{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2008:Z2ULJZOJ26TKIN7RQHPW4MR6GB","short_pith_number":"pith:Z2ULJZOJ","schema_version":"1.0","canonical_sha256":"cea8b4e5c9d7a6a437f181df6e323e3079ce3f08a27316ded8c9cf7620694d73","source":{"kind":"arxiv","id":"0806.3787","version":2},"attestation_state":"computed","paper":{"title":"Computational Approaches to Measuring the Similarity of Short Contexts : A Review of Applications and Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duluth), Ted Pedersen (University of Minnesota","submitted_at":"2008-06-23T23:27:20Z","abstract_excerpt":"Measuring the similarity of short written contexts is a fundamental problem in Natural Language Processing. This article provides a unifying framework by which short context problems can be categorized both by their intended application and proposed solution. The goal is to show that various problems and methodologies that appear quite different on the surface are in fact very closely related. The axes by which these categorizations are made include the format of the contexts (headed versus headless), the way in which the contexts are to be measured (first-order versus second-order similarity)"},"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":"0806.3787","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2008-06-23T23:27:20Z","cross_cats_sorted":[],"title_canon_sha256":"7807a1d33e0266a4469bd87471379cab098ab342f909ecf2ebbe7c84906d2e7a","abstract_canon_sha256":"decf7f6ea9ecbdd80ac5c9c47002e72e3dde5ee484409ec1a89c7651dead6418"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:39:08.606771Z","signature_b64":"kCpR3doF4QWolA3oKncwA5m2q+Py+vqFApSHSxWadw/pbPzzf1Lg8KW+2snPpepuQkcJALg6LyvUUmMIhHHIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea8b4e5c9d7a6a437f181df6e323e3079ce3f08a27316ded8c9cf7620694d73","last_reissued_at":"2026-05-18T04:39:08.606323Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:39:08.606323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computational Approaches to Measuring the Similarity of Short Contexts : A Review of Applications and Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duluth), Ted Pedersen (University of Minnesota","submitted_at":"2008-06-23T23:27:20Z","abstract_excerpt":"Measuring the similarity of short written contexts is a fundamental problem in Natural Language Processing. This article provides a unifying framework by which short context problems can be categorized both by their intended application and proposed solution. The goal is to show that various problems and methodologies that appear quite different on the surface are in fact very closely related. The axes by which these categorizations are made include the format of the contexts (headed versus headless), the way in which the contexts are to be measured (first-order versus second-order similarity)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"0806.3787","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":""},"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":"0806.3787","created_at":"2026-05-18T04:39:08.606395+00:00"},{"alias_kind":"arxiv_version","alias_value":"0806.3787v2","created_at":"2026-05-18T04:39:08.606395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.0806.3787","created_at":"2026-05-18T04:39:08.606395+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2ULJZOJ26TK","created_at":"2026-05-18T12:25:58.018023+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2ULJZOJ26TKIN7R","created_at":"2026-05-18T12:25:58.018023+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2ULJZOJ","created_at":"2026-05-18T12:25:58.018023+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/Z2ULJZOJ26TKIN7RQHPW4MR6GB","json":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB.json","graph_json":"https://pith.science/api/pith-number/Z2ULJZOJ26TKIN7RQHPW4MR6GB/graph.json","events_json":"https://pith.science/api/pith-number/Z2ULJZOJ26TKIN7RQHPW4MR6GB/events.json","paper":"https://pith.science/paper/Z2ULJZOJ"},"agent_actions":{"view_html":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB","download_json":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB.json","view_paper":"https://pith.science/paper/Z2ULJZOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=0806.3787&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2ULJZOJ26TKIN7RQHPW4MR6GB/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2ULJZOJ26TKIN7RQHPW4MR6GB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB/action/storage_attestation","attest_author":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB/action/author_attestation","sign_citation":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB/action/citation_signature","submit_replication":"https://pith.science/pith/Z2ULJZOJ26TKIN7RQHPW4MR6GB/action/replication_record"}},"created_at":"2026-05-18T04:39:08.606395+00:00","updated_at":"2026-05-18T04:39:08.606395+00:00"}