profiling of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30018","kind":"arxiv","version":1},"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":"sha256:9038ed1dae6955219b3c65d4925de0917fb0e0128adc3bfb2f8c02d21c9aa23a","target":"record","created_at":"2026-05-29T02:06:07Z","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":"17cda22fb0a124536c416cf4cd0e462de0efaa9c07340d481f11f628ccdcceb4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:41:26Z","title_canon_sha256":"66aa47242350e30a8d22b2598d3385efffcd5da3c6c9ae842865774c597387dc"},"schema_version":"1.0","source":{"id":"2605.30018","kind":"arxiv","version":1}},"canonical_sha256":"2f098d44371d05ed932d07ab3e276193908590849a196fea0328da838f90265b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f098d44371d05ed932d07ab3e276193908590849a196fea0328da838f90265b","first_computed_at":"2026-05-29T02:06:07.201647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:07.201647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n0H9O/zz406Bt+pz7NvuS3qBF+2oqRHWNuVXEPtR3llwFt+oZ40I1xZIFHlhpDBnjwY7tZKW85WDuhTKmnGEBw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:07.202392Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9038ed1dae6955219b3c65d4925de0917fb0e0128adc3bfb2f8c02d21c9aa23a","sha256:1b9d4cb6924ac8a0fd221cf630a644ab67b8b5d8bc89646d5400ec095ccc4ae8"],"state_sha256":"d735d9487521482197c5c91652f94c6005b69ef507510f2a0bd566812947e2f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YnKj103uzqswPFWgCGcej+Z8cbfYZfTVYK3g8cbd8TuSuS0MflzsyInCVCVS9w2bLkk3l3SKk1DY58zkTqQMDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T15:32:30.863219Z","bundle_sha256":"b2aa7710f583ed22c3a852e37da7de7a5d0132d2ea8f219d3a753f7a306c60db"}}