{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5OAIR5RY2XHMEVCKI7TCMHHL7E","short_pith_number":"pith:5OAIR5RY","canonical_record":{"source":{"id":"1904.01130","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-01T22:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"3ffcb0159d12f777399e8d02993aef988b662da4ef0f6af0ee87a49a3931390b","abstract_canon_sha256":"ed24f169ccc673a617cd87cdb7baa57aa6d22b9d184f5abea53fbe7a8f463194"},"schema_version":"1.0"},"canonical_sha256":"eb8088f638d5cec2544a47e6261cebf91566063013ec333875041d54f4cea759","source":{"kind":"arxiv","id":"1904.01130","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01130","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01130v1","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01130","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"5OAIR5RY2XHM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5OAIR5RY2XHMEVCK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5OAIR5RY","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5OAIR5RY2XHMEVCKI7TCMHHL7E","target":"record","payload":{"canonical_record":{"source":{"id":"1904.01130","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-01T22:21:14Z","cross_cats_sorted":[],"title_canon_sha256":"3ffcb0159d12f777399e8d02993aef988b662da4ef0f6af0ee87a49a3931390b","abstract_canon_sha256":"ed24f169ccc673a617cd87cdb7baa57aa6d22b9d184f5abea53fbe7a8f463194"},"schema_version":"1.0"},"canonical_sha256":"eb8088f638d5cec2544a47e6261cebf91566063013ec333875041d54f4cea759","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:35.834384Z","signature_b64":"YDPp74F5VTi325z4VUjluVTMzmFWDEQ1nPYBxXLXigabA645JU0qNBlbLrnvctAAnrD2OfF8nZ/gD+F1bv9bDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb8088f638d5cec2544a47e6261cebf91566063013ec333875041d54f4cea759","last_reissued_at":"2026-05-17T23:49:35.833711Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:35.833711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.01130","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":"2026-05-17T23:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a3ey+644LKe4kAVBlssHbpFW26lQDvgOEyNzBS2nju/NbV0GmnK8XqwOkUVpunmE1l1LnyBLiEbcHHw4apcgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T03:51:28.005452Z"},"content_sha256":"255ef8dbff67612048685d91e137582743148da7491e8f85344edf6b43336c34","schema_version":"1.0","event_id":"sha256:255ef8dbff67612048685d91e137582743148da7491e8f85344edf6b43336c34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5OAIR5RY2XHMEVCKI7TCMHHL7E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PAWS: Paraphrase Adversaries from Word Scrambling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jason Baldridge, Luheng He, Yuan Zhang","submitted_at":"2019-04-01T22:21:14Z","abstract_excerpt":"Existing paraphrase identification datasets lack sentence pairs that have high lexical overlap without being paraphrases. Models trained on such data fail to distinguish pairs like flights from New York to Florida and flights from Florida to New York. This paper introduces PAWS (Paraphrase Adversaries from Word Scrambling), a new dataset with 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap. Challenging pairs are generated by controlled word swapping and back translation, followed by fluency and paraphrase judgments by human raters. State-of-the-art models trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01130","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":"2026-05-17T23:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0PYKB9FFcevYEG3kpTgzNsk4ONCNyXAlACNVldiF3SqWIGEaVKDs3WPhBhKenNqaLPiKUXAMsYWjd9yCKixTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T03:51:28.005822Z"},"content_sha256":"a39c320dde8c5126f9c9de7686218606296409c4af9478156d607bb622dbd998","schema_version":"1.0","event_id":"sha256:a39c320dde8c5126f9c9de7686218606296409c4af9478156d607bb622dbd998"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E/bundle.json","state_url":"https://pith.science/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E/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":"2026-05-30T03:51:28Z","links":{"resolver":"https://pith.science/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E","bundle":"https://pith.science/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E/bundle.json","state":"https://pith.science/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5OAIR5RY2XHMEVCKI7TCMHHL7E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5OAIR5RY2XHMEVCKI7TCMHHL7E","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":"ed24f169ccc673a617cd87cdb7baa57aa6d22b9d184f5abea53fbe7a8f463194","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-01T22:21:14Z","title_canon_sha256":"3ffcb0159d12f777399e8d02993aef988b662da4ef0f6af0ee87a49a3931390b"},"schema_version":"1.0","source":{"id":"1904.01130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01130","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01130v1","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01130","created_at":"2026-05-17T23:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"5OAIR5RY2XHM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5OAIR5RY2XHMEVCK","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5OAIR5RY","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:a39c320dde8c5126f9c9de7686218606296409c4af9478156d607bb622dbd998","target":"graph","created_at":"2026-05-17T23:49:35Z","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":"Existing paraphrase identification datasets lack sentence pairs that have high lexical overlap without being paraphrases. Models trained on such data fail to distinguish pairs like flights from New York to Florida and flights from Florida to New York. This paper introduces PAWS (Paraphrase Adversaries from Word Scrambling), a new dataset with 108,463 well-formed paraphrase and non-paraphrase pairs with high lexical overlap. Challenging pairs are generated by controlled word swapping and back translation, followed by fluency and paraphrase judgments by human raters. State-of-the-art models trai","authors_text":"Jason Baldridge, Luheng He, Yuan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-01T22:21:14Z","title":"PAWS: Paraphrase Adversaries from Word Scrambling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01130","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":"sha256:255ef8dbff67612048685d91e137582743148da7491e8f85344edf6b43336c34","target":"record","created_at":"2026-05-17T23:49:35Z","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":"ed24f169ccc673a617cd87cdb7baa57aa6d22b9d184f5abea53fbe7a8f463194","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-01T22:21:14Z","title_canon_sha256":"3ffcb0159d12f777399e8d02993aef988b662da4ef0f6af0ee87a49a3931390b"},"schema_version":"1.0","source":{"id":"1904.01130","kind":"arxiv","version":1}},"canonical_sha256":"eb8088f638d5cec2544a47e6261cebf91566063013ec333875041d54f4cea759","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb8088f638d5cec2544a47e6261cebf91566063013ec333875041d54f4cea759","first_computed_at":"2026-05-17T23:49:35.833711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:35.833711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YDPp74F5VTi325z4VUjluVTMzmFWDEQ1nPYBxXLXigabA645JU0qNBlbLrnvctAAnrD2OfF8nZ/gD+F1bv9bDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:35.834384Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:255ef8dbff67612048685d91e137582743148da7491e8f85344edf6b43336c34","sha256:a39c320dde8c5126f9c9de7686218606296409c4af9478156d607bb622dbd998"],"state_sha256":"cff13ff43e362faa504d2840959a6f02580576b2a8717f7ee49838eb37abc1d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gB7hnohJdzM4K3+kKce2zhIjA7AwC+spLyuNbuvl4Bhp61v/VKZLHf3QhQDBzMpgYOfgbVi8jrMi4xOQtaESAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T03:51:28.007860Z","bundle_sha256":"fcf5fba7e11d412c5609ca5122121e4c822de1ba5f30eefeb60a04a682ef6ec5"}}