{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GY4FKLXFRA3PH3LJZEJS6WAGBP","short_pith_number":"pith:GY4FKLXF","canonical_record":{"source":{"id":"2605.20684","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T04:23:06Z","cross_cats_sorted":[],"title_canon_sha256":"3a9bb439a4c51330fec51893d8a65d4b314ad87c53546ea0842bce2aab9b54ec","abstract_canon_sha256":"71d05cefeb49271db19bc9f28a2be7047ab44f417276dfc3c5bcb38e7d8245fe"},"schema_version":"1.0"},"canonical_sha256":"3638552ee58836f3ed69c9132f58060bf026c9d1eb9ceb6a8d9ab7de4945335b","source":{"kind":"arxiv","id":"2605.20684","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20684","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20684v1","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20684","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"GY4FKLXFRA3P","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"GY4FKLXFRA3PH3LJ","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"GY4FKLXF","created_at":"2026-05-21T01:04:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GY4FKLXFRA3PH3LJZEJS6WAGBP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20684","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T04:23:06Z","cross_cats_sorted":[],"title_canon_sha256":"3a9bb439a4c51330fec51893d8a65d4b314ad87c53546ea0842bce2aab9b54ec","abstract_canon_sha256":"71d05cefeb49271db19bc9f28a2be7047ab44f417276dfc3c5bcb38e7d8245fe"},"schema_version":"1.0"},"canonical_sha256":"3638552ee58836f3ed69c9132f58060bf026c9d1eb9ceb6a8d9ab7de4945335b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:49.084309Z","signature_b64":"3Sb1TtqMXmUo8woCW9UtjqHUnuO6kUHa25ZJo1BdeonSNP8BlI1LpyozCfJc3tXktjlhTUlgl7X5Yo5hda8eAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3638552ee58836f3ed69c9132f58060bf026c9d1eb9ceb6a8d9ab7de4945335b","last_reissued_at":"2026-05-21T01:04:49.083728Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:49.083728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20684","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NUjFMBnCrcf6mZ1ZnSJJ4ZEHWv89OCN9nptt7eLWUhcu196i3Mo/ytfMR3LYLOdEfoEGu86tX52WeXpMuYstCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:48:15.881445Z"},"content_sha256":"eafae7aa06f4581e2a732fc540ef86927a5b5ef2d5520221e37e9c5f254d26b1","schema_version":"1.0","event_id":"sha256:eafae7aa06f4581e2a732fc540ef86927a5b5ef2d5520221e37e9c5f254d26b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GY4FKLXFRA3PH3LJZEJS6WAGBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ezekiel Tee Kongquan, Kelvin Heng, Kenneth Zhu Ke, Linus Ng Junjia, Zhao Jing Yuan","submitted_at":"2026-05-20T04:23:06Z","abstract_excerpt":"Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG) pipelines optimize for semantic similarity, which frequently surfaces passages that are topically related but lack decision utility, a problem we term the similarity-utility gap. We propose a two-phase non-parametric retrieval architecture that separates high-recall candidate retrieval from high-precision utility ranking. The first phase combines lexical and dense multilingual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20684","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/2605.20684/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-21T01:04:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mz4CuZetRrz+C6UaoT7Ya00MH2tRwma7dlDTavpoPBCwcOHXrRwzZ61CQhl9KKrN/mNjP9HsaylEdVbgifK3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:48:15.882180Z"},"content_sha256":"44ecb5842ec457c6d8d7be48967dd739d6dcf2a67f8eabd6844c6d239d825a12","schema_version":"1.0","event_id":"sha256:44ecb5842ec457c6d8d7be48967dd739d6dcf2a67f8eabd6844c6d239d825a12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP/bundle.json","state_url":"https://pith.science/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T23:48:15Z","links":{"resolver":"https://pith.science/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP","bundle":"https://pith.science/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP/bundle.json","state":"https://pith.science/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GY4FKLXFRA3PH3LJZEJS6WAGBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GY4FKLXFRA3PH3LJZEJS6WAGBP","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":"71d05cefeb49271db19bc9f28a2be7047ab44f417276dfc3c5bcb38e7d8245fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T04:23:06Z","title_canon_sha256":"3a9bb439a4c51330fec51893d8a65d4b314ad87c53546ea0842bce2aab9b54ec"},"schema_version":"1.0","source":{"id":"2605.20684","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20684","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20684v1","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20684","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"GY4FKLXFRA3P","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"GY4FKLXFRA3PH3LJ","created_at":"2026-05-21T01:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"GY4FKLXF","created_at":"2026-05-21T01:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:44ecb5842ec457c6d8d7be48967dd739d6dcf2a67f8eabd6844c6d239d825a12","target":"graph","created_at":"2026-05-21T01:04:49Z","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/2605.20684/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG) pipelines optimize for semantic similarity, which frequently surfaces passages that are topically related but lack decision utility, a problem we term the similarity-utility gap. We propose a two-phase non-parametric retrieval architecture that separates high-recall candidate retrieval from high-precision utility ranking. The first phase combines lexical and dense multilingual","authors_text":"Ezekiel Tee Kongquan, Kelvin Heng, Kenneth Zhu Ke, Linus Ng Junjia, Zhao Jing Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T04:23:06Z","title":"Beyond Semantic Similarity: A Two-Phase Non-Parametric Retrieval Workflow for Corporate Credit Underwriting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20684","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:eafae7aa06f4581e2a732fc540ef86927a5b5ef2d5520221e37e9c5f254d26b1","target":"record","created_at":"2026-05-21T01:04:49Z","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":"71d05cefeb49271db19bc9f28a2be7047ab44f417276dfc3c5bcb38e7d8245fe","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T04:23:06Z","title_canon_sha256":"3a9bb439a4c51330fec51893d8a65d4b314ad87c53546ea0842bce2aab9b54ec"},"schema_version":"1.0","source":{"id":"2605.20684","kind":"arxiv","version":1}},"canonical_sha256":"3638552ee58836f3ed69c9132f58060bf026c9d1eb9ceb6a8d9ab7de4945335b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3638552ee58836f3ed69c9132f58060bf026c9d1eb9ceb6a8d9ab7de4945335b","first_computed_at":"2026-05-21T01:04:49.083728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:49.083728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3Sb1TtqMXmUo8woCW9UtjqHUnuO6kUHa25ZJo1BdeonSNP8BlI1LpyozCfJc3tXktjlhTUlgl7X5Yo5hda8eAw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:49.084309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20684","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eafae7aa06f4581e2a732fc540ef86927a5b5ef2d5520221e37e9c5f254d26b1","sha256:44ecb5842ec457c6d8d7be48967dd739d6dcf2a67f8eabd6844c6d239d825a12"],"state_sha256":"77b5083a96eeecfe1d9bcda84e83e4f8fffb0efa7950c281aea4c268fb4ebeac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3yUgiXcehMiNHi+AEKE/LPGHjUkYqQVHrLlLmugodAIK1wJUXgUVuKBJ36n8RLpSO0lTzHjf7XtW9d7drKNLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:48:15.885789Z","bundle_sha256":"7fd357fd25a09be8ce43d5d15cc8847f289373e34affabe0fab95450b1089d18"}}