{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PSEWPCJYZXFPNUWQHXJ3AJVSM6","short_pith_number":"pith:PSEWPCJY","canonical_record":{"source":{"id":"1902.03402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-02-09T10:32:45Z","cross_cats_sorted":[],"title_canon_sha256":"65ba0186787f77ae5d249a804819eb00704255939804ff921e78ed0ea3da9133","abstract_canon_sha256":"e0677a66a7e11aa7eeb3593c3cb6442a7196c4ebef68815b34f26f6a3a5e411e"},"schema_version":"1.0"},"canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","source":{"kind":"arxiv","id":"1902.03402","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.03402","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"1902.03402v1","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03402","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"PSEWPCJYZXFP","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PSEWPCJYZXFPNUWQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PSEWPCJY","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PSEWPCJYZXFPNUWQHXJ3AJVSM6","target":"record","payload":{"canonical_record":{"source":{"id":"1902.03402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-02-09T10:32:45Z","cross_cats_sorted":[],"title_canon_sha256":"65ba0186787f77ae5d249a804819eb00704255939804ff921e78ed0ea3da9133","abstract_canon_sha256":"e0677a66a7e11aa7eeb3593c3cb6442a7196c4ebef68815b34f26f6a3a5e411e"},"schema_version":"1.0"},"canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:20.965877Z","signature_b64":"8lGkyDpQ1Rk+wWHfu3jsnn0z8Rq1tXRApYqDAWtUr2pdpLP9nopTfFc79n9FfmI8hNKXDToA8wGgJbQOdovGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","last_reissued_at":"2026-05-17T23:54:20.965263Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:20.965263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.03402","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":"2026-05-17T23:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vi3gz4OW4Dg2Gpxn8yqRNFpu4sPTJYJGGwTxmexu48hCpnO82boKyGl8b0pYCOpd05i787b2/Bvgn6RjkvIXBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:47:19.178278Z"},"content_sha256":"0bbc0bb747d0e635241145a3356c6deea08a2cb4f7cfe980273d7c5718317325","schema_version":"1.0","event_id":"sha256:0bbc0bb747d0e635241145a3356c6deea08a2cb4f7cfe980273d7c5718317325"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PSEWPCJYZXFPNUWQHXJ3AJVSM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A new simple and effective measure for bag-of-word inter-document similarity measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gholamreza Haffari, Kai Ming Ting, Sunil Aryal, Takashi Washio","submitted_at":"2019-02-09T10:32:45Z","abstract_excerpt":"To measure the similarity of two documents in the bag-of-words (BoW) vector representation, different term weighting schemes are used to improve the performance of cosine similarity---the most widely used inter-document similarity measure in text mining. In this paper, we identify the shortcomings of the underlying assumptions of term weighting in the inter-document similarity measurement task; and provide a more fit-to-the-purpose alternative. Based on this new assumption, we introduce a new simple but effective similarity measure which does not require explicit term weighting. The proposed m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03402","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":"2026-05-17T23:54:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4EaclWsskAo9M9YXsN038LnUdB5lp2OSVQq75KJWaf6go7p5MhdZWf7DD8h3XPK6ahruUS2BDINjUiagIF4pBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:47:19.178646Z"},"content_sha256":"b5fb284296db1af3ce5c05bf80ad19317082101774f5f391f18bc5e6ef95ab34","schema_version":"1.0","event_id":"sha256:b5fb284296db1af3ce5c05bf80ad19317082101774f5f391f18bc5e6ef95ab34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/bundle.json","state_url":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/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":"2026-06-05T00:47:19Z","links":{"resolver":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6","bundle":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/bundle.json","state":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PSEWPCJYZXFPNUWQHXJ3AJVSM6","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":"e0677a66a7e11aa7eeb3593c3cb6442a7196c4ebef68815b34f26f6a3a5e411e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-02-09T10:32:45Z","title_canon_sha256":"65ba0186787f77ae5d249a804819eb00704255939804ff921e78ed0ea3da9133"},"schema_version":"1.0","source":{"id":"1902.03402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.03402","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"arxiv_version","alias_value":"1902.03402v1","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03402","created_at":"2026-05-17T23:54:20Z"},{"alias_kind":"pith_short_12","alias_value":"PSEWPCJYZXFP","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PSEWPCJYZXFPNUWQ","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PSEWPCJY","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:b5fb284296db1af3ce5c05bf80ad19317082101774f5f391f18bc5e6ef95ab34","target":"graph","created_at":"2026-05-17T23:54:20Z","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":"To measure the similarity of two documents in the bag-of-words (BoW) vector representation, different term weighting schemes are used to improve the performance of cosine similarity---the most widely used inter-document similarity measure in text mining. In this paper, we identify the shortcomings of the underlying assumptions of term weighting in the inter-document similarity measurement task; and provide a more fit-to-the-purpose alternative. Based on this new assumption, we introduce a new simple but effective similarity measure which does not require explicit term weighting. The proposed m","authors_text":"Gholamreza Haffari, Kai Ming Ting, Sunil Aryal, Takashi Washio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-02-09T10:32:45Z","title":"A new simple and effective measure for bag-of-word inter-document similarity measurement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03402","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":"sha256:0bbc0bb747d0e635241145a3356c6deea08a2cb4f7cfe980273d7c5718317325","target":"record","created_at":"2026-05-17T23:54:20Z","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":"e0677a66a7e11aa7eeb3593c3cb6442a7196c4ebef68815b34f26f6a3a5e411e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-02-09T10:32:45Z","title_canon_sha256":"65ba0186787f77ae5d249a804819eb00704255939804ff921e78ed0ea3da9133"},"schema_version":"1.0","source":{"id":"1902.03402","kind":"arxiv","version":1}},"canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","first_computed_at":"2026-05-17T23:54:20.965263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:20.965263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8lGkyDpQ1Rk+wWHfu3jsnn0z8Rq1tXRApYqDAWtUr2pdpLP9nopTfFc79n9FfmI8hNKXDToA8wGgJbQOdovGBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:20.965877Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.03402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bbc0bb747d0e635241145a3356c6deea08a2cb4f7cfe980273d7c5718317325","sha256:b5fb284296db1af3ce5c05bf80ad19317082101774f5f391f18bc5e6ef95ab34"],"state_sha256":"0d490d818fc9fa641994a7641005722fe6210463c5a2c414e5592b0826bd33e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MhBLQjdhOIbSyqiIQvDThqYeculEU1eIdFL67Y6bU0miBwIETJaQxftbrThMUvoOFvfwzqx4hnUy3pRSZo7BCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:47:19.180643Z","bundle_sha256":"7db6772081f4184878e76cb2eaeb22912c1b37524ebf0060690d12bebae98024"}}