{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TVA73HRMY4LDXVU53Q6HXSRLBZ","short_pith_number":"pith:TVA73HRM","canonical_record":{"source":{"id":"2502.15954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T21:36:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad7f9e253a9c8acf1917f1fc81d23cc340342ec9e79b8b066283ea2aa9156ef2","abstract_canon_sha256":"0f1e49bef8c47c1374635de5dc42a736d93faf0e22a12fd48fd98cdd4a664f81"},"schema_version":"1.0"},"canonical_sha256":"9d41fd9e2cc7163bd69ddc3c7bca2b0e5417cdb356df67d9583b09145fc65ae2","source":{"kind":"arxiv","id":"2502.15954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15954","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15954v1","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15954","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"TVA73HRMY4LD","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"TVA73HRMY4LDXVU5","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"TVA73HRM","created_at":"2026-07-05T10:18:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TVA73HRMY4LDXVU53Q6HXSRLBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.15954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T21:36:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad7f9e253a9c8acf1917f1fc81d23cc340342ec9e79b8b066283ea2aa9156ef2","abstract_canon_sha256":"0f1e49bef8c47c1374635de5dc42a736d93faf0e22a12fd48fd98cdd4a664f81"},"schema_version":"1.0"},"canonical_sha256":"9d41fd9e2cc7163bd69ddc3c7bca2b0e5417cdb356df67d9583b09145fc65ae2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:18.989490Z","signature_b64":"Tb4+uV15Gvsis/06lT67IlA80Rnqy3qsnHn0ifjhyfA52cxg/lgoujOBXUj9QsFH5KuIBGS/2+Xuac9xmiGvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d41fd9e2cc7163bd69ddc3c7bca2b0e5417cdb356df67d9583b09145fc65ae2","last_reissued_at":"2026-07-05T10:18:18.989009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:18.989009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.15954","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":"2026-07-05T10:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRFRzmh5iRP8GC3g38XR3CINGbNYgAkt8jNjGDpFVf8ILGEE/XPoTBMk5aGHHlkxUxda+aStgyR92aEET9u7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:13:40.761826Z"},"content_sha256":"122d9d40e70f9aebe51b3b3bcf9279072096d0fdd928ed5a38c523feb912226a","schema_version":"1.0","event_id":"sha256:122d9d40e70f9aebe51b3b3bcf9279072096d0fdd928ed5a38c523feb912226a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TVA73HRMY4LDXVU53Q6HXSRLBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMRAG: Multi-Mode Retrieval-Augmented Generation with Large Language Models for Biomedical In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiawen Deng, Jun Wang, Rui Zhang, Shuang Zhou, Zaifu Zhan","submitted_at":"2025-02-21T21:36:48Z","abstract_excerpt":"Objective: To optimize in-context learning in biomedical natural language processing by improving example selection. Methods: We introduce a novel multi-mode retrieval-augmented generation (MMRAG) framework, which integrates four retrieval strategies: (1) Random Mode, selecting examples arbitrarily; (2) Top Mode, retrieving the most relevant examples based on similarity; (3) Diversity Mode, ensuring variation in selected examples; and (4) Class Mode, selecting category-representative examples. This study evaluates MMRAG on three core biomedical NLP tasks: Named Entity Recognition (NER), Relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15954","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/2502.15954/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":"2026-07-05T10:18:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q8JWYfEijql0zgbxpPAdFbI2vRYIR4C8CXWX0DAP6SOTwgvLnr3K47UtiraAfSdtwgcx/T971AZXlpaxxfvdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:13:40.762329Z"},"content_sha256":"0c6a56c1c6b8df5c4949f8c5431118f5f3767e560d6b81e6142465add99d4159","schema_version":"1.0","event_id":"sha256:0c6a56c1c6b8df5c4949f8c5431118f5f3767e560d6b81e6142465add99d4159"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ/bundle.json","state_url":"https://pith.science/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ/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":"2026-08-05T00:13:40Z","links":{"resolver":"https://pith.science/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ","bundle":"https://pith.science/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ/bundle.json","state":"https://pith.science/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TVA73HRMY4LDXVU53Q6HXSRLBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TVA73HRMY4LDXVU53Q6HXSRLBZ","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":"0f1e49bef8c47c1374635de5dc42a736d93faf0e22a12fd48fd98cdd4a664f81","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T21:36:48Z","title_canon_sha256":"ad7f9e253a9c8acf1917f1fc81d23cc340342ec9e79b8b066283ea2aa9156ef2"},"schema_version":"1.0","source":{"id":"2502.15954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.15954","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.15954v1","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15954","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"pith_short_12","alias_value":"TVA73HRMY4LD","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"pith_short_16","alias_value":"TVA73HRMY4LDXVU5","created_at":"2026-07-05T10:18:18Z"},{"alias_kind":"pith_short_8","alias_value":"TVA73HRM","created_at":"2026-07-05T10:18:18Z"}],"graph_snapshots":[{"event_id":"sha256:0c6a56c1c6b8df5c4949f8c5431118f5f3767e560d6b81e6142465add99d4159","target":"graph","created_at":"2026-07-05T10:18:18Z","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/2502.15954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Objective: To optimize in-context learning in biomedical natural language processing by improving example selection. Methods: We introduce a novel multi-mode retrieval-augmented generation (MMRAG) framework, which integrates four retrieval strategies: (1) Random Mode, selecting examples arbitrarily; (2) Top Mode, retrieving the most relevant examples based on similarity; (3) Diversity Mode, ensuring variation in selected examples; and (4) Class Mode, selecting category-representative examples. This study evaluates MMRAG on three core biomedical NLP tasks: Named Entity Recognition (NER), Relati","authors_text":"Jiawen Deng, Jun Wang, Rui Zhang, Shuang Zhou, Zaifu Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T21:36:48Z","title":"MMRAG: Multi-Mode Retrieval-Augmented Generation with Large Language Models for Biomedical In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15954","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":"sha256:122d9d40e70f9aebe51b3b3bcf9279072096d0fdd928ed5a38c523feb912226a","target":"record","created_at":"2026-07-05T10:18:18Z","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":"0f1e49bef8c47c1374635de5dc42a736d93faf0e22a12fd48fd98cdd4a664f81","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-21T21:36:48Z","title_canon_sha256":"ad7f9e253a9c8acf1917f1fc81d23cc340342ec9e79b8b066283ea2aa9156ef2"},"schema_version":"1.0","source":{"id":"2502.15954","kind":"arxiv","version":1}},"canonical_sha256":"9d41fd9e2cc7163bd69ddc3c7bca2b0e5417cdb356df67d9583b09145fc65ae2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d41fd9e2cc7163bd69ddc3c7bca2b0e5417cdb356df67d9583b09145fc65ae2","first_computed_at":"2026-07-05T10:18:18.989009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:18.989009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tb4+uV15Gvsis/06lT67IlA80Rnqy3qsnHn0ifjhyfA52cxg/lgoujOBXUj9QsFH5KuIBGS/2+Xuac9xmiGvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:18.989490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.15954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:122d9d40e70f9aebe51b3b3bcf9279072096d0fdd928ed5a38c523feb912226a","sha256:0c6a56c1c6b8df5c4949f8c5431118f5f3767e560d6b81e6142465add99d4159"],"state_sha256":"ba2c138187cea20528d21001e7174da04ecc891aacdb444f8f13127e78b1847c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQrrkouxkTIA2nOxmFOobnRLoF/vDdptMStAQ1nPLSPicYLy23hApTXZW0S+GMzaUcVh6vbckrTY5f/HmpUhDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:13:40.766026Z","bundle_sha256":"1f12e0b138a25af3c8fdcaa7fee7cb5a1d666ed4dd4026c6531387a718e2607b"}}