{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BHGHSF3RU7TFHJP5BFR7VWOTN7","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":"69a7c8a89446e0d461770277837e777d2787a21290fbc75f44d686dd0257268a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-07T18:43:57Z","title_canon_sha256":"3d164c52f36f2b68c8fa1e8f4a5a80f26a695b27ae977156b5a69b3ba8d8f27a"},"schema_version":"1.0","source":{"id":"2505.04732","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04732","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04732v1","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04732","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"pith_short_12","alias_value":"BHGHSF3RU7TF","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"pith_short_16","alias_value":"BHGHSF3RU7TFHJP5","created_at":"2026-07-05T11:00:12Z"},{"alias_kind":"pith_short_8","alias_value":"BHGHSF3R","created_at":"2026-07-05T11:00:12Z"}],"graph_snapshots":[{"event_id":"sha256:f99889d5cab8f9262859149156f371d3781c9e748b53872c76d21b9d132c3538","target":"graph","created_at":"2026-07-05T11:00:12Z","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/2505.04732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Query-By-Document (QBD) problem is an information retrieval problem where the query is a document, and the retrieved candidates are documents that match the query document, often in a domain or query specific manner. This can be crucial for tasks such as patent matching, legal or compliance case retrieval, and academic literature review. Existing retrieval methods, including keyword search and document embeddings, can be optimized with domain-specific datasets to improve QBD search performance. However, creating these domain-specific datasets is often costly and time-consuming. Our work in","authors_text":"Sriram Gopalakrishnan, Sunandita Patra","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-07T18:43:57Z","title":"QBD-RankedDataGen: Generating Custom Ranked Datasets for Improving Query-By-Document Search Using LLM-Reranking with Reduced Human Effort"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04732","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:affde0e115a5c1fe35ab83756d137df7ba0f33c6aaef5d9ee1bab203eeacec9f","target":"record","created_at":"2026-07-05T11:00:12Z","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":"69a7c8a89446e0d461770277837e777d2787a21290fbc75f44d686dd0257268a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-07T18:43:57Z","title_canon_sha256":"3d164c52f36f2b68c8fa1e8f4a5a80f26a695b27ae977156b5a69b3ba8d8f27a"},"schema_version":"1.0","source":{"id":"2505.04732","kind":"arxiv","version":1}},"canonical_sha256":"09cc791771a7e653a5fd0963fad9d36fd6dd26acce6d9882d955ac42f4155ba8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09cc791771a7e653a5fd0963fad9d36fd6dd26acce6d9882d955ac42f4155ba8","first_computed_at":"2026-07-05T11:00:12.895997Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:12.895997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3JYL/0iwpDAddu+79cvYe9f5C/Gbsojg9TMNsFRdQwyI0OweDdPMts8PyAuqa/YxiHQQHEFQT+JJhVn046CjDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:12.896484Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04732","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:affde0e115a5c1fe35ab83756d137df7ba0f33c6aaef5d9ee1bab203eeacec9f","sha256:f99889d5cab8f9262859149156f371d3781c9e748b53872c76d21b9d132c3538"],"state_sha256":"e8280c3969db708bcb6800f22063a44cef7b08ab10996df3def05474cde6971a"}