{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JINAWJS73UIYBJGSHDCUM4VZ4L","short_pith_number":"pith:JINAWJS7","schema_version":"1.0","canonical_sha256":"4a1a0b265fdd1180a4d238c54672b9e2d6128a0c281dede97404d69777b322b1","source":{"kind":"arxiv","id":"1908.10993","version":1},"attestation_state":"computed","paper":{"title":"Scientific Statement Classification over arXiv.org","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.DL"],"primary_cat":"cs.CL","authors_text":"Bruce R. Miller, Deyan Ginev","submitted_at":"2019-08-29T00:25:38Z","abstract_excerpt":"We introduce a new classification task for scientific statements and release a large-scale dataset for supervised learning. Our resource is derived from a machine-readable representation of the arXiv.org collection of preprint articles. We explore fifty author-annotated categories and empirically motivate a task design of grouping 10.5 million annotated paragraphs into thirteen classes. We demonstrate that the task setup aligns with known success rates from the state of the art, peaking at a 0.91 F1-score via a BiLSTM encoder-decoder model. Additionally, we introduce a lexeme serialization for"},"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":"1908.10993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-29T00:25:38Z","cross_cats_sorted":["cs.AI","cs.DL"],"title_canon_sha256":"ded18559c92a59d3f6fcfa5fe69aaf8b1a4dac055507b017e08973915b5de486","abstract_canon_sha256":"f7977d5e697b4ac83407f66f98d3d7c3e196a533ac718daaf6eda6d5e62dd1c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:27.499448Z","signature_b64":"UBzBtcedQvqOIHkTzsFnzpMtKnJuRjKZVTaRYXI8pcsz3S9rKnp8i+n7UM4WVnO6vR3GiwBnLBMFzmaGuX06CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a1a0b265fdd1180a4d238c54672b9e2d6128a0c281dede97404d69777b322b1","last_reissued_at":"2026-07-05T10:35:27.498752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:27.498752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scientific Statement Classification over arXiv.org","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.DL"],"primary_cat":"cs.CL","authors_text":"Bruce R. Miller, Deyan Ginev","submitted_at":"2019-08-29T00:25:38Z","abstract_excerpt":"We introduce a new classification task for scientific statements and release a large-scale dataset for supervised learning. Our resource is derived from a machine-readable representation of the arXiv.org collection of preprint articles. We explore fifty author-annotated categories and empirically motivate a task design of grouping 10.5 million annotated paragraphs into thirteen classes. We demonstrate that the task setup aligns with known success rates from the state of the art, peaking at a 0.91 F1-score via a BiLSTM encoder-decoder model. Additionally, we introduce a lexeme serialization for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10993","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/1908.10993/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":"1908.10993","created_at":"2026-07-05T10:35:27.498822+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10993v1","created_at":"2026-07-05T10:35:27.498822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10993","created_at":"2026-07-05T10:35:27.498822+00:00"},{"alias_kind":"pith_short_12","alias_value":"JINAWJS73UIY","created_at":"2026-07-05T10:35:27.498822+00:00"},{"alias_kind":"pith_short_16","alias_value":"JINAWJS73UIYBJGS","created_at":"2026-07-05T10:35:27.498822+00:00"},{"alias_kind":"pith_short_8","alias_value":"JINAWJS7","created_at":"2026-07-05T10:35:27.498822+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/JINAWJS73UIYBJGSHDCUM4VZ4L","json":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L.json","graph_json":"https://pith.science/api/pith-number/JINAWJS73UIYBJGSHDCUM4VZ4L/graph.json","events_json":"https://pith.science/api/pith-number/JINAWJS73UIYBJGSHDCUM4VZ4L/events.json","paper":"https://pith.science/paper/JINAWJS7"},"agent_actions":{"view_html":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L","download_json":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L.json","view_paper":"https://pith.science/paper/JINAWJS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10993&json=true","fetch_graph":"https://pith.science/api/pith-number/JINAWJS73UIYBJGSHDCUM4VZ4L/graph.json","fetch_events":"https://pith.science/api/pith-number/JINAWJS73UIYBJGSHDCUM4VZ4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L/action/storage_attestation","attest_author":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L/action/author_attestation","sign_citation":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L/action/citation_signature","submit_replication":"https://pith.science/pith/JINAWJS73UIYBJGSHDCUM4VZ4L/action/replication_record"}},"created_at":"2026-07-05T10:35:27.498822+00:00","updated_at":"2026-07-05T10:35:27.498822+00:00"}