{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NMSB67DWLZ5WUU7LHECMKLTQNU","short_pith_number":"pith:NMSB67DW","schema_version":"1.0","canonical_sha256":"6b241f7c765e7b6a53eb3904c52e706d15da2ca0945470c2f943ffac6a9944a6","source":{"kind":"arxiv","id":"2606.06754","version":1},"attestation_state":"computed","paper":{"title":"MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MA","authors_text":"Ali Keramati, Mark Warschauer, Sharad Mehrotra, Shiyuan Zhou","submitted_at":"2026-06-04T22:32:47Z","abstract_excerpt":"We present MADRAG, a training-free framework for analytic essay scoring that combines multi-agent reasoning with retrieval-augmented grounding. Unlike standard LLM-as-judge approaches, which are prone to bias and unstable scoring, MADRAG decomposes evaluation into an interactive process: an Advocate identifies strengths, a Skeptic critiques weaknesses, and a Judge aggregates their arguments into a final score. Crucially, the Judge is augmented with rubric-aligned exemplar retrieval, enabling calibration through comparison with scored examples. Our results show that MADRAG significantly outperf"},"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":"2606.06754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-06-04T22:32:47Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0c80ca247038e80422a9463e98520fae328073949f9f42a2826917a889d672ab","abstract_canon_sha256":"03fc2b5c3806affee25d2cdbf555ce8190602d5239a9eb32d0a32d6ff90c5bfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:26.670878Z","signature_b64":"bM1aAFUZUU/gYxQ9RPJ7zHFEMRlQsaFqowt47IWK2wgGf1gt3/JIdBYLybC0Khm+BrjWBRVb6KJbexA40twnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b241f7c765e7b6a53eb3904c52e706d15da2ca0945470c2f943ffac6a9944a6","last_reissued_at":"2026-06-08T01:04:26.670125Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:26.670125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MADRAG: Multi-Agent Debate with Retrieval-Augmented Generation for Training-Free Analytic Essay Scoring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.MA","authors_text":"Ali Keramati, Mark Warschauer, Sharad Mehrotra, Shiyuan Zhou","submitted_at":"2026-06-04T22:32:47Z","abstract_excerpt":"We present MADRAG, a training-free framework for analytic essay scoring that combines multi-agent reasoning with retrieval-augmented grounding. Unlike standard LLM-as-judge approaches, which are prone to bias and unstable scoring, MADRAG decomposes evaluation into an interactive process: an Advocate identifies strengths, a Skeptic critiques weaknesses, and a Judge aggregates their arguments into a final score. Crucially, the Judge is augmented with rubric-aligned exemplar retrieval, enabling calibration through comparison with scored examples. Our results show that MADRAG significantly outperf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06754","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/2606.06754/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":"2606.06754","created_at":"2026-06-08T01:04:26.670254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06754v1","created_at":"2026-06-08T01:04:26.670254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06754","created_at":"2026-06-08T01:04:26.670254+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMSB67DWLZ5W","created_at":"2026-06-08T01:04:26.670254+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMSB67DWLZ5WUU7L","created_at":"2026-06-08T01:04:26.670254+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMSB67DW","created_at":"2026-06-08T01:04:26.670254+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/NMSB67DWLZ5WUU7LHECMKLTQNU","json":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU.json","graph_json":"https://pith.science/api/pith-number/NMSB67DWLZ5WUU7LHECMKLTQNU/graph.json","events_json":"https://pith.science/api/pith-number/NMSB67DWLZ5WUU7LHECMKLTQNU/events.json","paper":"https://pith.science/paper/NMSB67DW"},"agent_actions":{"view_html":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU","download_json":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU.json","view_paper":"https://pith.science/paper/NMSB67DW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06754&json=true","fetch_graph":"https://pith.science/api/pith-number/NMSB67DWLZ5WUU7LHECMKLTQNU/graph.json","fetch_events":"https://pith.science/api/pith-number/NMSB67DWLZ5WUU7LHECMKLTQNU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU/action/storage_attestation","attest_author":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU/action/author_attestation","sign_citation":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU/action/citation_signature","submit_replication":"https://pith.science/pith/NMSB67DWLZ5WUU7LHECMKLTQNU/action/replication_record"}},"created_at":"2026-06-08T01:04:26.670254+00:00","updated_at":"2026-06-08T01:04:26.670254+00:00"}