{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PRBKJQN7QALYPQFXW3L7IWI6ZR","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":"225254fa07cc192f6d752e4527fb1bbc5802dbb711ae87bcfef00a122ac9dbe5","cross_cats_sorted":["cs.DL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T10:33:22Z","title_canon_sha256":"9157d3730031186dc9af53a99f6dea1050eb198c7cd457e69c0c8167df3b6091"},"schema_version":"1.0","source":{"id":"2301.09350","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.09350","created_at":"2026-07-05T06:57:20Z"},{"alias_kind":"arxiv_version","alias_value":"2301.09350v2","created_at":"2026-07-05T06:57:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.09350","created_at":"2026-07-05T06:57:20Z"},{"alias_kind":"pith_short_12","alias_value":"PRBKJQN7QALY","created_at":"2026-07-05T06:57:20Z"},{"alias_kind":"pith_short_16","alias_value":"PRBKJQN7QALYPQFX","created_at":"2026-07-05T06:57:20Z"},{"alias_kind":"pith_short_8","alias_value":"PRBKJQN7","created_at":"2026-07-05T06:57:20Z"}],"graph_snapshots":[{"event_id":"sha256:57f8fbf89c858aa49f3f3698fa5569139fa5b6a189696873e8f739ed94ea1557","target":"graph","created_at":"2026-07-05T06:57:20Z","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/2301.09350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anastasia Krithara, Anastasios Nentidis, Georgios Paliouras, Grigorios Tsoumakas, Thomas Chatzopoulos","cross_cats":["cs.DL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T10:33:22Z","title":"Large-scale investigation of weakly-supervised deep learning for the fine-grained semantic indexing of biomedical literature"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.09350","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:fe5619147239e743813c88d97e61e49f0d2bfa7a5edc9934731ca2ac2ebe1d68","target":"record","created_at":"2026-07-05T06:57:20Z","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":"225254fa07cc192f6d752e4527fb1bbc5802dbb711ae87bcfef00a122ac9dbe5","cross_cats_sorted":["cs.DL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-23T10:33:22Z","title_canon_sha256":"9157d3730031186dc9af53a99f6dea1050eb198c7cd457e69c0c8167df3b6091"},"schema_version":"1.0","source":{"id":"2301.09350","kind":"arxiv","version":2}},"canonical_sha256":"7c42a4c1bf801787c0b7b6d7f4591ecc610f2f37b46ef6a93aee3ef947397841","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c42a4c1bf801787c0b7b6d7f4591ecc610f2f37b46ef6a93aee3ef947397841","first_computed_at":"2026-07-05T06:57:20.833978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:20.833978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"stzh+Wkwr2WHrYhw9GFWO8QAh01YS+2mCXQo2M0e+lDM1kErtuXvfmrRE16Lhu7t1DlyXd9b66I86I5qy0ldDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:20.834476Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.09350","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe5619147239e743813c88d97e61e49f0d2bfa7a5edc9934731ca2ac2ebe1d68","sha256:57f8fbf89c858aa49f3f3698fa5569139fa5b6a189696873e8f739ed94ea1557"],"state_sha256":"632e8f9bdbc2b48f1ca7d651ed48f3a53b4052104e1b7080005c60971226d098"}