{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RA7TJFPOTVIJWBCI5U64N3BBWQ","short_pith_number":"pith:RA7TJFPO","schema_version":"1.0","canonical_sha256":"883f3495ee9d509b0448ed3dc6ec21b437e8aab65f1bfd18fc223bba4b6953d0","source":{"kind":"arxiv","id":"2504.21589","version":1},"attestation_state":"computed","paper":{"title":"DNB-AI-Project at SemEval-2025 Task 5: An LLM-Ensemble Approach for Automated Subject Indexing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DL"],"primary_cat":"cs.CL","authors_text":"Lisa Kluge, Maximilian K\\\"ahler","submitted_at":"2025-04-30T12:47:09Z","abstract_excerpt":"This paper presents our system developed for the SemEval-2025 Task 5: LLMs4Subjects: LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog. Our system relies on prompting a selection of LLMs with varying examples of intellectually annotated records and asking the LLMs to similarly suggest keywords for new records. This few-shot prompting technique is combined with a series of post-processing steps that map the generated keywords to the target vocabulary, aggregate the resulting subject terms to an ensemble vote and, finally, rank them as to their relevance "},"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":"2504.21589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-30T12:47:09Z","cross_cats_sorted":["cs.AI","cs.DL"],"title_canon_sha256":"a1b8754a2c60de951057f6f724db41e3f8b07e4288c2ab5b3eb61bc3087fe37f","abstract_canon_sha256":"9f857337c4e5f1dea5357e104d74ff9a537613dff190899b530b4bbd68975676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:46.129227Z","signature_b64":"5ekh58a3UqXQHK4lB0FEDgPaYwigfDukwmqhekCMK9f4DEug2QoYDAtgkD4myZ6gPkXWqqDlup/a7QPg0R/yDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"883f3495ee9d509b0448ed3dc6ec21b437e8aab65f1bfd18fc223bba4b6953d0","last_reissued_at":"2026-07-05T11:53:46.128790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:46.128790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DNB-AI-Project at SemEval-2025 Task 5: An LLM-Ensemble Approach for Automated Subject Indexing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DL"],"primary_cat":"cs.CL","authors_text":"Lisa Kluge, Maximilian K\\\"ahler","submitted_at":"2025-04-30T12:47:09Z","abstract_excerpt":"This paper presents our system developed for the SemEval-2025 Task 5: LLMs4Subjects: LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog. Our system relies on prompting a selection of LLMs with varying examples of intellectually annotated records and asking the LLMs to similarly suggest keywords for new records. This few-shot prompting technique is combined with a series of post-processing steps that map the generated keywords to the target vocabulary, aggregate the resulting subject terms to an ensemble vote and, finally, rank them as to their relevance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21589","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/2504.21589/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":"2504.21589","created_at":"2026-07-05T11:53:46.128850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21589v1","created_at":"2026-07-05T11:53:46.128850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21589","created_at":"2026-07-05T11:53:46.128850+00:00"},{"alias_kind":"pith_short_12","alias_value":"RA7TJFPOTVIJ","created_at":"2026-07-05T11:53:46.128850+00:00"},{"alias_kind":"pith_short_16","alias_value":"RA7TJFPOTVIJWBCI","created_at":"2026-07-05T11:53:46.128850+00:00"},{"alias_kind":"pith_short_8","alias_value":"RA7TJFPO","created_at":"2026-07-05T11:53:46.128850+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/RA7TJFPOTVIJWBCI5U64N3BBWQ","json":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ.json","graph_json":"https://pith.science/api/pith-number/RA7TJFPOTVIJWBCI5U64N3BBWQ/graph.json","events_json":"https://pith.science/api/pith-number/RA7TJFPOTVIJWBCI5U64N3BBWQ/events.json","paper":"https://pith.science/paper/RA7TJFPO"},"agent_actions":{"view_html":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ","download_json":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ.json","view_paper":"https://pith.science/paper/RA7TJFPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21589&json=true","fetch_graph":"https://pith.science/api/pith-number/RA7TJFPOTVIJWBCI5U64N3BBWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RA7TJFPOTVIJWBCI5U64N3BBWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ/action/storage_attestation","attest_author":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ/action/author_attestation","sign_citation":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ/action/citation_signature","submit_replication":"https://pith.science/pith/RA7TJFPOTVIJWBCI5U64N3BBWQ/action/replication_record"}},"created_at":"2026-07-05T11:53:46.128850+00:00","updated_at":"2026-07-05T11:53:46.128850+00:00"}