{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GCWLSTE3YQY6IFF6BOEILJ6TOJ","short_pith_number":"pith:GCWLSTE3","canonical_record":{"source":{"id":"2506.17330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-19T03:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"a6f3c4f9c3a2ca232104d70f3fca709d02a8358421d8d278526fd57f7b18f8c1","abstract_canon_sha256":"76a4fc84bfac3dbc6c73aec3b608f373a01f662c0a21298605ed5f5b373dc6f8"},"schema_version":"1.0"},"canonical_sha256":"30acb94c9bc431e414be0b8885a7d3725c3ce6b2e6a7919c0c866278d94706d2","source":{"kind":"arxiv","id":"2506.17330","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17330","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17330v1","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17330","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"GCWLSTE3YQY6","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"GCWLSTE3YQY6IFF6","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"GCWLSTE3","created_at":"2026-07-05T11:25:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GCWLSTE3YQY6IFF6BOEILJ6TOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-19T03:47:38Z","cross_cats_sorted":[],"title_canon_sha256":"a6f3c4f9c3a2ca232104d70f3fca709d02a8358421d8d278526fd57f7b18f8c1","abstract_canon_sha256":"76a4fc84bfac3dbc6c73aec3b608f373a01f662c0a21298605ed5f5b373dc6f8"},"schema_version":"1.0"},"canonical_sha256":"30acb94c9bc431e414be0b8885a7d3725c3ce6b2e6a7919c0c866278d94706d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:16.002999Z","signature_b64":"7JuGWui+Ig1eTz7rd6nP2d0YScy5ea9tLdTUb6h5zmwo0LWtayAnjmTErRedvMRsH6xEfDbV5OfVVFjfvHmqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30acb94c9bc431e414be0b8885a7d3725c3ce6b2e6a7919c0c866278d94706d2","last_reissued_at":"2026-07-05T11:25:16.002495Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:16.002495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17330","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":"2026-07-05T11:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEfkP83nUNa0dKCH9sV6LmpRxgAuJi0MgAsWBqMklIQB+qj2Gby3RJtH4+7sMIMdUlRacMrdyMBDY8qe/+DQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:21:33.332362Z"},"content_sha256":"b3d1aeef06ad6e97774bc2d05bda551df382d72a2630d691b5f82ebb005cebfe","schema_version":"1.0","event_id":"sha256:b3d1aeef06ad6e97774bc2d05bda551df382d72a2630d691b5f82ebb005cebfe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GCWLSTE3YQY6IFF6BOEILJ6TOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Simon Thorne","submitted_at":"2025-06-19T03:47:38Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated some significant capabilities across various domains; however, their effectiveness in spreadsheet related tasks remains underexplored. This study introduces a foundation for a comprehensive benchmark framework to evaluate the performance of leading LLMs in executing spreadsheet functions, formula generation and data manipulation tasks. The benchmark encompasses tasks ranging from basic formula creation to complex, real world spreadsheet scenarios. Our findings reveal that while LLMs exhibit proficiency in straightforward tasks, they often falter i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17330","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/2506.17330/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":"2026-07-05T11:25:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N5MnXSiqSVyylXJyvleP5uJhTiP9NwNMSQ6plA2uzY0YXaz9wxmnjK82IwsLOMPMh8B4aQs6v0p7MBnOsXh/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:21:33.332882Z"},"content_sha256":"00605606cc536d44a5da28d1a872819a115f6117e7930be37d339d40840abf77","schema_version":"1.0","event_id":"sha256:00605606cc536d44a5da28d1a872819a115f6117e7930be37d339d40840abf77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ/bundle.json","state_url":"https://pith.science/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ/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":"2026-08-05T18:21:33Z","links":{"resolver":"https://pith.science/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ","bundle":"https://pith.science/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ/bundle.json","state":"https://pith.science/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GCWLSTE3YQY6IFF6BOEILJ6TOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GCWLSTE3YQY6IFF6BOEILJ6TOJ","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":"76a4fc84bfac3dbc6c73aec3b608f373a01f662c0a21298605ed5f5b373dc6f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-19T03:47:38Z","title_canon_sha256":"a6f3c4f9c3a2ca232104d70f3fca709d02a8358421d8d278526fd57f7b18f8c1"},"schema_version":"1.0","source":{"id":"2506.17330","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17330","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17330v1","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17330","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_12","alias_value":"GCWLSTE3YQY6","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_16","alias_value":"GCWLSTE3YQY6IFF6","created_at":"2026-07-05T11:25:16Z"},{"alias_kind":"pith_short_8","alias_value":"GCWLSTE3","created_at":"2026-07-05T11:25:16Z"}],"graph_snapshots":[{"event_id":"sha256:00605606cc536d44a5da28d1a872819a115f6117e7930be37d339d40840abf77","target":"graph","created_at":"2026-07-05T11:25:16Z","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/2506.17330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated some significant capabilities across various domains; however, their effectiveness in spreadsheet related tasks remains underexplored. This study introduces a foundation for a comprehensive benchmark framework to evaluate the performance of leading LLMs in executing spreadsheet functions, formula generation and data manipulation tasks. The benchmark encompasses tasks ranging from basic formula creation to complex, real world spreadsheet scenarios. Our findings reveal that while LLMs exhibit proficiency in straightforward tasks, they often falter i","authors_text":"Simon Thorne","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-19T03:47:38Z","title":"Large Language Models for Spreadsheets: Benchmarking Progress and Evaluating Performance with FLARE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17330","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:b3d1aeef06ad6e97774bc2d05bda551df382d72a2630d691b5f82ebb005cebfe","target":"record","created_at":"2026-07-05T11:25:16Z","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":"76a4fc84bfac3dbc6c73aec3b608f373a01f662c0a21298605ed5f5b373dc6f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-06-19T03:47:38Z","title_canon_sha256":"a6f3c4f9c3a2ca232104d70f3fca709d02a8358421d8d278526fd57f7b18f8c1"},"schema_version":"1.0","source":{"id":"2506.17330","kind":"arxiv","version":1}},"canonical_sha256":"30acb94c9bc431e414be0b8885a7d3725c3ce6b2e6a7919c0c866278d94706d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30acb94c9bc431e414be0b8885a7d3725c3ce6b2e6a7919c0c866278d94706d2","first_computed_at":"2026-07-05T11:25:16.002495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:16.002495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7JuGWui+Ig1eTz7rd6nP2d0YScy5ea9tLdTUb6h5zmwo0LWtayAnjmTErRedvMRsH6xEfDbV5OfVVFjfvHmqDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:16.002999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17330","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3d1aeef06ad6e97774bc2d05bda551df382d72a2630d691b5f82ebb005cebfe","sha256:00605606cc536d44a5da28d1a872819a115f6117e7930be37d339d40840abf77"],"state_sha256":"16e89e76beaf00fe79d53c45383fe578668e5523bcc4f992f8e87510990102cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1cq55TMnCYMeV93r1gRmfeGha/7+nHWlJt1M42Nm48ZldKS2ikL5abq2hThqVB5arYTYOGSi6IDsfuT5xdJlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:21:33.336666Z","bundle_sha256":"c7e438b7fda7ead2c3cf7ecaf3d0fc0b9025252defef32fd3c8228fd7000240e"}}