{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:55ZTWZG4RTHETJEJFJ4CJC7U4W","short_pith_number":"pith:55ZTWZG4","canonical_record":{"source":{"id":"1406.1580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-06T04:37:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"faf85430a918b90108ce853f891f28a9eca24a6a961f5faf9d9751812ba49a28","abstract_canon_sha256":"c8a46a95f7daac1be6ce077072942fcc21b2c5e830c2e5f098e6a0b796b6b034"},"schema_version":"1.0"},"canonical_sha256":"ef733b64dc8cce49a4892a78248bf4e5a54e7c1c5fe32f1d422bc575d94148fa","source":{"kind":"arxiv","id":"1406.1580","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.1580","created_at":"2026-05-18T02:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"1406.1580v1","created_at":"2026-05-18T02:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1580","created_at":"2026-05-18T02:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"55ZTWZG4RTHE","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"55ZTWZG4RTHETJEJ","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"55ZTWZG4","created_at":"2026-05-18T12:28:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:55ZTWZG4RTHETJEJFJ4CJC7U4W","target":"record","payload":{"canonical_record":{"source":{"id":"1406.1580","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-06T04:37:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"faf85430a918b90108ce853f891f28a9eca24a6a961f5faf9d9751812ba49a28","abstract_canon_sha256":"c8a46a95f7daac1be6ce077072942fcc21b2c5e830c2e5f098e6a0b796b6b034"},"schema_version":"1.0"},"canonical_sha256":"ef733b64dc8cce49a4892a78248bf4e5a54e7c1c5fe32f1d422bc575d94148fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:50:22.192779Z","signature_b64":"bdIfHOLduxxRtvzkO+rRVAquPjvPW9lnHJ3FKvlcXJFZ6JnWSBRXCSMi/sFHhO+Qwg/oz9FKP1fGSb4m5xQEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef733b64dc8cce49a4892a78248bf4e5a54e7c1c5fe32f1d422bc575d94148fa","last_reissued_at":"2026-05-18T02:50:22.192355Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:50:22.192355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1406.1580","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:50:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BHpvK9qc+EgCRNE1ewgPKjcYOy2evsLU65iYFCr74gtpv0gWgrc1yRO6KNXTplezUq/lM6E4JwKj48aKesJ3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:08:12.681874Z"},"content_sha256":"94b44d773facf4da68d3246ded6fc32cd2a68a31e0ecf2fd31a6ceca47e9f7cc","schema_version":"1.0","event_id":"sha256:94b44d773facf4da68d3246ded6fc32cd2a68a31e0ecf2fd31a6ceca47e9f7cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:55ZTWZG4RTHETJEJFJ4CJC7U4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Machine learning approach for text and document mining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Jordan Pascual, Pinki Kumari, Vijay Bhaskar Semwal, Vishwanath Bijalwan","submitted_at":"2014-06-06T04:37:19Z","abstract_excerpt":"Text Categorization (TC), also known as Text Classification, is the task of automatically classifying a set of text documents into different categories from a predefined set. If a document belongs to exactly one of the categories, it is a single-label classification task; otherwise, it is a multi-label classification task. TC uses several tools from Information Retrieval (IR) and Machine Learning (ML) and has received much attention in the last years from both researchers in the academia and industry developers. In this paper, we first categorize the documents using KNN based machine learning "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1580","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":""},"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":"2026-05-18T02:50:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjTMrQ79Ye+jgEt8kEhwTLsBTLe3JI7JCdZWM6nqtwmmM5+Cbd0oSkyY6ih+nnF5E8Cott87d5FmcLh/fqbBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-03T17:08:12.682212Z"},"content_sha256":"225cc629010d76c8ca9219e3c2e3a93667d03b2222bf8fa9f1516c79130143bf","schema_version":"1.0","event_id":"sha256:225cc629010d76c8ca9219e3c2e3a93667d03b2222bf8fa9f1516c79130143bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W/bundle.json","state_url":"https://