{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6PIX3AKYJELFTZ6LUYFW6OPSUN","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":"cec6148ad9eaef95d830b1928a6f2a0f155c7f9c0b9fa0815de8576fe2e82746","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T06:44:38Z","title_canon_sha256":"2f78ff643a77ab813805b3b7a6468e95c8ad019a75c98b8006817f95bcdfb421"},"schema_version":"1.0","source":{"id":"2503.04828","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04828","created_at":"2026-07-05T10:25:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04828v1","created_at":"2026-07-05T10:25:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04828","created_at":"2026-07-05T10:25:49Z"},{"alias_kind":"pith_short_12","alias_value":"6PIX3AKYJELF","created_at":"2026-07-05T10:25:49Z"},{"alias_kind":"pith_short_16","alias_value":"6PIX3AKYJELFTZ6L","created_at":"2026-07-05T10:25:49Z"},{"alias_kind":"pith_short_8","alias_value":"6PIX3AKY","created_at":"2026-07-05T10:25:49Z"}],"graph_snapshots":[{"event_id":"sha256:2dd602af1fa6307e50aa69ca8d6202929e716663c7562170fe51a780dc0b9f3a","target":"graph","created_at":"2026-07-05T10:25:49Z","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/2503.04828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Models (LLMs) are fundamentally next-token prediction systems, their practical applications extend far beyond this basic function. From natural language processing and text generation to conversational assistants and software use, LLMs have numerous use-cases, and have already acquired a significant degree of enterprise adoption. To evaluate such models, static evaluation datasets, consisting of a set of prompts and their corresponding ground truths, are often used to benchmark the efficacy of the model for a particular task. In this paper, we provide the basis for a more ","authors_text":"Archie Chaudhury, Shreya Agrawal, Vishakha Agrawal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T06:44:38Z","title":"Beyond Next Word Prediction: Developing Comprehensive Evaluation Frameworks for measuring LLM performance on real world applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04828","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:ee26a952fa613de07b02db2c4352e71bbe63be576c13b87c6885a38b362d235d","target":"record","created_at":"2026-07-05T10:25:49Z","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":"cec6148ad9eaef95d830b1928a6f2a0f155c7f9c0b9fa0815de8576fe2e82746","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-05T06:44:38Z","title_canon_sha256":"2f78ff643a77ab813805b3b7a6468e95c8ad019a75c98b8006817f95bcdfb421"},"schema_version":"1.0","source":{"id":"2503.04828","kind":"arxiv","version":1}},"canonical_sha256":"f3d17d8158491659e7cba60b6f39f2a36a6877b4b8c950e3e26f661fef7e9e98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3d17d8158491659e7cba60b6f39f2a36a6877b4b8c950e3e26f661fef7e9e98","first_computed_at":"2026-07-05T10:25:49.984360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:49.984360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wmG2pe1jyCtSBHvbMrtXU5DFCi5fR/ap6q6fM9KwVtxvVPnrHem8Aa015O1slC/BYPFVcty6BZvLy/0D5emECQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:49.985037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04828","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee26a952fa613de07b02db2c4352e71bbe63be576c13b87c6885a38b362d235d","sha256:2dd602af1fa6307e50aa69ca8d6202929e716663c7562170fe51a780dc0b9f3a"],"state_sha256":"c30f622249925192466d24693dc24068525b9ff6e89b8414e52dbc53ab5e8db2"}