{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MIY7RWZ24DGUFBYOL2MCO4KE73","short_pith_number":"pith:MIY7RWZ2","canonical_record":{"source":{"id":"2404.18443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T05:40:08Z","cross_cats_sorted":["cs.AI","cs.IR","q-bio.QM"],"title_canon_sha256":"91ceb568ede924767fcba9bc52c215a9b01c0041b0f8a6538e5e2a5aad95473f","abstract_canon_sha256":"edfbd581f77ef2747a4d9ddbf1f4bb7b4bec2cfb6464cffece9cc8d709933b1d"},"schema_version":"1.0"},"canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","source":{"kind":"arxiv","id":"2404.18443","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18443","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18443v2","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18443","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"pith_short_12","alias_value":"MIY7RWZ24DGU","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"pith_short_16","alias_value":"MIY7RWZ24DGUFBYO","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"pith_short_8","alias_value":"MIY7RWZ2","created_at":"2026-07-05T09:15:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MIY7RWZ24DGUFBYOL2MCO4KE73","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T05:40:08Z","cross_cats_sorted":["cs.AI","cs.IR","q-bio.QM"],"title_canon_sha256":"91ceb568ede924767fcba9bc52c215a9b01c0041b0f8a6538e5e2a5aad95473f","abstract_canon_sha256":"edfbd581f77ef2747a4d9ddbf1f4bb7b4bec2cfb6464cffece9cc8d709933b1d"},"schema_version":"1.0"},"canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:31.861496Z","signature_b64":"LRjGXAqGEkXuFAIZBuuFbs9UPLeoTExOtdO6wumgHemj3O+ea9O5bUbdxFkjJIoKqdUM58qKxJl/S3mCUQxpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","last_reissued_at":"2026-07-05T09:15:31.860976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:31.860976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18443","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPuWsYjJKsq9krFYWoAB8LlnTfyET7iwiW1xCuuOF7Ec+8OXGCSB+BfpDt2qrKmp2brO8tGI4dfQMsWQFWG6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:16:42.515875Z"},"content_sha256":"f88f826b9bfb50bdb525808fb467d038b92f7082cf46501599a6b475cc75d67b","schema_version":"1.0","event_id":"sha256:f88f826b9bfb50bdb525808fb467d038b92f7082cf46501599a6b475cc75d67b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MIY7RWZ24DGUFBYOL2MCO4KE73","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Carl Yang, Chao Zhang, Joyce C. Ho, May D. Wang, Ran Xu, Wenqi Shi, Yanqiao Zhu, Yuchen Zhuang, Yue Yu","submitted_at":"2024-04-29T05:40:08Z","abstract_excerpt":"Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We present BMRetriever, a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedical corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs. Experiments on 5 biomedical tasks across 11 datasets verify BMRetriever's efficacy on various biomedical applications. BM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18443","kind":"arxiv","version":2},"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/2404.18443/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":"2026-07-05T09:15:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W4fyFFQbWbA+MtQ++g9GjwBfN2Zxm24cibPWkZOA4rSnywv2t1t4tQOHz50gTnegiIbznBF043dxH2Jo/sTLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T11:16:42.517159Z"},"content_sha256":"d8db913e3966573a9fbe0d06fae134029cae493d034785a9b4739a64594361c3","schema_version":"1.0","event_id":"sha256:d8db913e3966573a9fbe0d06fae134029cae493d034785a9b4739a64594361c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/bundle.json","state_url":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/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":"2026-08-07T11:16:42Z","links":{"resolver":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73","bundle":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/bundle.json","state":"https://pith.science/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIY7RWZ24DGUFBYOL2MCO4KE73/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MIY7RWZ24DGUFBYOL2MCO4KE73","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":"edfbd581f77ef2747a4d9ddbf1f4bb7b4bec2cfb6464cffece9cc8d709933b1d","cross_cats_sorted":["cs.AI","cs.IR","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T05:40:08Z","title_canon_sha256":"91ceb568ede924767fcba9bc52c215a9b01c0041b0f8a6538e5e2a5aad95473f"},"schema_version":"1.0","source":{"id":"2404.18443","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18443","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18443v2","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18443","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"pith_short_12","alias_value":"MIY7RWZ24DGU","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"pith_short_16","alias_value":"MIY7RWZ24DGUFBYO","created_at":"2026-07-05T09:15:31Z"},{"alias_kind":"pith_short_8","alias_value":"MIY7RWZ2","created_at":"2026-07-05T09:15:31Z"}],"graph_snapshots":[{"event_id":"sha256:d8db913e3966573a9fbe0d06fae134029cae493d034785a9b4739a64594361c3","target":"graph","created_at":"2026-07-05T09:15:31Z","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/2404.18443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Developing effective biomedical retrieval models is important for excelling at knowledge-intensive biomedical tasks but still challenging due to the deficiency of sufficient publicly annotated biomedical data and computational resources. We present BMRetriever, a series of dense retrievers for enhancing biomedical retrieval via unsupervised pre-training on large biomedical corpora, followed by instruction fine-tuning on a combination of labeled datasets and synthetic pairs. Experiments on 5 biomedical tasks across 11 datasets verify BMRetriever's efficacy on various biomedical applications. BM","authors_text":"Carl Yang, Chao Zhang, Joyce C. Ho, May D. Wang, Ran Xu, Wenqi Shi, Yanqiao Zhu, Yuchen Zhuang, Yue Yu","cross_cats":["cs.AI","cs.IR","q-bio.QM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T05:40:08Z","title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18443","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:f88f826b9bfb50bdb525808fb467d038b92f7082cf46501599a6b475cc75d67b","target":"record","created_at":"2026-07-05T09:15:31Z","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":"edfbd581f77ef2747a4d9ddbf1f4bb7b4bec2cfb6464cffece9cc8d709933b1d","cross_cats_sorted":["cs.AI","cs.IR","q-bio.QM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T05:40:08Z","title_canon_sha256":"91ceb568ede924767fcba9bc52c215a9b01c0041b0f8a6538e5e2a5aad95473f"},"schema_version":"1.0","source":{"id":"2404.18443","kind":"arxiv","version":2}},"canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6231f8db3ae0cd42870e5e98277144feff50bcb55ddefe0e4503b1232cabfeb8","first_computed_at":"2026-07-05T09:15:31.860976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:31.860976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRjGXAqGEkXuFAIZBuuFbs9UPLeoTExOtdO6wumgHemj3O+ea9O5bUbdxFkjJIoKqdUM58qKxJl/S3mCUQxpDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:31.861496Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18443","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f88f826b9bfb50bdb525808fb467d038b92f7082cf46501599a6b475cc75d67b","sha256:d8db913e3966573a9fbe0d06fae134029cae493d034785a9b4739a64594361c3"],"state_sha256":"bab5ab64eb89bb7b9f3c385f33b2dd523f959b6655885924d8b3b6a6793b2d64"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ewEEqePtwojYfn8+nwmbX/Ph7BluwBELRlb9wD/CvrDgWjD8lTI3Nxld/subolvlUYwY3Ger4ydQ9OhLox+XAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T11:16:42.528642Z","bundle_sha256":"38d8ffb19c343550840ce4a6e20a4f83a0dd717b6f409ae8ff1f1d9dbdb75a58"}}