{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:OAVQB6G7NZ4TBEWM4DM4UO35G3","short_pith_number":"pith:OAVQB6G7","schema_version":"1.0","canonical_sha256":"702b00f8df6e793092cce0d9ca3b7d36f2105a0b9cfa5d33fe0709551b58d55e","source":{"kind":"arxiv","id":"1710.02271","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Extraction of Representative Concepts from Scientific Literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Adit Krishnan, Aravind Sankar, Jiawei Han, Shi Zhi","submitted_at":"2017-10-06T04:04:43Z","abstract_excerpt":"This paper studies the automated categorization and extraction of scientific concepts from titles of scientific articles, in order to gain a deeper understanding of their key contributions and facilitate the construction of a generic academic knowledgebase. Towards this goal, we propose an unsupervised, domain-independent, and scalable two-phase algorithm to type and extract key concept mentions into aspects of interest (e.g., Techniques, Applications, etc.). In the first phase of our algorithm we propose PhraseType, a probabilistic generative model which exploits textual features and limited "},"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":"1710.02271","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-10-06T04:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"41bcf6ab9bcf7e67487162693e5bc3585fda45df664a20a25391d205534e48f3","abstract_canon_sha256":"6c90b276b21440161113214d776725d42b54b8d0e9252e15f2646dc1bd532acf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:57.319732Z","signature_b64":"aYbc4Z0t4oWxk3QQ9Nxx3uVRm/5laxrmf1DsMy842KaHakmGuxL8/kd6QQQHdq7WCdhLi6Ry23tvgoWHebBKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"702b00f8df6e793092cce0d9ca3b7d36f2105a0b9cfa5d33fe0709551b58d55e","last_reissued_at":"2026-05-18T00:30:57.319194Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:57.319194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Extraction of Representative Concepts from Scientific Literature","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Adit Krishnan, Aravind Sankar, Jiawei Han, Shi Zhi","submitted_at":"2017-10-06T04:04:43Z","abstract_excerpt":"This paper studies the automated categorization and extraction of scientific concepts from titles of scientific articles, in order to gain a deeper understanding of their key contributions and facilitate the construction of a generic academic knowledgebase. Towards this goal, we propose an unsupervised, domain-independent, and scalable two-phase algorithm to type and extract key concept mentions into aspects of interest (e.g., Techniques, Applications, etc.). In the first phase of our algorithm we propose PhraseType, a probabilistic generative model which exploits textual features and limited "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02271","kind":"arxiv","version":3},"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":"1710.02271","created_at":"2026-05-18T00:30:57.319274+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.02271v3","created_at":"2026-05-18T00:30:57.319274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02271","created_at":"2026-05-18T00:30:57.319274+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAVQB6G7NZ4T","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAVQB6G7NZ4TBEWM","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAVQB6G7","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.20220","citing_title":"Alternatives to the Laplacian for Scalable Spectral Clustering with Group Fairness Constraints","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3","json":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3.json","graph_json":"https://pith.science/api/pith-number/OAVQB6G7NZ4TBEWM4DM4UO35G3/graph.json","events_json":"https://pith.science/api/pith-number/OAVQB6G7NZ4TBEWM4DM4UO35G3/events.json","paper":"https://pith.science/paper/OAVQB6G7"},"agent_actions":{"view_html":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3","download_json":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3.json","view_paper":"https://pith.science/paper/OAVQB6G7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.02271&json=true","fetch_graph":"https://pith.science/api/pith-number/OAVQB6G7NZ4TBEWM4DM4UO35G3/graph.json","fetch_events":"https://pith.science/api/pith-number/OAVQB6G7NZ4TBEWM4DM4UO35G3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3/action/storage_attestation","attest_author":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3/action/author_attestation","sign_citation":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3/action/citation_signature","submit_replication":"https://pith.science/pith/OAVQB6G7NZ4TBEWM4DM4UO35G3/action/replication_record"}},"created_at":"2026-05-18T00:30:57.319274+00:00","updated_at":"2026-05-18T00:30:57.319274+00:00"}