{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QXHM4JZ2OJH7FQW53FDIASOSCF","short_pith_number":"pith:QXHM4JZ2","schema_version":"1.0","canonical_sha256":"85cece273a724ff2c2ddd9468049d2117fe1525ff367e735f4a9380ad1e8bb9d","source":{"kind":"arxiv","id":"2408.11729","version":2},"attestation_state":"computed","paper":{"title":"LLM4VV: Exploring LLM-as-a-Judge for Validation and Verification Testsuites","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aaron Jarmusch, Christian Munley, Jay Patel, Sunita Chandrasekaran, Zachariah Sollenberger","submitted_at":"2024-08-21T15:54:17Z","abstract_excerpt":"Large Language Models (LLM) are evolving and have significantly revolutionized the landscape of software development. If used well, they can significantly accelerate the software development cycle. At the same time, the community is very cautious of the models being trained on biased or sensitive data, which can lead to biased outputs along with the inadvertent release of confidential information. Additionally, the carbon footprints and the un-explainability of these black box models continue to raise questions about the usability of LLMs.\n  With the abundance of opportunities LLMs have to off"},"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":"2408.11729","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-08-21T15:54:17Z","cross_cats_sorted":[],"title_canon_sha256":"5dd47807ecdb39dc08779b3422be8a1c592688cd5091bb85ad02bc8f5e482111","abstract_canon_sha256":"9dfdf1b76818bbf26700ae6258cf38af9e626c893f531af1604c4473b58604ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:24.242925Z","signature_b64":"nf2Km9dRJdHowPjahTUrAUeNPHa/diddNven3vsdqS0+H/cGkLZAFdiYL9FF+61rnw0fb/n6yBsUwCiMIjdsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85cece273a724ff2c2ddd9468049d2117fe1525ff367e735f4a9380ad1e8bb9d","last_reissued_at":"2026-07-05T09:02:24.242242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:24.242242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM4VV: Exploring LLM-as-a-Judge for Validation and Verification Testsuites","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Aaron Jarmusch, Christian Munley, Jay Patel, Sunita Chandrasekaran, Zachariah Sollenberger","submitted_at":"2024-08-21T15:54:17Z","abstract_excerpt":"Large Language Models (LLM) are evolving and have significantly revolutionized the landscape of software development. If used well, they can significantly accelerate the software development cycle. At the same time, the community is very cautious of the models being trained on biased or sensitive data, which can lead to biased outputs along with the inadvertent release of confidential information. Additionally, the carbon footprints and the un-explainability of these black box models continue to raise questions about the usability of LLMs.\n  With the abundance of opportunities LLMs have to off"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11729","kind":"arxiv","version":2},"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/2408.11729/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":"2408.11729","created_at":"2026-07-05T09:02:24.242326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.11729v2","created_at":"2026-07-05T09:02:24.242326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11729","created_at":"2026-07-05T09:02:24.242326+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXHM4JZ2OJH7","created_at":"2026-07-05T09:02:24.242326+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXHM4JZ2OJH7FQW5","created_at":"2026-07-05T09:02:24.242326+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXHM4JZ2","created_at":"2026-07-05T09:02:24.242326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF","json":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF.json","graph_json":"https://pith.science/api/pith-number/QXHM4JZ2OJH7FQW53FDIASOSCF/graph.json","events_json":"https://pith.science/api/pith-number/QXHM4JZ2OJH7FQW53FDIASOSCF/events.json","paper":"https://pith.science/paper/QXHM4JZ2"},"agent_actions":{"view_html":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF","download_json":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF.json","view_paper":"https://pith.science/paper/QXHM4JZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.11729&json=true","fetch_graph":"https://pith.science/api/pith-number/QXHM4JZ2OJH7FQW53FDIASOSCF/graph.json","fetch_events":"https://pith.science/api/pith-number/QXHM4JZ2OJH7FQW53FDIASOSCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF/action/storage_attestation","attest_author":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF/action/author_attestation","sign_citation":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF/action/citation_signature","submit_replication":"https://pith.science/pith/QXHM4JZ2OJH7FQW53FDIASOSCF/action/replication_record"}},"created_at":"2026-07-05T09:02:24.242326+00:00","updated_at":"2026-07-05T09:02:24.242326+00:00"}