{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NIS5BKWDILXN66RFV4VDC3V2UF","short_pith_number":"pith:NIS5BKWD","canonical_record":{"source":{"id":"2507.09483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"43fc9047a48ca33cbd0fae65d8f867d1985cb8bd0ee62e0905a077b7f34c5c01","abstract_canon_sha256":"925f61387656554a417eed9f7f7935f51fca5a9cba7b942bcd13ee08042a947d"},"schema_version":"1.0"},"canonical_sha256":"6a25d0aac342eedf7a25af2a316ebaa17152ec37126cf3543d0f6468fb01aded","source":{"kind":"arxiv","id":"2507.09483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09483","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09483v1","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09483","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"NIS5BKWDILXN","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"NIS5BKWDILXN66RF","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"NIS5BKWD","created_at":"2026-07-05T11:36:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NIS5BKWDILXN66RFV4VDC3V2UF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"43fc9047a48ca33cbd0fae65d8f867d1985cb8bd0ee62e0905a077b7f34c5c01","abstract_canon_sha256":"925f61387656554a417eed9f7f7935f51fca5a9cba7b942bcd13ee08042a947d"},"schema_version":"1.0"},"canonical_sha256":"6a25d0aac342eedf7a25af2a316ebaa17152ec37126cf3543d0f6468fb01aded","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:09.797885Z","signature_b64":"eZrnAW6PgbLPF5uDMSCTgeuze4Jneb/HT2eKR6c/uRM1x+tVgb0ROMKN2rD0MxC0AyTKAquRwXN5b6m7zuVRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a25d0aac342eedf7a25af2a316ebaa17152ec37126cf3543d0f6468fb01aded","last_reissued_at":"2026-07-05T11:36:09.797461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:09.797461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09483","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":"2026-07-05T11:36:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRxlQTrfLZRuZBkCKNVQHViSgE4Qtl4dLeH6GNwC2k1k2/GfxQfEMKRH7kyRc3QSKEErmb/2tc73Hq7RG5UhAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:14:46.493901Z"},"content_sha256":"963581590ac1029f1d509721768bd7127d384f62d52a9a77e8cc741044f83319","schema_version":"1.0","event_id":"sha256:963581590ac1029f1d509721768bd7127d384f62d52a9a77e8cc741044f83319"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NIS5BKWDILXN66RFV4VDC3V2UF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Does UMBRELA Work on Other LLMs?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Laura Dietz, Naghmeh Farzi","submitted_at":"2025-07-13T04:05:25Z","abstract_excerpt":"We reproduce the UMBRELA LLM Judge evaluation framework across a range of large language models (LLMs) to assess its generalizability beyond the original study. Our investigation evaluates how LLM choice affects relevance assessment accuracy, focusing on leaderboard rank correlation and per-label agreement metrics. Results demonstrate that UMBRELA with DeepSeek V3 obtains very comparable performance to GPT-4o (used in original work). For LLaMA-3.3-70B we obtain slightly lower performance, which further degrades with smaller LLMs."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09483","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/2507.09483/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":"2026-07-05T11:36:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGJO/iE8e7csH60PfskNmDQ5wid58vaVmyv5dzBHZtty/73j7bF24IKaX/bWqrRROv/yjcXDdTSq8+Hi+OGXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:14:46.494449Z"},"content_sha256":"910a732b5fac54dd55949f5ec7399d4179b6de2daf79ec90bfc069aadf1c2e3a","schema_version":"1.0","event_id":"sha256:910a732b5fac54dd55949f5ec7399d4179b6de2daf79ec90bfc069aadf1c2e3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIS5BKWDILXN66RFV4VDC3V2UF/bundle.json","state_url":"https://pith.science/pith/NIS5BKWDILXN66RFV4VDC3V2UF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIS5BKWDILXN66RFV4VDC3V2UF/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":"2026-08-07T06:14:46Z","links":{"resolver":"https://pith.science/pith/NIS5BKWDILXN66RFV4VDC3V2UF","bundle":"https://pith.science/pith/NIS5BKWDILXN66RFV4VDC3V2UF/bundle.json","state":"https://pith.science/pith/NIS5BKWDILXN66RFV4VDC3V2UF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIS5BKWDILXN66RFV4VDC3V2UF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NIS5BKWDILXN66RFV4VDC3V2UF","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":"925f61387656554a417eed9f7f7935f51fca5a9cba7b942bcd13ee08042a947d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:05:25Z","title_canon_sha256":"43fc9047a48ca33cbd0fae65d8f867d1985cb8bd0ee62e0905a077b7f34c5c01"},"schema_version":"1.0","source":{"id":"2507.09483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09483","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09483v1","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09483","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"NIS5BKWDILXN","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"NIS5BKWDILXN66RF","created_at":"2026-07-05T11:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"NIS5BKWD","created_at":"2026-07-05T11:36:09Z"}],"graph_snapshots":[{"event_id":"sha256:910a732b5fac54dd55949f5ec7399d4179b6de2daf79ec90bfc069aadf1c2e3a","target":"graph","created_at":"2026-07-05T11:36:09Z","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/2507.09483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We reproduce the UMBRELA LLM Judge evaluation framework across a range of large language models (LLMs) to assess its generalizability beyond the original study. Our investigation evaluates how LLM choice affects relevance assessment accuracy, focusing on leaderboard rank correlation and per-label agreement metrics. Results demonstrate that UMBRELA with DeepSeek V3 obtains very comparable performance to GPT-4o (used in original work). For LLaMA-3.3-70B we obtain slightly lower performance, which further degrades with smaller LLMs.","authors_text":"Laura Dietz, Naghmeh Farzi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:05:25Z","title":"Does UMBRELA Work on Other LLMs?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09483","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":"sha256:963581590ac1029f1d509721768bd7127d384f62d52a9a77e8cc741044f83319","target":"record","created_at":"2026-07-05T11:36:09Z","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":"925f61387656554a417eed9f7f7935f51fca5a9cba7b942bcd13ee08042a947d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-07-13T04:05:25Z","title_canon_sha256":"43fc9047a48ca33cbd0fae65d8f867d1985cb8bd0ee62e0905a077b7f34c5c01"},"schema_version":"1.0","source":{"id":"2507.09483","kind":"arxiv","version":1}},"canonical_sha256":"6a25d0aac342eedf7a25af2a316ebaa17152ec37126cf3543d0f6468fb01aded","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a25d0aac342eedf7a25af2a316ebaa17152ec37126cf3543d0f6468fb01aded","first_computed_at":"2026-07-05T11:36:09.797461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:09.797461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eZrnAW6PgbLPF5uDMSCTgeuze4Jneb/HT2eKR6c/uRM1x+tVgb0ROMKN2rD0MxC0AyTKAquRwXN5b6m7zuVRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:09.797885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:963581590ac1029f1d509721768bd7127d384f62d52a9a77e8cc741044f83319","sha256:910a732b5fac54dd55949f5ec7399d4179b6de2daf79ec90bfc069aadf1c2e3a"],"state_sha256":"e085f94bceb35678745dcd3cfa8adec9a4c79f1340779c697fa84696ce0dd253"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUEs7hXXDzIhxNgkrT5cXJI17XOcLaENAZjHL31ovowLJL/wGPCNX5AD67Co+3lVPHHC/E1a42wS9EX/7yujBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:14:46.498187Z","bundle_sha256":"11174791bb2130d35f3f7c38a1a8551974121e178ca3b5f342dbcf248430c649"}}