{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:37H4ZDH5SHWXXR6V57ELVOBHCW","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":"66d173ae35675a39a7dc7efd173a64832638b0f15da5918b646ff10ca3fa1870","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-25T21:25:06Z","title_canon_sha256":"6db1a787b9c444b32299a58591d7c9e1ad6f70aec935da3aac3801e3b8a54d64"},"schema_version":"1.0","source":{"id":"2402.16200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16200","created_at":"2026-07-05T10:42:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16200v2","created_at":"2026-07-05T10:42:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16200","created_at":"2026-07-05T10:42:57Z"},{"alias_kind":"pith_short_12","alias_value":"37H4ZDH5SHWX","created_at":"2026-07-05T10:42:57Z"},{"alias_kind":"pith_short_16","alias_value":"37H4ZDH5SHWXXR6V","created_at":"2026-07-05T10:42:57Z"},{"alias_kind":"pith_short_8","alias_value":"37H4ZDH5","created_at":"2026-07-05T10:42:57Z"}],"graph_snapshots":[{"event_id":"sha256:d0162893bd27805d2ee1fbe4fbabe2dfa89a3b9df5f387d5a17c45a4cd3a7d8e","target":"graph","created_at":"2026-07-05T10:42:57Z","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/2402.16200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effective information retrieval (IR) in settings with limited training data, particularly for complex queries, remains a challenging task. This paper introduces IR2, Information Regularization for Information Retrieval, a technique for reducing overfitting during synthetic data generation. This approach, representing a novel application of regularization techniques in synthetic data creation for IR, is tested on three recent IR tasks characterized by complex queries: DORIS-MAE, ArguAna, and WhatsThatBook. Experimental results indicate that our regularization techniques not only outperform prev","authors_text":"Jianyou Wang, Kaicheng Wang, Leon Bergen, Ramamohan Paturi, Weili Cao, Xiaoyue Wang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-25T21:25:06Z","title":"IR2: Information Regularization for Information Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16200","kind":"arxiv","version":2},"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:d33d5dc26bebf89ff65f92b5fd851097ee9fc19404991096c4eba1150f2cf24f","target":"record","created_at":"2026-07-05T10:42:57Z","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":"66d173ae35675a39a7dc7efd173a64832638b0f15da5918b646ff10ca3fa1870","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-02-25T21:25:06Z","title_canon_sha256":"6db1a787b9c444b32299a58591d7c9e1ad6f70aec935da3aac3801e3b8a54d64"},"schema_version":"1.0","source":{"id":"2402.16200","kind":"arxiv","version":2}},"canonical_sha256":"dfcfcc8cfd91ed7bc7d5efc8bab82715b52b2d08445622faf3f96815cbce50c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfcfcc8cfd91ed7bc7d5efc8bab82715b52b2d08445622faf3f96815cbce50c6","first_computed_at":"2026-07-05T10:42:57.501151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:57.501151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xPrANuUc7+0ifgVk2RT0pfAUf4Ttbb45sIJgG+UtMnHvFxJfjyePCk84mJcVFSBeJSjfJNReWZyEH+B9QY9UBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:57.501627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d33d5dc26bebf89ff65f92b5fd851097ee9fc19404991096c4eba1150f2cf24f","sha256:d0162893bd27805d2ee1fbe4fbabe2dfa89a3b9df5f387d5a17c45a4cd3a7d8e"],"state_sha256":"183882c30cb432c8ef6c3465ad04ea6959da6194b183744eab7f7513171b76bd"}