{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZWHZXFAU32TKEEXS5CFSNKA5YN","short_pith_number":"pith:ZWHZXFAU","canonical_record":{"source":{"id":"2103.13103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-24T11:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"2f088326470fc1239c9c1986909dab415a72a186d2195186abf783e1c0fff3fc","abstract_canon_sha256":"5762428723b868a9e5f8ecba55c102bafdac0e7960d94e60fb5215712cec3770"},"schema_version":"1.0"},"canonical_sha256":"cd8f9b9414dea6a212f2e88b26a81dc37f0851e8424b20bafaf9d2664c37be72","source":{"kind":"arxiv","id":"2103.13103","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13103","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13103v1","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13103","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZWHZXFAU32TK","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZWHZXFAU32TKEEXS","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZWHZXFAU","created_at":"2026-07-05T02:26:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZWHZXFAU32TKEEXS5CFSNKA5YN","target":"record","payload":{"canonical_record":{"source":{"id":"2103.13103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-24T11:24:10Z","cross_cats_sorted":[],"title_canon_sha256":"2f088326470fc1239c9c1986909dab415a72a186d2195186abf783e1c0fff3fc","abstract_canon_sha256":"5762428723b868a9e5f8ecba55c102bafdac0e7960d94e60fb5215712cec3770"},"schema_version":"1.0"},"canonical_sha256":"cd8f9b9414dea6a212f2e88b26a81dc37f0851e8424b20bafaf9d2664c37be72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:05.685230Z","signature_b64":"xcsd9+0zWYQrYKmHSN+uGenBlyTgUiW+jRnn/vMiJ9U4IuIPh8pJBQYlW4TokRD7G8ht6MsM4mBKgin9l4t4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd8f9b9414dea6a212f2e88b26a81dc37f0851e8424b20bafaf9d2664c37be72","last_reissued_at":"2026-07-05T02:26:05.684768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:05.684768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.13103","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":"2026-07-05T02:26:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WR8fR017jOUzXfSj3N5ngafrI4nT3wXppUKAiNDNtH+zdkg5HtnnOIBpxNykP1jFAaXgLFufFnsCne5/blkdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:03:59.928005Z"},"content_sha256":"7ab2d92e54bd207fbf58c6f49d120f25e0f52374047bec5571e098f0cd9aa47f","schema_version":"1.0","event_id":"sha256:7ab2d92e54bd207fbf58c6f49d120f25e0f52374047bec5571e098f0cd9aa47f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZWHZXFAU32TKEEXS5CFSNKA5YN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finnish Paraphrase Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ginter, Hanna-Mari Kupari, Iiro Rastas, Jemina Kilpel\\\"ainen, Jenna Kanerva, Jenna Saarni, Li-Hsin Chang, Maija Sev\\'on, Otto Tarkka, Valtteri Skantsi","submitted_at":"2021-03-24T11:24:10Z","abstract_excerpt":"In this paper, we introduce the first fully manually annotated paraphrase corpus for Finnish containing 53,572 paraphrase pairs harvested from alternative subtitles and news headings. Out of all paraphrase pairs in our corpus 98% are manually classified to be paraphrases at least in their given context, if not in all contexts. Additionally, we establish a manual candidate selection method and demonstrate its feasibility in high quality paraphrase selection in terms of both cost and quality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13103","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/2103.13103/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":"2026-07-05T02:26:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obuxVoH9dcdik1UsGQZPOhemSKXZS5amRUWiOYVG4q0lys1E01R4BtdCxldA6LdPXKF8WCFNEb/7I94nb+4SDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:03:59.928812Z"},"content_sha256":"5e293169b3c90a494d5f75ef8ec3a18c296e8307b5ff9b498058efa41e63d22e","schema_version":"1.0","event_id":"sha256:5e293169b3c90a494d5f75ef8ec3a18c296e8307b5ff9b498058efa41e63d22e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN/bundle.json","state_url":"https://pith.science/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN/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":"2026-08-13T02:03:59Z","links":{"resolver":"https://pith.science/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN","bundle":"https://pith.science/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN/bundle.json","state":"https://pith.science/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZWHZXFAU32TKEEXS5CFSNKA5YN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZWHZXFAU32TKEEXS5CFSNKA5YN","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":"5762428723b868a9e5f8ecba55c102bafdac0e7960d94e60fb5215712cec3770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-24T11:24:10Z","title_canon_sha256":"2f088326470fc1239c9c1986909dab415a72a186d2195186abf783e1c0fff3fc"},"schema_version":"1.0","source":{"id":"2103.13103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13103","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13103v1","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13103","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZWHZXFAU32TK","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZWHZXFAU32TKEEXS","created_at":"2026-07-05T02:26:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZWHZXFAU","created_at":"2026-07-05T02:26:05Z"}],"graph_snapshots":[{"event_id":"sha256:5e293169b3c90a494d5f75ef8ec3a18c296e8307b5ff9b498058efa41e63d22e","target":"graph","created_at":"2026-07-05T02:26:05Z","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/2103.13103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce the first fully manually annotated paraphrase corpus for Finnish containing 53,572 paraphrase pairs harvested from alternative subtitles and news headings. Out of all paraphrase pairs in our corpus 98% are manually classified to be paraphrases at least in their given context, if not in all contexts. Additionally, we establish a manual candidate selection method and demonstrate its feasibility in high quality paraphrase selection in terms of both cost and quality.","authors_text":"Filip Ginter, Hanna-Mari Kupari, Iiro Rastas, Jemina Kilpel\\\"ainen, Jenna Kanerva, Jenna Saarni, Li-Hsin Chang, Maija Sev\\'on, Otto Tarkka, Valtteri Skantsi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-24T11:24:10Z","title":"Finnish Paraphrase Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13103","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":"sha256:7ab2d92e54bd207fbf58c6f49d120f25e0f52374047bec5571e098f0cd9aa47f","target":"record","created_at":"2026-07-05T02:26:05Z","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":"5762428723b868a9e5f8ecba55c102bafdac0e7960d94e60fb5215712cec3770","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-24T11:24:10Z","title_canon_sha256":"2f088326470fc1239c9c1986909dab415a72a186d2195186abf783e1c0fff3fc"},"schema_version":"1.0","source":{"id":"2103.13103","kind":"arxiv","version":1}},"canonical_sha256":"cd8f9b9414dea6a212f2e88b26a81dc37f0851e8424b20bafaf9d2664c37be72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd8f9b9414dea6a212f2e88b26a81dc37f0851e8424b20bafaf9d2664c37be72","first_computed_at":"2026-07-05T02:26:05.684768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:05.684768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xcsd9+0zWYQrYKmHSN+uGenBlyTgUiW+jRnn/vMiJ9U4IuIPh8pJBQYlW4TokRD7G8ht6MsM4mBKgin9l4t4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:05.685230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.13103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ab2d92e54bd207fbf58c6f49d120f25e0f52374047bec5571e098f0cd9aa47f","sha256:5e293169b3c90a494d5f75ef8ec3a18c296e8307b5ff9b498058efa41e63d22e"],"state_sha256":"42f59711febf8daa44d1f98d8814192afa08d11f6de54b241a209fd1bf435937"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ea5eQ840/4RWou9MIGLWmeTa7mkR7fU9LL7pvUf/iqRIMMOtJW3/faZq8IeR3+yBbYpCu8EqEGYnLwip31kkAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:03:59.934407Z","bundle_sha256":"1f4b12f1e3c93733f6cd1e9a29015f45a35e2ff502caaa5c34d37ac7a64708b3"}}