{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GBD2MV6JE64FSJ2WOHBX3WUHVI","short_pith_number":"pith:GBD2MV6J","canonical_record":{"source":{"id":"2111.07119","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T14:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"f260f16c0f8cfa0598465c590408838b27b744f6edeccac4c17e22126f2ab46a","abstract_canon_sha256":"6b1fba6a78736c9e3c4f0ebcea5f1572b5387fc377bdf51e2868b2bd8d772284"},"schema_version":"1.0"},"canonical_sha256":"3047a657c927b859275671c37dda87aa013bdacfa61494022a41b945e42f8138","source":{"kind":"arxiv","id":"2111.07119","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07119","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07119v1","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07119","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"pith_short_12","alias_value":"GBD2MV6JE64F","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"pith_short_16","alias_value":"GBD2MV6JE64FSJ2W","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"pith_short_8","alias_value":"GBD2MV6J","created_at":"2026-07-05T03:31:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GBD2MV6JE64FSJ2WOHBX3WUHVI","target":"record","payload":{"canonical_record":{"source":{"id":"2111.07119","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T14:06:37Z","cross_cats_sorted":[],"title_canon_sha256":"f260f16c0f8cfa0598465c590408838b27b744f6edeccac4c17e22126f2ab46a","abstract_canon_sha256":"6b1fba6a78736c9e3c4f0ebcea5f1572b5387fc377bdf51e2868b2bd8d772284"},"schema_version":"1.0"},"canonical_sha256":"3047a657c927b859275671c37dda87aa013bdacfa61494022a41b945e42f8138","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:36.146859Z","signature_b64":"naUezfWA6U2CXemimY0tAkSBLFtrtXzQaJEREJ+6O0ecAXCvCH8L2/HUXw85yaiaEcDeURdK1iyfEGX6smNdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3047a657c927b859275671c37dda87aa013bdacfa61494022a41b945e42f8138","last_reissued_at":"2026-07-05T03:31:36.146525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:36.146525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.07119","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":"2026-07-05T03:31:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GK6cjLm4eiFb+6wgj0/ycwl/1ef574hJtXVmGgwurPcVULV1+mMcLBZnWPfVeMknM2MGc//AN8DYCYW2fPucAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:43:24.392072Z"},"content_sha256":"f7d37e581438031a8292647e31a05c9bb374785a58293a9aaf295aed5a52da99","schema_version":"1.0","event_id":"sha256:f7d37e581438031a8292647e31a05c9bb374785a58293a9aaf295aed5a52da99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GBD2MV6JE64FSJ2WOHBX3WUHVI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extracting and filtering paraphrases by bridging natural language inference and paraphrasing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marko Robnik-\\v{S}ikonja, Matej Klemen","submitted_at":"2021-11-13T14:06:37Z","abstract_excerpt":"Paraphrasing is a useful natural language processing task that can contribute to more diverse generated or translated texts. Natural language inference (NLI) and paraphrasing share some similarities and can benefit from a joint approach. We propose a novel methodology for the extraction of paraphrasing datasets from NLI datasets and cleaning existing paraphrasing datasets. Our approach is based on bidirectional entailment; namely, if two sentences can be mutually entailed, they are paraphrases. We evaluate our approach using several large pretrained transformer language models in the monolingu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07119","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.07119/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":"2026-07-05T03:31:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErYtKiBPk+ZTtZ0l0Lq3A3U2lkHEKtQvPYg1jFbpebEwmkU6wLYFoVf+/L8OkP8/mgujS3hHTEw7a1SfEytHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:43:24.392450Z"},"content_sha256":"5156f3fac07aed823c7387457c46074cf21f1f3bc6dac13d7cd2dcf9b4bd232f","schema_version":"1.0","event_id":"sha256:5156f3fac07aed823c7387457c46074cf21f1f3bc6dac13d7cd2dcf9b4bd232f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI/bundle.json","state_url":"https://pith.science/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI/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":"2026-07-05T10:43:24Z","links":{"resolver":"https://pith.science/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI","bundle":"https://pith.science/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI/bundle.json","state":"https://pith.science/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBD2MV6JE64FSJ2WOHBX3WUHVI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GBD2MV6JE64FSJ2WOHBX3WUHVI","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":"6b1fba6a78736c9e3c4f0ebcea5f1572b5387fc377bdf51e2868b2bd8d772284","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T14:06:37Z","title_canon_sha256":"f260f16c0f8cfa0598465c590408838b27b744f6edeccac4c17e22126f2ab46a"},"schema_version":"1.0","source":{"id":"2111.07119","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.07119","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"arxiv_version","alias_value":"2111.07119v1","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.07119","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"pith_short_12","alias_value":"GBD2MV6JE64F","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"pith_short_16","alias_value":"GBD2MV6JE64FSJ2W","created_at":"2026-07-05T03:31:36Z"},{"alias_kind":"pith_short_8","alias_value":"GBD2MV6J","created_at":"2026-07-05T03:31:36Z"}],"graph_snapshots":[{"event_id":"sha256:5156f3fac07aed823c7387457c46074cf21f1f3bc6dac13d7cd2dcf9b4bd232f","target":"graph","created_at":"2026-07-05T03:31:36Z","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/2111.07119/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Paraphrasing is a useful natural language processing task that can contribute to more diverse generated or translated texts. Natural language inference (NLI) and paraphrasing share some similarities and can benefit from a joint approach. We propose a novel methodology for the extraction of paraphrasing datasets from NLI datasets and cleaning existing paraphrasing datasets. Our approach is based on bidirectional entailment; namely, if two sentences can be mutually entailed, they are paraphrases. We evaluate our approach using several large pretrained transformer language models in the monolingu","authors_text":"Marko Robnik-\\v{S}ikonja, Matej Klemen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T14:06:37Z","title":"Extracting and filtering paraphrases by bridging natural language inference and paraphrasing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.07119","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:f7d37e581438031a8292647e31a05c9bb374785a58293a9aaf295aed5a52da99","target":"record","created_at":"2026-07-05T03:31:36Z","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":"6b1fba6a78736c9e3c4f0ebcea5f1572b5387fc377bdf51e2868b2bd8d772284","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-13T14:06:37Z","title_canon_sha256":"f260f16c0f8cfa0598465c590408838b27b744f6edeccac4c17e22126f2ab46a"},"schema_version":"1.0","source":{"id":"2111.07119","kind":"arxiv","version":1}},"canonical_sha256":"3047a657c927b859275671c37dda87aa013bdacfa61494022a41b945e42f8138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3047a657c927b859275671c37dda87aa013bdacfa61494022a41b945e42f8138","first_computed_at":"2026-07-05T03:31:36.146525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:31:36.146525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"naUezfWA6U2CXemimY0tAkSBLFtrtXzQaJEREJ+6O0ecAXCvCH8L2/HUXw85yaiaEcDeURdK1iyfEGX6smNdBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:31:36.146859Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.07119","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7d37e581438031a8292647e31a05c9bb374785a58293a9aaf295aed5a52da99","sha256:5156f3fac07aed823c7387457c46074cf21f1f3bc6dac13d7cd2dcf9b4bd232f"],"state_sha256":"ee69278f4e626ed9c2149d848127eab4ebeb94c2c44c9bf87726c823028b109d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3myO/EAG/e3F9BJrualPoHzZRBnIL8YK3IDX+cBJzPP9LwjZyEjfty2MHS5ZfBEKSmuwzqqb8iBL1TgzCLRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T10:43:24.394422Z","bundle_sha256":"554e86352de5767aa3a71a42824a6ef2757d1036b6ff24a67995becb0aa211f5"}}