{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DZCSQYD4TL2H2MD6TTHXPROPZH","short_pith_number":"pith:DZCSQYD4","canonical_record":{"source":{"id":"2607.28282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T14:31:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0f8fcf6fb2c183205992b34a1b66ffdde4675ceebc855c2b1ae73194312327d","abstract_canon_sha256":"4039e9797dfff2c1a7bbe246499e864a0c2857d1d0c609953b426784672c3fb6"},"schema_version":"1.0"},"canonical_sha256":"1e4528607c9af47d307e9ccf77c5cfc9cf76d31b0e9f0e43d198ac705315a8c6","source":{"kind":"arxiv","id":"2607.28282","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28282","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28282v1","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28282","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"DZCSQYD4TL2H","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"DZCSQYD4TL2H2MD6","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"DZCSQYD4","created_at":"2026-07-31T01:37:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DZCSQYD4TL2H2MD6TTHXPROPZH","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T14:31:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c0f8fcf6fb2c183205992b34a1b66ffdde4675ceebc855c2b1ae73194312327d","abstract_canon_sha256":"4039e9797dfff2c1a7bbe246499e864a0c2857d1d0c609953b426784672c3fb6"},"schema_version":"1.0"},"canonical_sha256":"1e4528607c9af47d307e9ccf77c5cfc9cf76d31b0e9f0e43d198ac705315a8c6","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e4528607c9af47d307e9ccf77c5cfc9cf76d31b0e9f0e43d198ac705315a8c6","last_reissued_at":"2026-07-31T01:37:08.345653Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:08.345653Z"},"source_kind":"arxiv","source_id":"2607.28282","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":"2026-07-31T01:37:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WFYoy3Fs4I5b9jZeNmNqoBOWR61334YU0oLnrFMTPis7bbtgvvt10EzJcKie0jLp0LD0fUvFdz8bc6cs+l5NDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:48:43.030491Z"},"content_sha256":"84345baacedd248b114b48b7b3399c00362df40653421ddbfd064dbd36206644","schema_version":"1.0","event_id":"sha256:84345baacedd248b114b48b7b3399c00362df40653421ddbfd064dbd36206644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DZCSQYD4TL2H2MD6TTHXPROPZH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"(Towards) Scalable Reliable Automated Evaluation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bertil Braun, Martin Forell","submitted_at":"2026-07-30T14:31:07Z","abstract_excerpt":"Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive. Existing automated metrics often fail to capture the complexity and variability inherent in LLM-generated outputs. Moreover, these metrics typically rely on explicit reference standards, limiting their use mostly to domains with objective benchmarks. This work introduces a novel evaluation framework designed to approximate expert-level assessments of LLM-generated content. The proposed method employs pairwise comparisons of outputs by multiple LLMs, reducing bia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28282","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/2607.28282/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":"2026-07-31T01:37:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IcZqJIpwmI7Udjm1BJjgKuuUaBT1GBvbhfGLbkTZ8KKn5PJk/RluUAIY37sv3aARguIiZP5DKjOB6f0gFU6MAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:48:43.031060Z"},"content_sha256":"2bba3465586ab348a88ea7ff394597c96c76b8f277edee851b25c650e3c1b7fb","schema_version":"1.0","event_id":"sha256:2bba3465586ab348a88ea7ff394597c96c76b8f277edee851b25c650e3c1b7fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZCSQYD4TL2H2MD6TTHXPROPZH/bundle.json","state_url":"https://pith.science/pith/DZCSQYD4TL2H2MD6TTHXPROPZH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZCSQYD4TL2H2MD6TTHXPROPZH/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":"2026-08-03T15:48:43Z","links":{"resolver":"https://pith.science/pith/DZCSQYD4TL2H2MD6TTHXPROPZH","bundle":"https://pith.science/pith/DZCSQYD4TL2H2MD6TTHXPROPZH/bundle.json","state":"https://pith.science/pith/DZCSQYD4TL2H2MD6TTHXPROPZH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZCSQYD4TL2H2MD6TTHXPROPZH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DZCSQYD4TL2H2MD6TTHXPROPZH","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":"4039e9797dfff2c1a7bbe246499e864a0c2857d1d0c609953b426784672c3fb6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T14:31:07Z","title_canon_sha256":"c0f8fcf6fb2c183205992b34a1b66ffdde4675ceebc855c2b1ae73194312327d"},"schema_version":"1.0","source":{"id":"2607.28282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28282","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28282v1","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28282","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"DZCSQYD4TL2H","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"DZCSQYD4TL2H2MD6","created_at":"2026-07-31T01:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"DZCSQYD4","created_at":"2026-07-31T01:37:08Z"}],"graph_snapshots":[{"event_id":"sha256:2bba3465586ab348a88ea7ff394597c96c76b8f277edee851b25c650e3c1b7fb","target":"graph","created_at":"2026-07-31T01:37:08Z","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/2607.28282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the quality and relevance of textual outputs from Large Language Models (LLMs) remains challenging and resource-intensive. Existing automated metrics often fail to capture the complexity and variability inherent in LLM-generated outputs. Moreover, these metrics typically rely on explicit reference standards, limiting their use mostly to domains with objective benchmarks. This work introduces a novel evaluation framework designed to approximate expert-level assessments of LLM-generated content. The proposed method employs pairwise comparisons of outputs by multiple LLMs, reducing bia","authors_text":"Bertil Braun, Martin Forell","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T14:31:07Z","title":"(Towards) Scalable Reliable Automated Evaluation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28282","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":"sha256:84345baacedd248b114b48b7b3399c00362df40653421ddbfd064dbd36206644","target":"record","created_at":"2026-07-31T01:37:08Z","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":"4039e9797dfff2c1a7bbe246499e864a0c2857d1d0c609953b426784672c3fb6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-30T14:31:07Z","title_canon_sha256":"c0f8fcf6fb2c183205992b34a1b66ffdde4675ceebc855c2b1ae73194312327d"},"schema_version":"1.0","source":{"id":"2607.28282","kind":"arxiv","version":1}},"canonical_sha256":"1e4528607c9af47d307e9ccf77c5cfc9cf76d31b0e9f0e43d198ac705315a8c6","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e4528607c9af47d307e9ccf77c5cfc9cf76d31b0e9f0e43d198ac705315a8c6","first_computed_at":"2026-07-31T01:37:08.345653Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:08.345653Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84345baacedd248b114b48b7b3399c00362df40653421ddbfd064dbd36206644","sha256:2bba3465586ab348a88ea7ff394597c96c76b8f277edee851b25c650e3c1b7fb"],"state_sha256":"01c2e5350c7b6dc344ce169dedfdcbe5a27e2f48d4107d2cf354e95473dce065"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTA8gNyjRLndHVg+YMujZfmRCqX9gigKPhsGFoBQn2jD5v3JMWiE7RNA30nEFjAqKY/oFylewXdAq3o7tOonCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:48:43.034768Z","bundle_sha256":"2aa9a4e3b60a247d6e002b56d1278b43dc727c772c3432d39ba8ad578f461d16"}}