{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:B4H7ZCSZ35EXGEKZKPL36UTYYD","short_pith_number":"pith:B4H7ZCSZ","schema_version":"1.0","canonical_sha256":"0f0ffc8a59df4973115953d7bf5278c0f858b6ad5041dae18d63c6dcd5160929","source":{"kind":"arxiv","id":"2606.24387","version":1},"attestation_state":"computed","paper":{"title":"AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdirahman Abdullahm, Filippos Ventirozos, Ioanna Nteka, Jordan Lee, Matthew Shardlow, Peter Appleby","submitted_at":"2026-06-23T10:19:58Z","abstract_excerpt":"Vehicle advertisements contain rich specification information, but automotive NER resources remain limited. We introduce AutoSpecNER, an expert-annotated dataset for fine-grained entity recognition in vehicle listings. The dataset includes 659 advertisements from a popular car-selling website, with over 10,000 entities annotated across 15 categories, including MODEL, ENGINE_SPEC, and BATTERY_CAPACITY. Annotation quality was validated through inter-annotator agreement, achieving an average score of 91.5%. We benchmark rule-based extraction, fine-tuned transformer encoders, and large language mo"},"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":"2606.24387","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T10:19:58Z","cross_cats_sorted":[],"title_canon_sha256":"ced43bc45e60f2af8d8d304d425b3293a8fee59f651a24349568b20c4db96e34","abstract_canon_sha256":"8ac6571a496faebb2b85c5dea2fcf8a17b2ba18f3e89cdf1ce0e793fc7fc9be9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:29.262931Z","signature_b64":"NAcJxXc+4/T/M52rCKutfgr/hEY4SX5+qU96fq0WL/NJhiwQqf89L+R6PT+O+8pyivqcxFgaLiAJNcjIXF3xAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f0ffc8a59df4973115953d7bf5278c0f858b6ad5041dae18d63c6dcd5160929","last_reissued_at":"2026-06-24T01:15:29.262570Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:29.262570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoSpecNER: A Fine-Grained Named Entity Recognition Dataset for Vehicle Specification Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdirahman Abdullahm, Filippos Ventirozos, Ioanna Nteka, Jordan Lee, Matthew Shardlow, Peter Appleby","submitted_at":"2026-06-23T10:19:58Z","abstract_excerpt":"Vehicle advertisements contain rich specification information, but automotive NER resources remain limited. We introduce AutoSpecNER, an expert-annotated dataset for fine-grained entity recognition in vehicle listings. The dataset includes 659 advertisements from a popular car-selling website, with over 10,000 entities annotated across 15 categories, including MODEL, ENGINE_SPEC, and BATTERY_CAPACITY. Annotation quality was validated through inter-annotator agreement, achieving an average score of 91.5%. We benchmark rule-based extraction, fine-tuned transformer encoders, and large language mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24387","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/2606.24387/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":"2606.24387","created_at":"2026-06-24T01:15:29.262632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24387v1","created_at":"2026-06-24T01:15:29.262632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24387","created_at":"2026-06-24T01:15:29.262632+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4H7ZCSZ35EX","created_at":"2026-06-24T01:15:29.262632+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4H7ZCSZ35EXGEKZ","created_at":"2026-06-24T01:15:29.262632+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4H7ZCSZ","created_at":"2026-06-24T01:15:29.262632+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/B4H7ZCSZ35EXGEKZKPL36UTYYD","json":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD.json","graph_json":"https://pith.science/api/pith-number/B4H7ZCSZ35EXGEKZKPL36UTYYD/graph.json","events_json":"https://pith.science/api/pith-number/B4H7ZCSZ35EXGEKZKPL36UTYYD/events.json","paper":"https://pith.science/paper/B4H7ZCSZ"},"agent_actions":{"view_html":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD","download_json":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD.json","view_paper":"https://pith.science/paper/B4H7ZCSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24387&json=true","fetch_graph":"https://pith.science/api/pith-number/B4H7ZCSZ35EXGEKZKPL36UTYYD/graph.json","fetch_events":"https://pith.science/api/pith-number/B4H7ZCSZ35EXGEKZKPL36UTYYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD/action/storage_attestation","attest_author":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD/action/author_attestation","sign_citation":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD/action/citation_signature","submit_replication":"https://pith.science/pith/B4H7ZCSZ35EXGEKZKPL36UTYYD/action/replication_record"}},"created_at":"2026-06-24T01:15:29.262632+00:00","updated_at":"2026-06-24T01:15:29.262632+00:00"}