{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PRBKJQN7QALYPQFXW3L7IWI6ZR","short_pith_number":"pith:PRBKJQN7","schema_version":"1.0","canonical_sha256":"7c42a4c1bf801787c0b7b6d7f4591ecc610f2f37b46ef6a93aee3ef947397841","source":{"kind":"arxiv","id":"2301.09350","version":2},"attestation_state":"computed","paper":{"title":"Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasia Krithara, Anastasios Nentidis, Georgios Paliouras, Grigorios Tsoumakas, Thomas Chatzopoulos","submitted_at":"2023-01-23T10:33:22Z","abstract_excerpt":"Objective: Semantic indexing of biomedical literature is usually done at the level of MeSH descriptors with several related but distinct biomedical concepts often grouped together and treated as a single topic. This study proposes a new method for the automated refinement of subject annotations at the level of MeSH concepts. Methods: Lacking labelled data, we rely on weak supervision based on concept occurrence in the abstract of an article, which is also enhanced by dictionary-based heuristics. In addition, we investigate deep learning approaches, making design choices to tackle the particula"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.09350","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T10:33:22Z","cross_cats_sorted":["cs.DL","cs.LG"],"title_canon_sha256":"9157d3730031186dc9af53a99f6dea1050eb198c7cd457e69c0c8167df3b6091","abstract_canon_sha256":"225254fa07cc192f6d752e4527fb1bbc5802dbb711ae87bcfef00a122ac9dbe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:20.834476Z","signature_b64":"stzh+Wkwr2WHrYhw9GFWO8QAh01YS+2mCXQo2M0e+lDM1kErtuXvfmrRE16Lhu7t1DlyXd9b66I86I5qy0ldDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c42a4c1bf801787c0b7b6d7f4591ecc610f2f37b46ef6a93aee3ef947397841","last_reissued_at":"2026-07-05T06:57:20.833978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:20.833978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anastasia Krithara, Anastasios Nentidis, Georgios Paliouras, Grigorios Tsoumakas, Thomas Chatzopoulos","submitted_at":"2023-01-23T10:33:22Z","abstract_excerpt":"Objective: Semantic indexing of biomedical literature is usually done at the level of MeSH descriptors with several related but distinct biomedical concepts often grouped together and treated as a single topic. This study proposes a new method for the automated refinement of subject annotations at the level of MeSH concepts. Methods: Lacking labelled data, we rely on weak supervision based on concept occurrence in the abstract of an article, which is also enhanced by dictionary-based heuristics. In addition, we investigate deep learning approaches, making design choices to tackle the particula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09350","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/2301.09350/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.09350","created_at":"2026-07-05T06:57:20.834038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.09350v2","created_at":"2026-07-05T06:57:20.834038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09350","created_at":"2026-07-05T06:57:20.834038+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRBKJQN7QALY","created_at":"2026-07-05T06:57:20.834038+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRBKJQN7QALYPQFX","created_at":"2026-07-05T06:57:20.834038+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRBKJQN7","created_at":"2026-07-05T06:57:20.834038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR","json":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR.json","graph_json":"https://pith.science/api/pith-number/PRBKJQN7QALYPQFXW3L7IWI6ZR/graph.json","events_json":"https://pith.science/api/pith-number/PRBKJQN7QALYPQFXW3L7IWI6ZR/events.json","paper":"https://pith.science/paper/PRBKJQN7"},"agent_actions":{"view_html":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR","download_json":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR.json","view_paper":"https://pith.science/paper/PRBKJQN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.09350&json=true","fetch_graph":"https://pith.science/api/pith-number/PRBKJQN7QALYPQFXW3L7IWI6ZR/graph.json","fetch_events":"https://pith.science/api/pith-number/PRBKJQN7QALYPQFXW3L7IWI6ZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR/action/storage_attestation","attest_author":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR/action/author_attestation","sign_citation":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR/action/citation_signature","submit_replication":"https://pith.science/pith/PRBKJQN7QALYPQFXW3L7IWI6ZR/action/replication_record"}},"created_at":"2026-07-05T06:57:20.834038+00:00","updated_at":"2026-07-05T06:57:20.834038+00:00"}