{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:IIO77B3CD7D2HGE7U4Y5SVX4A5","short_pith_number":"pith:IIO77B3C","canonical_record":{"source":{"id":"1707.02919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-10T16:02:44Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"5fbae670bb6e42401e1904fe5a81a7a71bb6407acec4e53ace47e3eb61936f30","abstract_canon_sha256":"159799df4b3d1b2ec1b1e65e436ee723257c7b6c93c0a0c063dc8cc016683cef"},"schema_version":"1.0"},"canonical_sha256":"421dff87621fc7a3989fa731d956fc0751941ca9be7c90ea0df17a0ba126a395","source":{"kind":"arxiv","id":"1707.02919","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02919","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02919v2","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02919","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"IIO77B3CD7D2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IIO77B3CD7D2HGE7","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IIO77B3C","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:IIO77B3CD7D2HGE7U4Y5SVX4A5","target":"record","payload":{"canonical_record":{"source":{"id":"1707.02919","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-10T16:02:44Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"5fbae670bb6e42401e1904fe5a81a7a71bb6407acec4e53ace47e3eb61936f30","abstract_canon_sha256":"159799df4b3d1b2ec1b1e65e436ee723257c7b6c93c0a0c063dc8cc016683cef"},"schema_version":"1.0"},"canonical_sha256":"421dff87621fc7a3989fa731d956fc0751941ca9be7c90ea0df17a0ba126a395","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:17.648928Z","signature_b64":"3IeHiHbdGKQh46fNLwzMnFRmLmkjOcpUg5c9EmIqcBW2S7/0THZmhQDblVzvQtMul8MvhmpOm33UWfZAgyUgBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421dff87621fc7a3989fa731d956fc0751941ca9be7c90ea0df17a0ba126a395","last_reissued_at":"2026-05-18T00:39:17.648145Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:17.648145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.02919","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FxmqAVVR5+SrebzvOkISIRt8qXXQGrRVM3LSFvLeGMfCd8ywLu0LoZ9CK3bGUDpvMB5FL3E60XJexXUbuh3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:17:19.756428Z"},"content_sha256":"ab003b3ca46d46f0bf6679c0361005ad0eb6a71293b22038d5ccc3dc07699bc8","schema_version":"1.0","event_id":"sha256:ab003b3ca46d46f0bf6679c0361005ad0eb6a71293b22038d5ccc3dc07699bc8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:IIO77B3CD7D2HGE7U4Y5SVX4A5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Elizabeth D. Trippe, Juan B. Gutierrez, Krys Kochut, Mehdi Allahyari, Mehdi Assefi, Saied Safaei, Seyedamin Pouriyeh","submitted_at":"2017-07-10T16:02:44Z","abstract_excerpt":"The amount of text that is generated every day is increasing dramatically. This tremendous volume of mostly unstructured text cannot be simply processed and perceived by computers. Therefore, efficient and effective techniques and algorithms are required to discover useful patterns. Text mining is the task of extracting meaningful information from text, which has gained significant attentions in recent years. In this paper, we describe several of the most fundamental text mining tasks and techniques including text pre-processing, classification and clustering. Additionally, we briefly explain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02919","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bc17AJnymb0fSI895/8XjrJebKDvjraOhXvop7enpJCg4OX8CyPLo9v+1Jno/Veldfc35qL59dlnrvwhNbs7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:17:19.756794Z"},"content_sha256":"e9865c4dc07e0367957d4dce152470aca0f618677408c310d5835549b10bb2d8","schema_version":"1.0","event_id":"sha256:e9865c4dc07e0367957d4dce152470aca0f618677408c310d5835549b10bb2d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5/bundle.json","state_url":"https://pith.science/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T00:17:19Z","links":{"resolver":"https://pith.science/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5","bundle":"https://pith.science/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5/bundle.json","state":"https://pith.science/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIO77B3CD7D2HGE7U4Y5SVX4A5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:IIO77B3CD7D2HGE7U4Y5SVX4A5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"159799df4b3d1b2ec1b1e65e436ee723257c7b6c93c0a0c063dc8cc016683cef","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-10T16:02:44Z","title_canon_sha256":"5fbae670bb6e42401e1904fe5a81a7a71bb6407acec4e53ace47e3eb61936f30"},"schema_version":"1.0","source":{"id":"1707.02919","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.02919","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"1707.02919v2","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02919","created_at":"2026-05-18T00:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"IIO77B3CD7D2","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"IIO77B3CD7D2HGE7","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"IIO77B3C","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:e9865c4dc07e0367957d4dce152470aca0f618677408c310d5835549b10bb2d8","target":"graph","created_at":"2026-05-18T00:39:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The amount of text that is generated every day is increasing dramatically. This tremendous volume of mostly unstructured text cannot be simply processed and perceived by computers. Therefore, efficient and effective techniques and algorithms are required to discover useful patterns. Text mining is the task of extracting meaningful information from text, which has gained significant attentions in recent years. In this paper, we describe several of the most fundamental text mining tasks and techniques including text pre-processing, classification and clustering. Additionally, we briefly explain ","authors_text":"Elizabeth D. Trippe, Juan B. Gutierrez, Krys Kochut, Mehdi Allahyari, Mehdi Assefi, Saied Safaei, Seyedamin Pouriyeh","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-10T16:02:44Z","title":"A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02919","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab003b3ca46d46f0bf6679c0361005ad0eb6a71293b22038d5ccc3dc07699bc8","target":"record","created_at":"2026-05-18T00:39:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"159799df4b3d1b2ec1b1e65e436ee723257c7b6c93c0a0c063dc8cc016683cef","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-10T16:02:44Z","title_canon_sha256":"5fbae670bb6e42401e1904fe5a81a7a71bb6407acec4e53ace47e3eb61936f30"},"schema_version":"1.0","source":{"id":"1707.02919","kind":"arxiv","version":2}},"canonical_sha256":"421dff87621fc7a3989fa731d956fc0751941ca9be7c90ea0df17a0ba126a395","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"421dff87621fc7a3989fa731d956fc0751941ca9be7c90ea0df17a0ba126a395","first_computed_at":"2026-05-18T00:39:17.648145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:17.648145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3IeHiHbdGKQh46fNLwzMnFRmLmkjOcpUg5c9EmIqcBW2S7/0THZmhQDblVzvQtMul8MvhmpOm33UWfZAgyUgBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:17.648928Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.02919","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab003b3ca46d46f0bf6679c0361005ad0eb6a71293b22038d5ccc3dc07699bc8","sha256:e9865c4dc07e0367957d4dce152470aca0f618677408c310d5835549b10bb2d8"],"state_sha256":"6b2f638b795daa4540e6addc0281967f2e2559b03dbf951ff36ef73efd7c249f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UeCqHNXUPJNv6fnPLGkRNHvYOrifGanqobLWuX6BqfsIY8p6UgoSGJbp8p+Zz/YOGpkbwUMrucmqtARS6paKCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:17:19.759650Z","bundle_sha256":"69c4c40903b15c09d4f31fc5ee3347bd1cf286b0ddd63c6cb9172932eb03a21f"}}