{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2MZWHCXWKDNE5QI4MCKXGFRUKS","short_pith_number":"pith:2MZWHCXW","canonical_record":{"source":{"id":"2006.02648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T05:43:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a0abe2645abcb4b0f4e1f996abb997dd3ab3c92a2d9c33df0b0c0dcda267987","abstract_canon_sha256":"62128233050f7d39b4ac8b325aed84b3b1c3e47e75dc73f0812f6b2cd625fc44"},"schema_version":"1.0"},"canonical_sha256":"d333638af650da4ec11c609573163454a8aa7101c8a61cb8a412a322ea2460d2","source":{"kind":"arxiv","id":"2006.02648","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.02648","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.02648v2","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02648","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"2MZWHCXWKDNE","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"2MZWHCXWKDNE5QI4","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"2MZWHCXW","created_at":"2026-07-05T01:08:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2MZWHCXWKDNE5QI4MCKXGFRUKS","target":"record","payload":{"canonical_record":{"source":{"id":"2006.02648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T05:43:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a0abe2645abcb4b0f4e1f996abb997dd3ab3c92a2d9c33df0b0c0dcda267987","abstract_canon_sha256":"62128233050f7d39b4ac8b325aed84b3b1c3e47e75dc73f0812f6b2cd625fc44"},"schema_version":"1.0"},"canonical_sha256":"d333638af650da4ec11c609573163454a8aa7101c8a61cb8a412a322ea2460d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:14.185357Z","signature_b64":"v4M3J2aGXIwr3pPyJXClkZX0QKYJV23gESboT3TlnTGpkfUtxf8pEj8KscKTuVQ8A3a8CKcWwJyzP0Lvy+PqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d333638af650da4ec11c609573163454a8aa7101c8a61cb8a412a322ea2460d2","last_reissued_at":"2026-07-05T01:08:14.184799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:14.184799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.02648","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":"2026-07-05T01:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8aa1SGT7k9WI90bmljJfhgsnxSZBkbtQQw937wLRjYCdzP2NrtI9xAGgUbDNw/irrgPyAYMFh0rQ/ZgqoWc7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:58:12.168650Z"},"content_sha256":"cdab3a2ec33ad569e51648c3feb93548bff89e2a58a1c988c664fb55a480d680","schema_version":"1.0","event_id":"sha256:cdab3a2ec33ad569e51648c3feb93548bff89e2a58a1c988c664fb55a480d680"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2MZWHCXWKDNE5QI4MCKXGFRUKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Experiments on Paraphrase Identification Using Quora Question Pairs Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andreas Chandra, Ruben Stefanus","submitted_at":"2020-06-04T05:43:25Z","abstract_excerpt":"We modeled the Quora question pairs dataset to identify a similar question. The dataset that we use is provided by Quora. The task is a binary classification. We tried several methods and algorithms and different approach from previous works. For feature extraction, we used Bag of Words including Count Vectorizer, and Term Frequency-Inverse Document Frequency with unigram for XGBoost and CatBoost. Furthermore, we also experimented with WordPiece tokenizer which improves the model performance significantly. We achieved up to 97 percent accuracy. Code and Dataset."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02648","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.02648/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcxTRRC7pM7SMfOfI3Gmy2J4hLvQdvpKksNll/BYkE57sVlodZLio/NMvjvUFf5lyJwPfOJUCzyhoqzUjpFQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T23:58:12.169198Z"},"content_sha256":"01a970fea78f1458e096b0eb2ddc71ab6b58203d9ca392b78f5fc1a449d629ae","schema_version":"1.0","event_id":"sha256:01a970fea78f1458e096b0eb2ddc71ab6b58203d9ca392b78f5fc1a449d629ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS/bundle.json","state_url":"https://pith.science/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS/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":"2026-08-19T23:58:12Z","links":{"resolver":"https://pith.science/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS","bundle":"https://pith.science/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS/bundle.json","state":"https://pith.science/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MZWHCXWKDNE5QI4MCKXGFRUKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2MZWHCXWKDNE5QI4MCKXGFRUKS","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":"62128233050f7d39b4ac8b325aed84b3b1c3e47e75dc73f0812f6b2cd625fc44","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T05:43:25Z","title_canon_sha256":"0a0abe2645abcb4b0f4e1f996abb997dd3ab3c92a2d9c33df0b0c0dcda267987"},"schema_version":"1.0","source":{"id":"2006.02648","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.02648","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2006.02648v2","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.02648","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"2MZWHCXWKDNE","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"2MZWHCXWKDNE5QI4","created_at":"2026-07-05T01:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"2MZWHCXW","created_at":"2026-07-05T01:08:14Z"}],"graph_snapshots":[{"event_id":"sha256:01a970fea78f1458e096b0eb2ddc71ab6b58203d9ca392b78f5fc1a449d629ae","target":"graph","created_at":"2026-07-05T01:08:14Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.02648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We modeled the Quora question pairs dataset to identify a similar question. The dataset that we use is provided by Quora. The task is a binary classification. We tried several methods and algorithms and different approach from previous works. For feature extraction, we used Bag of Words including Count Vectorizer, and Term Frequency-Inverse Document Frequency with unigram for XGBoost and CatBoost. Furthermore, we also experimented with WordPiece tokenizer which improves the model performance significantly. We achieved up to 97 percent accuracy. Code and Dataset.","authors_text":"Andreas Chandra, Ruben Stefanus","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T05:43:25Z","title":"Experiments on Paraphrase Identification Using Quora Question Pairs Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.02648","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:cdab3a2ec33ad569e51648c3feb93548bff89e2a58a1c988c664fb55a480d680","target":"record","created_at":"2026-07-05T01:08:14Z","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":"62128233050f7d39b4ac8b325aed84b3b1c3e47e75dc73f0812f6b2cd625fc44","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-06-04T05:43:25Z","title_canon_sha256":"0a0abe2645abcb4b0f4e1f996abb997dd3ab3c92a2d9c33df0b0c0dcda267987"},"schema_version":"1.0","source":{"id":"2006.02648","kind":"arxiv","version":2}},"canonical_sha256":"d333638af650da4ec11c609573163454a8aa7101c8a61cb8a412a322ea2460d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d333638af650da4ec11c609573163454a8aa7101c8a61cb8a412a322ea2460d2","first_computed_at":"2026-07-05T01:08:14.184799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:08:14.184799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v4M3J2aGXIwr3pPyJXClkZX0QKYJV23gESboT3TlnTGpkfUtxf8pEj8KscKTuVQ8A3a8CKcWwJyzP0Lvy+PqDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:08:14.185357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.02648","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdab3a2ec33ad569e51648c3feb93548bff89e2a58a1c988c664fb55a480d680","sha256:01a970fea78f1458e096b0eb2ddc71ab6b58203d9ca392b78f5fc1a449d629ae"],"state_sha256":"4a4276782aa8b3b4d771c12dc258e03905c1c5c9db5bc30894e417e9ed4b9ba6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3f5acxE0c2BE0AwnQFQraf/02ePkqBnsI0DCvkEZen6DH1L9AkhopSjYCl09Wnx0QouiBsrOacv9nfQqINvWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T23:58:12.173491Z","bundle_sha256":"a2cf351373ea2398bfb595008141f7b0c0a96ec562a03a817fca63caccc53a5c"}}