{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:SM66H44QQ4GEWGAUXQAHHVQ36Y","short_pith_number":"pith:SM66H44Q","canonical_record":{"source":{"id":"1708.00391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T15:41:51Z","cross_cats_sorted":[],"title_canon_sha256":"68534ed705becbc952d993e5dd266ef914cdbf9f595253374ad4238ca20e45b2","abstract_canon_sha256":"76175112a416a89eaf133ce58c03a38e4103e8df43da82d6ef62f3562af70ae8"},"schema_version":"1.0"},"canonical_sha256":"933de3f390870c4b1814bc0073d61bf610114a8e73fe9fe5c4e20d4eb75044c6","source":{"kind":"arxiv","id":"1708.00391","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00391","created_at":"2026-05-18T00:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00391v1","created_at":"2026-05-18T00:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00391","created_at":"2026-05-18T00:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"SM66H44QQ4GE","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SM66H44QQ4GEWGAU","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SM66H44Q","created_at":"2026-05-18T12:31:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:SM66H44QQ4GEWGAUXQAHHVQ36Y","target":"record","payload":{"canonical_record":{"source":{"id":"1708.00391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T15:41:51Z","cross_cats_sorted":[],"title_canon_sha256":"68534ed705becbc952d993e5dd266ef914cdbf9f595253374ad4238ca20e45b2","abstract_canon_sha256":"76175112a416a89eaf133ce58c03a38e4103e8df43da82d6ef62f3562af70ae8"},"schema_version":"1.0"},"canonical_sha256":"933de3f390870c4b1814bc0073d61bf610114a8e73fe9fe5c4e20d4eb75044c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:47.452281Z","signature_b64":"EbbkxUqm0lEEgP9/9DJnLTzMKqb3AZa+Y0glIfkABh48D50/ZwzcOA5fldehxS/aT9QaDqYoU9bIeBEYYLz9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"933de3f390870c4b1814bc0073d61bf610114a8e73fe9fe5c4e20d4eb75044c6","last_reissued_at":"2026-05-18T00:38:47.451765Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:47.451765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.00391","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":"2026-05-18T00:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vD/H53dYeCQuNe6K8vqvTb58Hh60aYpOw2hQbKlwr8ExxTGWlJSud9b2Q2Ilk5Gfe+dLvHT9vFxCEIzBSjcyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:33:37.441376Z"},"content_sha256":"ef0c1c52cd59e45cac598e59efcf0117a15c700d058a463e0ba3c5adc50f26e1","schema_version":"1.0","event_id":"sha256:ef0c1c52cd59e45cac598e59efcf0117a15c700d058a463e0ba3c5adc50f26e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:SM66H44QQ4GEWGAUXQAHHVQ36Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Continuously Growing Dataset of Sentential Paraphrases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua He, Siyu Qiu, Wei Xu, Wuwei Lan","submitted_at":"2017-08-01T15:41:51Z","abstract_excerpt":"A major challenge in paraphrase research is the lack of parallel corpora. In this paper, we present a new method to collect large-scale sentential paraphrases from Twitter by linking tweets through shared URLs. The main advantage of our method is its simplicity, as it gets rid of the classifier or human in the loop needed to select data before annotation and subsequent application of paraphrase identification algorithms in the previous work. We present the largest human-labeled paraphrase corpus to date of 51,524 sentence pairs and the first cross-domain benchmarking for automatic paraphrase i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00391","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":"2026-05-18T00:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/mpVFH0dvp/jTjeeI6eX1oK7TUXgonx4L/KSBg7Y7juKQ2JitkF+SaEITWm7yfQmZbfEPbRWt5dACT8ZgCwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T06:33:37.441733Z"},"content_sha256":"6ea58dac63b24a21708749751053c6fa32a6e091933cfa906a96a0ee08c42f7e","schema_version":"1.0","event_id":"sha256:6ea58dac63b24a21708749751053c6fa32a6e091933cfa906a96a0ee08c42f7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y/bundle.json","state_url":"https://pith.science/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y/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":"2026-06-05T06:33:37Z","links":{"resolver":"https://pith.science/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y","bundle":"https://pith.science/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y/bundle.json","state":"https://pith.science/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SM66H44QQ4GEWGAUXQAHHVQ36Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:SM66H44QQ4GEWGAUXQAHHVQ36Y","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":"76175112a416a89eaf133ce58c03a38e4103e8df43da82d6ef62f3562af70ae8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T15:41:51Z","title_canon_sha256":"68534ed705becbc952d993e5dd266ef914cdbf9f595253374ad4238ca20e45b2"},"schema_version":"1.0","source":{"id":"1708.00391","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.00391","created_at":"2026-05-18T00:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"1708.00391v1","created_at":"2026-05-18T00:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00391","created_at":"2026-05-18T00:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"SM66H44QQ4GE","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"SM66H44QQ4GEWGAU","created_at":"2026-05-18T12:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"SM66H44Q","created_at":"2026-05-18T12:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:6ea58dac63b24a21708749751053c6fa32a6e091933cfa906a96a0ee08c42f7e","target":"graph","created_at":"2026-05-18T00:38:47Z","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":"A major challenge in paraphrase research is the lack of parallel corpora. In this paper, we present a new method to collect large-scale sentential paraphrases from Twitter by linking tweets through shared URLs. The main advantage of our method is its simplicity, as it gets rid of the classifier or human in the loop needed to select data before annotation and subsequent application of paraphrase identification algorithms in the previous work. We present the largest human-labeled paraphrase corpus to date of 51,524 sentence pairs and the first cross-domain benchmarking for automatic paraphrase i","authors_text":"Hua He, Siyu Qiu, Wei Xu, Wuwei Lan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T15:41:51Z","title":"A Continuously Growing Dataset of Sentential Paraphrases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00391","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:ef0c1c52cd59e45cac598e59efcf0117a15c700d058a463e0ba3c5adc50f26e1","target":"record","created_at":"2026-05-18T00:38:47Z","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":"76175112a416a89eaf133ce58c03a38e4103e8df43da82d6ef62f3562af70ae8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-08-01T15:41:51Z","title_canon_sha256":"68534ed705becbc952d993e5dd266ef914cdbf9f595253374ad4238ca20e45b2"},"schema_version":"1.0","source":{"id":"1708.00391","kind":"arxiv","version":1}},"canonical_sha256":"933de3f390870c4b1814bc0073d61bf610114a8e73fe9fe5c4e20d4eb75044c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"933de3f390870c4b1814bc0073d61bf610114a8e73fe9fe5c4e20d4eb75044c6","first_computed_at":"2026-05-18T00:38:47.451765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:47.451765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EbbkxUqm0lEEgP9/9DJnLTzMKqb3AZa+Y0glIfkABh48D50/ZwzcOA5fldehxS/aT9QaDqYoU9bIeBEYYLz9AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:47.452281Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.00391","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef0c1c52cd59e45cac598e59efcf0117a15c700d058a463e0ba3c5adc50f26e1","sha256:6ea58dac63b24a21708749751053c6fa32a6e091933cfa906a96a0ee08c42f7e"],"state_sha256":"1ced0f49b9d912e9137f41c1e2936d06d926ae9478ecb49f431ee7fdbaaf5e7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Oi3FtCMK54I1DZfjx/HHUxZF3XXOAX8co+seaSHCUF8y1aB+sNmY6KpYUahUIeCmnXP6vfbbWIqlMtI+E2dBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T06:33:37.443871Z","bundle_sha256":"487e52bdae26050d4bcccfd2c1e67cbc7e86e1a102b5d5f7e0cad5d07e91e608"}}