{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BNKMU2MP57BE3UZEFQTY7GPHRL","short_pith_number":"pith:BNKMU2MP","canonical_record":{"source":{"id":"2101.08382","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T01:10:06Z","cross_cats_sorted":[],"title_canon_sha256":"0bfcd6c53fcda8ee3a14f762f9ffb2b6974b8f9b17906e4860bfd4af16c17609","abstract_canon_sha256":"d276a30bbcbbfb71694ac029a9d8995f9d34ca79bf47987c48d974e103b467f2"},"schema_version":"1.0"},"canonical_sha256":"0b54ca698fefc24dd3242c278f99e78ac571b6e6465e3b4d083a9b8405ecb55c","source":{"kind":"arxiv","id":"2101.08382","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08382","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08382v2","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08382","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"BNKMU2MP57BE","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"BNKMU2MP57BE3UZE","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"BNKMU2MP","created_at":"2026-07-05T02:13:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BNKMU2MP57BE3UZEFQTY7GPHRL","target":"record","payload":{"canonical_record":{"source":{"id":"2101.08382","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T01:10:06Z","cross_cats_sorted":[],"title_canon_sha256":"0bfcd6c53fcda8ee3a14f762f9ffb2b6974b8f9b17906e4860bfd4af16c17609","abstract_canon_sha256":"d276a30bbcbbfb71694ac029a9d8995f9d34ca79bf47987c48d974e103b467f2"},"schema_version":"1.0"},"canonical_sha256":"0b54ca698fefc24dd3242c278f99e78ac571b6e6465e3b4d083a9b8405ecb55c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:04.702979Z","signature_b64":"qW3qPYDybF3cS8WkpGIk5YVoI1myQihEEKd6Yp6y2okH1DXiSt2efUMv2CZik2zo0nL+gi3Q+XJrU9Vu3s5KCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b54ca698fefc24dd3242c278f99e78ac571b6e6465e3b4d083a9b8405ecb55c","last_reissued_at":"2026-07-05T02:13:04.702445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:04.702445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.08382","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":"2026-07-05T02:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NpEknOhF+zOKuhyASwDXS/6uJ6fnsx8Agk8fev/KBwyJl2kYlKFgrtZNCiUUj9MrD00uIoVnRPNKoNKOVJZtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:23:27.023239Z"},"content_sha256":"2d2d0463641f6a0acad02e40af3f08ec43d726935490fb81ee4fd12e1eb982ff","schema_version":"1.0","event_id":"sha256:2d2d0463641f6a0acad02e40af3f08ec43d726935490fb81ee4fd12e1eb982ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BNKMU2MP57BE3UZEFQTY7GPHRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qingxiu Dong, Xiaojun Wan, Yue Cao","submitted_at":"2021-01-21T01:10:06Z","abstract_excerpt":"We propose ParaSCI, the first large-scale paraphrase dataset in the scientific field, including 33,981 paraphrase pairs from ACL (ParaSCI-ACL) and 316,063 pairs from arXiv (ParaSCI-arXiv). Digging into characteristics and common patterns of scientific papers, we construct this dataset though intra-paper and inter-paper methods, such as collecting citations to the same paper or aggregating definitions by scientific terms. To take advantage of sentences paraphrased partially, we put up PDBERT as a general paraphrase discovering method. The major advantages of paraphrases in ParaSCI lie in the pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08382","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/2101.08382/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":"2026-07-05T02:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jNf17u22VEDYDTnOr0vOnsIZC1xhwa3paFVN2gZPLeLmP36SnNq7wsAtFc+g4WjYisqAU9xvEEtuns6Z4QSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:23:27.023746Z"},"content_sha256":"5a9f474bb1ac42a114d7c1b00a898c1a256e0e5dbe8b08fae125b5745e02e29f","schema_version":"1.0","event_id":"sha256:5a9f474bb1ac42a114d7c1b00a898c1a256e0e5dbe8b08fae125b5745e02e29f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNKMU2MP57BE3UZEFQTY7GPHRL/bundle.json","state_url":"https://pith.science/pith/BNKMU2MP57BE3UZEFQTY7GPHRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNKMU2MP57BE3UZEFQTY7GPHRL/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":"2026-08-20T04:23:27Z","links":{"resolver":"https://pith.science/pith/BNKMU2MP57BE3UZEFQTY7GPHRL","bundle":"https://pith.science/pith/BNKMU2MP57BE3UZEFQTY7GPHRL/bundle.json","state":"https://pith.science/pith/BNKMU2MP57BE3UZEFQTY7GPHRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNKMU2MP57BE3UZEFQTY7GPHRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BNKMU2MP57BE3UZEFQTY7GPHRL","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":"d276a30bbcbbfb71694ac029a9d8995f9d34ca79bf47987c48d974e103b467f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T01:10:06Z","title_canon_sha256":"0bfcd6c53fcda8ee3a14f762f9ffb2b6974b8f9b17906e4860bfd4af16c17609"},"schema_version":"1.0","source":{"id":"2101.08382","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08382","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08382v2","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08382","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"BNKMU2MP57BE","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"BNKMU2MP57BE3UZE","created_at":"2026-07-05T02:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"BNKMU2MP","created_at":"2026-07-05T02:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:5a9f474bb1ac42a114d7c1b00a898c1a256e0e5dbe8b08fae125b5745e02e29f","target":"graph","created_at":"2026-07-05T02:13:04Z","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/2101.08382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose ParaSCI, the first large-scale paraphrase dataset in the scientific field, including 33,981 paraphrase pairs from ACL (ParaSCI-ACL) and 316,063 pairs from arXiv (ParaSCI-arXiv). Digging into characteristics and common patterns of scientific papers, we construct this dataset though intra-paper and inter-paper methods, such as collecting citations to the same paper or aggregating definitions by scientific terms. To take advantage of sentences paraphrased partially, we put up PDBERT as a general paraphrase discovering method. The major advantages of paraphrases in ParaSCI lie in the pr","authors_text":"Qingxiu Dong, Xiaojun Wan, Yue Cao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T01:10:06Z","title":"ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08382","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":"sha256:2d2d0463641f6a0acad02e40af3f08ec43d726935490fb81ee4fd12e1eb982ff","target":"record","created_at":"2026-07-05T02:13:04Z","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":"d276a30bbcbbfb71694ac029a9d8995f9d34ca79bf47987c48d974e103b467f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T01:10:06Z","title_canon_sha256":"0bfcd6c53fcda8ee3a14f762f9ffb2b6974b8f9b17906e4860bfd4af16c17609"},"schema_version":"1.0","source":{"id":"2101.08382","kind":"arxiv","version":2}},"canonical_sha256":"0b54ca698fefc24dd3242c278f99e78ac571b6e6465e3b4d083a9b8405ecb55c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b54ca698fefc24dd3242c278f99e78ac571b6e6465e3b4d083a9b8405ecb55c","first_computed_at":"2026-07-05T02:13:04.702445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:04.702445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qW3qPYDybF3cS8WkpGIk5YVoI1myQihEEKd6Yp6y2okH1DXiSt2efUMv2CZik2zo0nL+gi3Q+XJrU9Vu3s5KCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:04.702979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.08382","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d2d0463641f6a0acad02e40af3f08ec43d726935490fb81ee4fd12e1eb982ff","sha256:5a9f474bb1ac42a114d7c1b00a898c1a256e0e5dbe8b08fae125b5745e02e29f"],"state_sha256":"537a54eb9ab720eb62fb4b8e7d848815a3dc4004cb3fc00e455312e079f1b3b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVpUEjAvQwBKzX0xa8kxADOoC3wiYD0dCDejAsL9HHqlkD7+8FcPLlzr8S+Oon7zGia0iEGqZ9URUFw02kWiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:23:27.027461Z","bundle_sha256":"02844b9a7af0af002e4b9a68292a59cb4655ed8989db93cb694c451e4854b18e"}}