{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:KDBRD6SDEJ4O3VLOEOHXJCYUBD","short_pith_number":"pith:KDBRD6SD","schema_version":"1.0","canonical_sha256":"50c311fa432278edd56e238f748b1408c596fb365161aeef8c30315da74b914d","source":{"kind":"arxiv","id":"1307.1718","version":2},"attestation_state":"computed","paper":{"title":"Graph-based Approach to Automatic Taxonomy Generation (GraBTax)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"C. Lee Giles, Madian Khabsa, Pucktada Treeratpituk","submitted_at":"2013-07-05T21:05:20Z","abstract_excerpt":"We propose a novel graph-based approach for constructing concept hierarchy from a large text corpus. Our algorithm, GraBTax, incorporates both statistical co-occurrences and lexical similarity in optimizing the structure of the taxonomy. To automatically generate topic-dependent taxonomies from a large text corpus, GraBTax first extracts topical terms and their relationships from the corpus. The algorithm then constructs a weighted graph representing topics and their associations. A graph partitioning algorithm is then used to recursively partition the topic graph into a taxonomy. For evaluati"},"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":"1307.1718","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2013-07-05T21:05:20Z","cross_cats_sorted":[],"title_canon_sha256":"985260867fb5ffa8ed3b074db976cc7f1f7b003ac1cd206a0d8667b76bfc9e83","abstract_canon_sha256":"c6554780c5ed86f81c31bf31f6879879a246dc28139c4c20c14f61becb64e485"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:52:58.437620Z","signature_b64":"4hZ9Cw6OAl9slY4OcS1PIYcSJ6Gya/DY7fS0KODCrVJ6CblDMmQNmiOc1u/HCrWHkCdD8F/poNa7KI9MnWXSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50c311fa432278edd56e238f748b1408c596fb365161aeef8c30315da74b914d","last_reissued_at":"2026-05-18T02:52:58.437091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:52:58.437091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-based Approach to Automatic Taxonomy Generation (GraBTax)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"C. Lee Giles, Madian Khabsa, Pucktada Treeratpituk","submitted_at":"2013-07-05T21:05:20Z","abstract_excerpt":"We propose a novel graph-based approach for constructing concept hierarchy from a large text corpus. Our algorithm, GraBTax, incorporates both statistical co-occurrences and lexical similarity in optimizing the structure of the taxonomy. To automatically generate topic-dependent taxonomies from a large text corpus, GraBTax first extracts topical terms and their relationships from the corpus. The algorithm then constructs a weighted graph representing topics and their associations. A graph partitioning algorithm is then used to recursively partition the topic graph into a taxonomy. For evaluati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1307.1718","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":"1307.1718","created_at":"2026-05-18T02:52:58.437168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1307.1718v2","created_at":"2026-05-18T02:52:58.437168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1307.1718","created_at":"2026-05-18T02:52:58.437168+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDBRD6SDEJ4O","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDBRD6SDEJ4O3VLO","created_at":"2026-05-18T12:27:49.015174+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDBRD6SD","created_at":"2026-05-18T12:27:49.015174+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/KDBRD6SDEJ4O3VLOEOHXJCYUBD","json":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD.json","graph_json":"https://pith.science/api/pith-number/KDBRD6SDEJ4O3VLOEOHXJCYUBD/graph.json","events_json":"https://pith.science/api/pith-number/KDBRD6SDEJ4O3VLOEOHXJCYUBD/events.json","paper":"https://pith.science/paper/KDBRD6SD"},"agent_actions":{"view_html":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD","download_json":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD.json","view_paper":"https://pith.science/paper/KDBRD6SD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1307.1718&json=true","fetch_graph":"https://pith.science/api/pith-number/KDBRD6SDEJ4O3VLOEOHXJCYUBD/graph.json","fetch_events":"https://pith.science/api/pith-number/KDBRD6SDEJ4O3VLOEOHXJCYUBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD/action/storage_attestation","attest_author":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD/action/author_attestation","sign_citation":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD/action/citation_signature","submit_replication":"https://pith.science/pith/KDBRD6SDEJ4O3VLOEOHXJCYUBD/action/replication_record"}},"created_at":"2026-05-18T02:52:58.437168+00:00","updated_at":"2026-05-18T02:52:58.437168+00:00"}