{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:4X7WYQTC4R2ITXHCYPG5PQ45Q5","short_pith_number":"pith:4X7WYQTC","canonical_record":{"source":{"id":"1211.1107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-11-06T04:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"0198f33480d71c86e5ef151988cdbcbe09cc5bf5175d879d796b5542d27ab1d9","abstract_canon_sha256":"8400bdfa3f6ae2766944a258b8596218fdb914670a836ab1bbe3af0f7aa1aa2d"},"schema_version":"1.0"},"canonical_sha256":"e5ff6c4262e47489dce2c3cdd7c39d8767f740dbd307d7fe2fcdda9bd27bb434","source":{"kind":"arxiv","id":"1211.1107","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1211.1107","created_at":"2026-05-18T03:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1211.1107v1","created_at":"2026-05-18T03:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.1107","created_at":"2026-05-18T03:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"4X7WYQTC4R2I","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4X7WYQTC4R2ITXHC","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4X7WYQTC","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:4X7WYQTC4R2ITXHCYPG5PQ45Q5","target":"record","payload":{"canonical_record":{"source":{"id":"1211.1107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-11-06T04:39:30Z","cross_cats_sorted":[],"title_canon_sha256":"0198f33480d71c86e5ef151988cdbcbe09cc5bf5175d879d796b5542d27ab1d9","abstract_canon_sha256":"8400bdfa3f6ae2766944a258b8596218fdb914670a836ab1bbe3af0f7aa1aa2d"},"schema_version":"1.0"},"canonical_sha256":"e5ff6c4262e47489dce2c3cdd7c39d8767f740dbd307d7fe2fcdda9bd27bb434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:41:22.292990Z","signature_b64":"t3v42PEh5PSW4mBh3w3d7GEoZ40HXV0HmaxuQvgj1DRtThsjW/2fRkIOyNEvquI4dHV5LvZJvooO/eJoPg9TCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5ff6c4262e47489dce2c3cdd7c39d8767f740dbd307d7fe2fcdda9bd27bb434","last_reissued_at":"2026-05-18T03:41:22.292298Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:41:22.292298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1211.1107","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":"2026-05-18T03:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pn5UiEK8Fwu67Jf9K/V4YqM6qw0ljEwLGEBLgHQfrh1R7u3Ec91oCCXxPJtUU4JmhQUNdd83wk7RnYHrkvInBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:14:23.135010Z"},"content_sha256":"3d3253a59f223f7b1dd1153a14b8eba175e5398b33c17e9b31413dd77741f4b9","schema_version":"1.0","event_id":"sha256:3d3253a59f223f7b1dd1153a14b8eba175e5398b33c17e9b31413dd77741f4b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:4X7WYQTC4R2ITXHCYPG5PQ45Q5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An effective web document clustering for information retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"R.K. Roul, S.K. Sahay","submitted_at":"2012-11-06T04:39:30Z","abstract_excerpt":"The size of web has increased exponentially over the past few years with thousands of documents related to a subject available to the user. With this much amount of information available, it is not possible to take the full advantage of the World Wide Web without having a proper framework to search through the available data. This requisite organization can be done in many ways. In this paper we introduce a combine approach to cluster the web pages which first finds the frequent sets and then clusters the documents. These frequent sets are generated by using Frequent Pattern growth technique. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.1107","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":"2026-05-18T03:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fO3qQoxjEiDoDl7qJZnUznAfhzNxktZKDJBzCrKmVSfav9RLvoa5ISgdUmeRRaYaRyEp3bYU4aG0flMy1wIZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:14:23.135383Z"},"content_sha256":"3eaa0bc3c2fcb706e3eacd472c22e8f8a823de2d02886c79b98cc7d504dfa035","schema_version":"1.0","event_id":"sha256:3eaa0bc3c2fcb706e3eacd472c22e8f8a823de2d02886c79b98cc7d504dfa035"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5/bundle.json","state_url":"https://pith.science/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5/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":"2026-07-02T19:14:23Z","links":{"resolver":"https://pith.science/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5","bundle":"https://pith.science/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5/bundle.json","state":"https://pith.science/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4X7WYQTC4R2ITXHCYPG5PQ45Q5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:4X7WYQTC4R2ITXHCYPG5PQ45Q5","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":"8400bdfa3f6ae2766944a258b8596218fdb914670a836ab1bbe3af0f7aa1aa2d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-11-06T04:39:30Z","title_canon_sha256":"0198f33480d71c86e5ef151988cdbcbe09cc5bf5175d879d796b5542d27ab1d9"},"schema_version":"1.0","source":{"id":"1211.1107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1211.1107","created_at":"2026-05-18T03:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1211.1107v1","created_at":"2026-05-18T03:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.1107","created_at":"2026-05-18T03:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"4X7WYQTC4R2I","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4X7WYQTC4R2ITXHC","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4X7WYQTC","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:3eaa0bc3c2fcb706e3eacd472c22e8f8a823de2d02886c79b98cc7d504dfa035","target":"graph","created_at":"2026-05-18T03:41:22Z","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":"The size of web has increased exponentially over the past few years with thousands of documents related to a subject available to the user. With this much amount of information available, it is not possible to take the full advantage of the World Wide Web without having a proper framework to search through the available data. This requisite organization can be done in many ways. In this paper we introduce a combine approach to cluster the web pages which first finds the frequent sets and then clusters the documents. These frequent sets are generated by using Frequent Pattern growth technique. ","authors_text":"R.K. Roul, S.K. Sahay","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-11-06T04:39:30Z","title":"An effective web document clustering for information retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.1107","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":"sha256:3d3253a59f223f7b1dd1153a14b8eba175e5398b33c17e9b31413dd77741f4b9","target":"record","created_at":"2026-05-18T03:41:22Z","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":"8400bdfa3f6ae2766944a258b8596218fdb914670a836ab1bbe3af0f7aa1aa2d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2012-11-06T04:39:30Z","title_canon_sha256":"0198f33480d71c86e5ef151988cdbcbe09cc5bf5175d879d796b5542d27ab1d9"},"schema_version":"1.0","source":{"id":"1211.1107","kind":"arxiv","version":1}},"canonical_sha256":"e5ff6c4262e47489dce2c3cdd7c39d8767f740dbd307d7fe2fcdda9bd27bb434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5ff6c4262e47489dce2c3cdd7c39d8767f740dbd307d7fe2fcdda9bd27bb434","first_computed_at":"2026-05-18T03:41:22.292298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:41:22.292298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t3v42PEh5PSW4mBh3w3d7GEoZ40HXV0HmaxuQvgj1DRtThsjW/2fRkIOyNEvquI4dHV5LvZJvooO/eJoPg9TCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:41:22.292990Z","signed_message":"canonical_sha256_bytes"},"source_id":"1211.1107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d3253a59f223f7b1dd1153a14b8eba175e5398b33c17e9b31413dd77741f4b9","sha256:3eaa0bc3c2fcb706e3eacd472c22e8f8a823de2d02886c79b98cc7d504dfa035"],"state_sha256":"4a233d2d4a37352a7941f98e093f0a05914feef2ad92e5b4d4cb10c1e83fa0b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OPptvhULOwgosjBsMSiX0B9ta/0qhc1kgQGq2m1yiVRr5nQYeB6K81IVwOrESsqMh6bJ4QDDSMoneqsBANGzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T19:14:23.137288Z","bundle_sha256":"7398b7a8316e601ae50a81b054c37f8d622fb73372e59cd731aed511f321e15b"}}