{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2002:2RB2XWMEQ47KWIZGS3GHF4RXCU","short_pith_number":"pith:2RB2XWME","schema_version":"1.0","canonical_sha256":"d443abd984873eab232696cc72f23715396f6378e579a4c237ed77115bd30220","source":{"kind":"arxiv","id":"cs/0205028","version":1},"attestation_state":"computed","paper":{"title":"NLTK: The Natural Language Toolkit","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Loper, Steven Bird","submitted_at":"2002-05-17T12:51:00Z","abstract_excerpt":"NLTK, the Natural Language Toolkit, is a suite of open source program modules, tutorials and problem sets, providing ready-to-use computational linguistics courseware. NLTK covers symbolic and statistical natural language processing, and is interfaced to annotated corpora. Students augment and replace existing components, learn structured programming by example, and manipulate sophisticated models from the outset."},"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":"cs/0205028","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"2002-05-17T12:51:00Z","cross_cats_sorted":[],"title_canon_sha256":"bff63eb4d702c8c68e35db94adeb46459882346663a1431f36ca160bb3f76c95","abstract_canon_sha256":"0d58f7d7d31df7632292707f3331c939e3b5b574176ec5fc0adcd46519bac4fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:24:17.663835Z","signature_b64":"ovMA8UAMh7/xf8gaMclXc+GCuP2CaKfPtBwplF2YhUJUVgdCVQH9D4K7E+YwIOPrQ/bUSl1vOr+HBqp8n1atDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d443abd984873eab232696cc72f23715396f6378e579a4c237ed77115bd30220","last_reissued_at":"2026-07-04T14:24:17.663448Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:24:17.663448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NLTK: The Natural Language Toolkit","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edward Loper, Steven Bird","submitted_at":"2002-05-17T12:51:00Z","abstract_excerpt":"NLTK, the Natural Language Toolkit, is a suite of open source program modules, tutorials and problem sets, providing ready-to-use computational linguistics courseware. NLTK covers symbolic and statistical natural language processing, and is interfaced to annotated corpora. Students augment and replace existing components, learn structured programming by example, and manipulate sophisticated models from the outset."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0205028","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/cs/0205028/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":"cs/0205028","created_at":"2026-07-04T14:24:17.663503+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0205028v1","created_at":"2026-07-04T14:24:17.663503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0205028","created_at":"2026-07-04T14:24:17.663503+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RB2XWMEQ47K","created_at":"2026-07-04T14:24:17.663503+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RB2XWMEQ47KWIZG","created_at":"2026-07-04T14:24:17.663503+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RB2XWME","created_at":"2026-07-04T14:24:17.663503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2607.07159","citing_title":"Recovering Latent Structures after Variational Bayesian Variable Selection: Fit Assessment and Factor-Number Selection in Partially Exploratory Factor Analysis","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23539","citing_title":"LightSTAR: Efficient Visual Document Retrieval via Lightweight Selection with Vision-Adaptive Refinement","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29199","citing_title":"Scalable AI-Driven Analytics for User Engagement and Stance Detection on Social Media","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30027","citing_title":"DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19316","citing_title":"A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"1910.03771","citing_title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","ref_index":170,"is_internal_anchor":true},{"citing_arxiv_id":"2101.00027","citing_title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":231,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU","json":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU.json","graph_json":"https://pith.science/api/pith-number/2RB2XWMEQ47KWIZGS3GHF4RXCU/graph.json","events_json":"https://pith.science/api/pith-number/2RB2XWMEQ47KWIZGS3GHF4RXCU/events.json","paper":"https://pith.science/paper/2RB2XWME"},"agent_actions":{"view_html":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU","download_json":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU.json","view_paper":"https://pith.science/paper/2RB2XWME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0205028&json=true","fetch_graph":"https://pith.science/api/pith-number/2RB2XWMEQ47KWIZGS3GHF4RXCU/graph.json","fetch_events":"https://pith.science/api/pith-number/2RB2XWMEQ47KWIZGS3GHF4RXCU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU/action/storage_attestation","attest_author":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU/action/author_attestation","sign_citation":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU/action/citation_signature","submit_replication":"https://pith.science/pith/2RB2XWMEQ47KWIZGS3GHF4RXCU/action/replication_record"}},"created_at":"2026-07-04T14:24:17.663503+00:00","updated_at":"2026-07-04T14:24:17.663503+00:00"}