{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:55WBIQLTONUGDWFGBYJUVMHBRN","short_pith_number":"pith:55WBIQLT","schema_version":"1.0","canonical_sha256":"ef6c144173736861d8a60e134ab0e18b65ac0c9b38a4ac853788e82871542d3e","source":{"kind":"arxiv","id":"2406.02524","version":5},"attestation_state":"computed","paper":{"title":"CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ales Kubicek, Eric Schreiber, Hubert Niewiadomski, Lorenzo Paleari, Maciej Besta, Marcin Copik, Patrick Iff, Piotr Nyczyk, Robert Gerstenberger, Tanja Srindran, Tomasz Lehmann, Torsten Hoefler","submitted_at":"2024-06-04T17:42:21Z","abstract_excerpt":"Large Language Models (LLMs) are transforming a wide range of domains, yet verifying their outputs remains a significant challenge, especially for complex open-ended tasks such as consolidation, summarization, and knowledge extraction. To address this, we introduce CheckEmbed (CE): a simple, scalable, and accurate verification method. CE reduces each LLM answer to a single embedding vector using powerful modern embedding LLM models like SFR-Embedding-Mistral. Prior methods such as BERTScore and SelfCheckGPT relied on weaker encoders like BERT, forcing them to operate at token or sentence granu"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.02524","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-04T17:42:21Z","cross_cats_sorted":[],"title_canon_sha256":"1dad41f37453a3b9c74ca57382b755ae874d7794f5c185c7f05e554ffb71dd40","abstract_canon_sha256":"dba08bd813952b4e3f7f8edabbe79d6b95df80ef571f8fe38f631cd74454d0fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:42.129359Z","signature_b64":"a5/InUJHGOd8ioN8eLUcYvJvfBi0yWT/4ENvymJV80gQ76Qhfw8X2iUrhOx5uOL6F7MBa8B42ald7ERVQZe7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef6c144173736861d8a60e134ab0e18b65ac0c9b38a4ac853788e82871542d3e","last_reissued_at":"2026-07-05T11:34:42.128899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:42.128899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ales Kubicek, Eric Schreiber, Hubert Niewiadomski, Lorenzo Paleari, Maciej Besta, Marcin Copik, Patrick Iff, Piotr Nyczyk, Robert Gerstenberger, Tanja Srindran, Tomasz Lehmann, Torsten Hoefler","submitted_at":"2024-06-04T17:42:21Z","abstract_excerpt":"Large Language Models (LLMs) are transforming a wide range of domains, yet verifying their outputs remains a significant challenge, especially for complex open-ended tasks such as consolidation, summarization, and knowledge extraction. To address this, we introduce CheckEmbed (CE): a simple, scalable, and accurate verification method. CE reduces each LLM answer to a single embedding vector using powerful modern embedding LLM models like SFR-Embedding-Mistral. Prior methods such as BERTScore and SelfCheckGPT relied on weaker encoders like BERT, forcing them to operate at token or sentence granu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02524","kind":"arxiv","version":5},"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/2406.02524/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2406.02524","created_at":"2026-07-05T11:34:42.128961+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02524v5","created_at":"2026-07-05T11:34:42.128961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02524","created_at":"2026-07-05T11:34:42.128961+00:00"},{"alias_kind":"pith_short_12","alias_value":"55WBIQLTONUG","created_at":"2026-07-05T11:34:42.128961+00:00"},{"alias_kind":"pith_short_16","alias_value":"55WBIQLTONUGDWFG","created_at":"2026-07-05T11:34:42.128961+00:00"},{"alias_kind":"pith_short_8","alias_value":"55WBIQLT","created_at":"2026-07-05T11:34:42.128961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11223","citing_title":"Reasoning Language Models: A Blueprint","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN","json":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN.json","graph_json":"https://pith.science/api/pith-number/55WBIQLTONUGDWFGBYJUVMHBRN/graph.json","events_json":"https://pith.science/api/pith-number/55WBIQLTONUGDWFGBYJUVMHBRN/events.json","paper":"https://pith.science/paper/55WBIQLT"},"agent_actions":{"view_html":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN","download_json":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN.json","view_paper":"https://pith.science/paper/55WBIQLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02524&json=true","fetch_graph":"https://pith.science/api/pith-number/55WBIQLTONUGDWFGBYJUVMHBRN/graph.json","fetch_events":"https://pith.science/api/pith-number/55WBIQLTONUGDWFGBYJUVMHBRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN/action/storage_attestation","attest_author":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN/action/author_attestation","sign_citation":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN/action/citation_signature","submit_replication":"https://pith.science/pith/55WBIQLTONUGDWFGBYJUVMHBRN/action/replication_record"}},"created_at":"2026-07-05T11:34:42.128961+00:00","updated_at":"2026-07-05T11:34:42.128961+00:00"}