pith.science/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W/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":"2026-07-03T17:08:12Z","links":{"resolver":"https://pith.science/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W","bundle":"https://pith.science/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W/bundle.json","state":"https://pith.science/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55ZTWZG4RTHETJEJFJ4CJC7U4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:55ZTWZG4RTHETJEJFJ4CJC7U4W","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":"c8a46a95f7daac1be6ce077072942fcc21b2c5e830c2e5f098e6a0b796b6b034","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-06T04:37:19Z","title_canon_sha256":"faf85430a918b90108ce853f891f28a9eca24a6a961f5faf9d9751812ba49a28"},"schema_version":"1.0","source":{"id":"1406.1580","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.1580","created_at":"2026-05-18T02:50:22Z"},{"alias_kind":"arxiv_version","alias_value":"1406.1580v1","created_at":"2026-05-18T02:50:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1580","created_at":"2026-05-18T02:50:22Z"},{"alias_kind":"pith_short_12","alias_value":"55ZTWZG4RTHE","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"55ZTWZG4RTHETJEJ","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"55ZTWZG4","created_at":"2026-05-18T12:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:225cc629010d76c8ca9219e3c2e3a93667d03b2222bf8fa9f1516c79130143bf","target":"graph","created_at":"2026-05-18T02:50:22Z","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":"Text Categorization (TC), also known as Text Classification, is the task of automatically classifying a set of text documents into different categories from a predefined set. If a document belongs to exactly one of the categories, it is a single-label classification task; otherwise, it is a multi-label classification task. TC uses several tools from Information Retrieval (IR) and Machine Learning (ML) and has received much attention in the last years from both researchers in the academia and industry developers. In this paper, we first categorize the documents using KNN based machine learning ","authors_text":"Jordan Pascual, Pinki Kumari, Vijay Bhaskar Semwal, Vishwanath Bijalwan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-06T04:37:19Z","title":"Machine learning approach for text and document mining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1580","kind":"arxiv","version":1},"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":"sha256:94b44d773facf4da68d3246ded6fc32cd2a68a31e0ecf2fd31a6ceca47e9f7cc","target":"record","created_at":"2026-05-18T02:50:22Z","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":"c8a46a95f7daac1be6ce077072942fcc21b2c5e830c2e5f098e6a0b796b6b034","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2014-06-06T04:37:19Z","title_canon_sha256":"faf85430a918b90108ce853f891f28a9eca24a6a961f5faf9d9751812ba49a28"},"schema_version":"1.0","source":{"id":"1406.1580","kind":"arxiv","version":1}},"canonical_sha256":"ef733b64dc8cce49a4892a78248bf4e5a54e7c1c5fe32f1d422bc575d94148fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef733b64dc8cce49a4892a78248bf4e5a54e7c1c5fe32f1d422bc575d94148fa","first_computed_at":"2026-05-18T02:50:22.192355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:50:22.192355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bdIfHOLduxxRtvzkO+rRVAquPjvPW9lnHJ3FKvlcXJFZ6JnWSBRXCSMi/sFHhO+Qwg/oz9FKP1fGSb4m5xQEBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:50:22.192779Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.1580","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94b44d773facf4da68d3246ded6fc32cd2a68a31e0ecf2fd31a6ceca47e9f7cc","sha256:225cc629010d76c8ca9219e3c2e3a93667d03b2222bf8fa9f1516c79130143bf"],"state_sha256":"cb23f8695dec01782c679112873e054dcb2fb003688fc07faa4de1e4391a4197"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GxMlURgkS6Ngwb3uRP4GDrVSOE7OJY1EUfF4NINeQrpE6opZhK8D0fSo8GwwkW5eTKtaJu30OD5gUQXdPkZYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-03T17:08:12.684061Z","bundle_sha256":"b441816c24db8ca97f949fffafb86619c11e346873adb6b8f2c560b2e4ce8ef2"}}