{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BCVSN37IPEYKZOYPNKDIRWLZ6Q","short_pith_number":"pith:BCVSN37I","canonical_record":{"source":{"id":"2503.23673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"f983aa4975a21cd5e73c18c3877928580513a0990af8e79711f851c65137a279","abstract_canon_sha256":"d4833e0cf95c0631387fa5a26d973339a393498a8e30cd0f1dae024f61236a60"},"schema_version":"1.0"},"canonical_sha256":"08ab26efe87930acbb0f6a8688d979f40db8327347323dcb3a489b06879bb6a5","source":{"kind":"arxiv","id":"2503.23673","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23673","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23673v1","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23673","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"BCVSN37IPEYK","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"BCVSN37IPEYKZOYP","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"BCVSN37I","created_at":"2026-07-05T10:41:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BCVSN37IPEYKZOYPNKDIRWLZ6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23673","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:36:30Z","cross_cats_sorted":[],"title_canon_sha256":"f983aa4975a21cd5e73c18c3877928580513a0990af8e79711f851c65137a279","abstract_canon_sha256":"d4833e0cf95c0631387fa5a26d973339a393498a8e30cd0f1dae024f61236a60"},"schema_version":"1.0"},"canonical_sha256":"08ab26efe87930acbb0f6a8688d979f40db8327347323dcb3a489b06879bb6a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:57.389077Z","signature_b64":"CCfGorDHxJvduoIXihRkLKV81Zv+oLFZIdYZ6Xfgj9h0t7Szmze8BhZiI+YtT5O+LX7mT85L1az3M0b6D0G3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08ab26efe87930acbb0f6a8688d979f40db8327347323dcb3a489b06879bb6a5","last_reissued_at":"2026-07-05T10:41:57.388577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:57.388577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23673","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":"2026-07-05T10:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wn6DnYAP88WEz/77Q/q9f+VwhhqFLhb7SzJq56wa9gq5NiaomRhGR6YGRz7jjBFBI8V8h/fEq/koReGBf8c0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:58:09.506900Z"},"content_sha256":"e6a934bac5e8b129418d1deea73a3451227d6258353fbef682c98e3cb47feba7","schema_version":"1.0","event_id":"sha256:e6a934bac5e8b129418d1deea73a3451227d6258353fbef682c98e3cb47feba7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BCVSN37IPEYKZOYPNKDIRWLZ6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Liang, Binyang Li, Kam-Fai Wong, Shubo Zhang, Zhengyi Zhao","submitted_at":"2025-03-31T02:36:30Z","abstract_excerpt":"In Biomedical Natural Language Processing (BioNLP) tasks, such as Relation Extraction, Named Entity Recognition, and Text Classification, the scarcity of high-quality data remains a significant challenge. This limitation poisons large language models to correctly understand relationships between biological entities, such as molecules and diseases, or drug interactions, and further results in potential misinterpretation of biomedical documents. To address this issue, current approaches generally adopt the Synthetic Data Augmentation method which involves similarity computation followed by word "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23673","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/2503.23673/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":"2026-07-05T10:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Agl/pAk3pWw0GMFlc3gj87Va9t9svvS+KTNT6QatDI/+P8ehZu0NZmCMNwjr3gZVIMWw8AKVY+gFkBG5OD7xCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:58:09.507467Z"},"content_sha256":"d5fb22229206d1bf5388ecfe6fda2e4d505cc40bab1fec4a3dc7a600166c3510","schema_version":"1.0","event_id":"sha256:d5fb22229206d1bf5388ecfe6fda2e4d505cc40bab1fec4a3dc7a600166c3510"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q/bundle.json","state_url":"https://pith.science/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q/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":"2026-08-06T23:58:09Z","links":{"resolver":"https://pith.science/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q","bundle":"https://pith.science/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q/bundle.json","state":"https://pith.science/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCVSN37IPEYKZOYPNKDIRWLZ6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BCVSN37IPEYKZOYPNKDIRWLZ6Q","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":"d4833e0cf95c0631387fa5a26d973339a393498a8e30cd0f1dae024f61236a60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:36:30Z","title_canon_sha256":"f983aa4975a21cd5e73c18c3877928580513a0990af8e79711f851c65137a279"},"schema_version":"1.0","source":{"id":"2503.23673","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23673","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23673v1","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23673","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"BCVSN37IPEYK","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"BCVSN37IPEYKZOYP","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"BCVSN37I","created_at":"2026-07-05T10:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:d5fb22229206d1bf5388ecfe6fda2e4d505cc40bab1fec4a3dc7a600166c3510","target":"graph","created_at":"2026-07-05T10:41:57Z","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/2503.23673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Biomedical Natural Language Processing (BioNLP) tasks, such as Relation Extraction, Named Entity Recognition, and Text Classification, the scarcity of high-quality data remains a significant challenge. This limitation poisons large language models to correctly understand relationships between biological entities, such as molecules and diseases, or drug interactions, and further results in potential misinterpretation of biomedical documents. To address this issue, current approaches generally adopt the Synthetic Data Augmentation method which involves similarity computation followed by word ","authors_text":"Bin Liang, Binyang Li, Kam-Fai Wong, Shubo Zhang, Zhengyi Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:36:30Z","title":"WHERE and WHICH: Iterative Debate for Biomedical Synthetic Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23673","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:e6a934bac5e8b129418d1deea73a3451227d6258353fbef682c98e3cb47feba7","target":"record","created_at":"2026-07-05T10:41:57Z","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":"d4833e0cf95c0631387fa5a26d973339a393498a8e30cd0f1dae024f61236a60","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:36:30Z","title_canon_sha256":"f983aa4975a21cd5e73c18c3877928580513a0990af8e79711f851c65137a279"},"schema_version":"1.0","source":{"id":"2503.23673","kind":"arxiv","version":1}},"canonical_sha256":"08ab26efe87930acbb0f6a8688d979f40db8327347323dcb3a489b06879bb6a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08ab26efe87930acbb0f6a8688d979f40db8327347323dcb3a489b06879bb6a5","first_computed_at":"2026-07-05T10:41:57.388577Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:57.388577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CCfGorDHxJvduoIXihRkLKV81Zv+oLFZIdYZ6Xfgj9h0t7Szmze8BhZiI+YtT5O+LX7mT85L1az3M0b6D0G3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:57.389077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23673","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6a934bac5e8b129418d1deea73a3451227d6258353fbef682c98e3cb47feba7","sha256:d5fb22229206d1bf5388ecfe6fda2e4d505cc40bab1fec4a3dc7a600166c3510"],"state_sha256":"2c82b764724f2594b710f075b40b4e649ffb1679cadc31719fef0f1ce18bdb9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MzfQmAqjp8MKAC+jAmj+Xfb6ZytHObM57cT5rwb4oaWwz0Ssf3AriITQJ9+8WGsb+kBROU2EFqX/JinUwLYqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:58:09.512366Z","bundle_sha256":"78effb673b554058004ef008a60ad9207c87069a1828114efff2efcbb693faf9"}}