{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HO4Y7P7EKGURSDHI5U7QAH4PW6","short_pith_number":"pith:HO4Y7P7E","canonical_record":{"source":{"id":"2501.14296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-24T07:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"873ca09e2975457edf44113f03e62bbaac37deaceb616d3bd192697002fdb9fb","abstract_canon_sha256":"1db2e00b2b0581a9fc514d7e72359db8675ffff0825fe219ea3fbe84c3549ce3"},"schema_version":"1.0"},"canonical_sha256":"3bb98fbfe451a9190ce8ed3f001f8fb7969d7d5d75c282aa64581b93de2fd3d8","source":{"kind":"arxiv","id":"2501.14296","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14296","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14296v1","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14296","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"HO4Y7P7EKGUR","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"HO4Y7P7EKGURSDHI","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"HO4Y7P7E","created_at":"2026-07-05T10:04:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HO4Y7P7EKGURSDHI5U7QAH4PW6","target":"record","payload":{"canonical_record":{"source":{"id":"2501.14296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-24T07:33:39Z","cross_cats_sorted":[],"title_canon_sha256":"873ca09e2975457edf44113f03e62bbaac37deaceb616d3bd192697002fdb9fb","abstract_canon_sha256":"1db2e00b2b0581a9fc514d7e72359db8675ffff0825fe219ea3fbe84c3549ce3"},"schema_version":"1.0"},"canonical_sha256":"3bb98fbfe451a9190ce8ed3f001f8fb7969d7d5d75c282aa64581b93de2fd3d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:48.273488Z","signature_b64":"ynWAyNJZE7Usr50yxrw6x0pjbTCRlb/j849F56RfXXbyJqbJU5obyiKg59gXOMfxqGBa4zk2Zml4uHY4DNl0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bb98fbfe451a9190ce8ed3f001f8fb7969d7d5d75c282aa64581b93de2fd3d8","last_reissued_at":"2026-07-05T10:04:48.273126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:48.273126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.14296","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":"2026-07-05T10:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LE72IIx0pmPBjOPTl3LrQMOPXuvpdLpOX6DE9dmuiXHlVSAkKp/ywXCvUKmvpZCR42friOYbnBPLROnxbWM0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:03:06.408916Z"},"content_sha256":"98e3ac02603942b7004a2e83ec993df60d64b3249cf73a927a6b5f94db092416","schema_version":"1.0","event_id":"sha256:98e3ac02603942b7004a2e83ec993df60d64b3249cf73a927a6b5f94db092416"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HO4Y7P7EKGURSDHI5U7QAH4PW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Danula Hettiachchi, Falk Scholer, Johanne R. Trippas, Julian A. Schnabel","submitted_at":"2025-01-24T07:33:39Z","abstract_excerpt":"The effectiveness of search systems is evaluated using relevance labels that indicate the usefulness of documents for specific queries and users. While obtaining these relevance labels from real users is ideal, scaling such data collection is challenging. Consequently, third-party annotators are employed, but their inconsistent accuracy demands costly auditing, training, and monitoring. We propose an LLM-based modular classification pipeline that divides the relevance assessment task into multiple stages, each utilising different prompts and models of varying sizes and capabilities. Applied to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14296","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/2501.14296/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":"2026-07-05T10:04:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7XVDNfSEyKWgFLEkIYLy2Q9A6pZ55GVBAEzs1sNFOEoD/hR5y+lCrIXtJxI+ZMAgK0A5SuLC4LC8/P7P22kLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:03:06.409922Z"},"content_sha256":"9101eae739d3b3471c579522a5227e8a9b566d540c8f038e391afddc857c6541","schema_version":"1.0","event_id":"sha256:9101eae739d3b3471c579522a5227e8a9b566d540c8f038e391afddc857c6541"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6/bundle.json","state_url":"https://pith.science/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6/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":"2026-08-12T12:03:06Z","links":{"resolver":"https://pith.science/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6","bundle":"https://pith.science/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6/bundle.json","state":"https://pith.science/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HO4Y7P7EKGURSDHI5U7QAH4PW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HO4Y7P7EKGURSDHI5U7QAH4PW6","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":"1db2e00b2b0581a9fc514d7e72359db8675ffff0825fe219ea3fbe84c3549ce3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-24T07:33:39Z","title_canon_sha256":"873ca09e2975457edf44113f03e62bbaac37deaceb616d3bd192697002fdb9fb"},"schema_version":"1.0","source":{"id":"2501.14296","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14296","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14296v1","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14296","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"HO4Y7P7EKGUR","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"HO4Y7P7EKGURSDHI","created_at":"2026-07-05T10:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"HO4Y7P7E","created_at":"2026-07-05T10:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:9101eae739d3b3471c579522a5227e8a9b566d540c8f038e391afddc857c6541","target":"graph","created_at":"2026-07-05T10:04:48Z","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/2501.14296/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The effectiveness of search systems is evaluated using relevance labels that indicate the usefulness of documents for specific queries and users. While obtaining these relevance labels from real users is ideal, scaling such data collection is challenging. Consequently, third-party annotators are employed, but their inconsistent accuracy demands costly auditing, training, and monitoring. We propose an LLM-based modular classification pipeline that divides the relevance assessment task into multiple stages, each utilising different prompts and models of varying sizes and capabilities. Applied to","authors_text":"Danula Hettiachchi, Falk Scholer, Johanne R. Trippas, Julian A. Schnabel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-24T07:33:39Z","title":"Multi-stage Large Language Model Pipelines Can Outperform GPT-4o in Relevance Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14296","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":"sha256:98e3ac02603942b7004a2e83ec993df60d64b3249cf73a927a6b5f94db092416","target":"record","created_at":"2026-07-05T10:04:48Z","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":"1db2e00b2b0581a9fc514d7e72359db8675ffff0825fe219ea3fbe84c3549ce3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-24T07:33:39Z","title_canon_sha256":"873ca09e2975457edf44113f03e62bbaac37deaceb616d3bd192697002fdb9fb"},"schema_version":"1.0","source":{"id":"2501.14296","kind":"arxiv","version":1}},"canonical_sha256":"3bb98fbfe451a9190ce8ed3f001f8fb7969d7d5d75c282aa64581b93de2fd3d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bb98fbfe451a9190ce8ed3f001f8fb7969d7d5d75c282aa64581b93de2fd3d8","first_computed_at":"2026-07-05T10:04:48.273126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:04:48.273126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ynWAyNJZE7Usr50yxrw6x0pjbTCRlb/j849F56RfXXbyJqbJU5obyiKg59gXOMfxqGBa4zk2Zml4uHY4DNl0Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:04:48.273488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14296","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98e3ac02603942b7004a2e83ec993df60d64b3249cf73a927a6b5f94db092416","sha256:9101eae739d3b3471c579522a5227e8a9b566d540c8f038e391afddc857c6541"],"state_sha256":"4492980eb4f57035c7905066bdbaa50b9e3b36e0ca779726238293dc07605429"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+QY6HXCAEqmKVr/zXstGW9fw3chNTOoM4YZ5RWfG4jVNgII8YMXJoE/aw/atxyy7doYDPAoHlfGAZPka6ffzAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:03:06.419265Z","bundle_sha256":"843aa7cd80c810e72de217d3ac13b16c1ce90b639435ed7eae20e325dc56d69b"}}