{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7UPP6UOQQJB7D6VDLR6HYVP37O","short_pith_number":"pith:7UPP6UOQ","canonical_record":{"source":{"id":"2112.04886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-09T13:16:42Z","cross_cats_sorted":[],"title_canon_sha256":"1fd03f7e5c74bea72ec95f7c823b8a9610badd08e52b08548b876d01dba8a70f","abstract_canon_sha256":"bc4b4de0e3fa384abcdfd5c9d166445c44233fc9d66a598703bfa8660269c43d"},"schema_version":"1.0"},"canonical_sha256":"fd1eff51d08243f1faa35c7c7c55fbfb9c2fdb01978386b375ed3f79bda2af1a","source":{"kind":"arxiv","id":"2112.04886","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04886","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04886v1","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04886","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"7UPP6UOQQJB7","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"7UPP6UOQQJB7D6VD","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"7UPP6UOQ","created_at":"2026-07-05T10:16:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7UPP6UOQQJB7D6VDLR6HYVP37O","target":"record","payload":{"canonical_record":{"source":{"id":"2112.04886","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-09T13:16:42Z","cross_cats_sorted":[],"title_canon_sha256":"1fd03f7e5c74bea72ec95f7c823b8a9610badd08e52b08548b876d01dba8a70f","abstract_canon_sha256":"bc4b4de0e3fa384abcdfd5c9d166445c44233fc9d66a598703bfa8660269c43d"},"schema_version":"1.0"},"canonical_sha256":"fd1eff51d08243f1faa35c7c7c55fbfb9c2fdb01978386b375ed3f79bda2af1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:30.415527Z","signature_b64":"neoa1WcrUWBrwMD0WI5nUW2W0KAcDxRjNeQ0JzjjN2lbv+4+ulzU+eAogJl2egnVBguyQq/69t4SCv6VC5MrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1eff51d08243f1faa35c7c7c55fbfb9c2fdb01978386b375ed3f79bda2af1a","last_reissued_at":"2026-07-05T10:16:30.415047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:30.415047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.04886","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":"2026-07-05T10:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUCwyqga8ig8ORtKOBH3k3DJ9oKHUiXLbFp5PBX6fLxyxutuJxL4UoYNFHnnyPPNYJrpJDs2GSp5L+OUghDIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:06:03.365354Z"},"content_sha256":"d37e6953e644ff79c8db78e949d5f39137fb5737958c83f0d511c7efea0bdc23","schema_version":"1.0","event_id":"sha256:d37e6953e644ff79c8db78e949d5f39137fb5737958c83f0d511c7efea0bdc23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7UPP6UOQQJB7D6VDLR6HYVP37O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semantic Search as Extractive Paraphrase Span Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Filip Ginter, Hanna Kitti, Jenna Kanerva, Li-Hsin Chang, Mathias Creutz, Teemu Vahtola","submitted_at":"2021-12-09T13:16:42Z","abstract_excerpt":"In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering. On the Turku Paraphrase Corpus of 100,000 manually extracted Finnish paraphrase pairs including their original document context, we find that our paraphrase span detection model outperforms two strong retrieval baselines (lexical similarity and BERT sentence embeddings) by 31.9pp and 22.4pp respecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04886","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/2112.04886/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":"2026-07-05T10:16:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zdBbAeE6ChzREARNIaiISWmAXfBxc/j+vX6kSynGt/GDFYOf7vaFvhDY+BZ/N1NjjTPZulFU/++13ftsJBngCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:06:03.365887Z"},"content_sha256":"177f01faaede7da0dc7e9d9f6fc9ff631a400940a4973c6ec37d796083286f43","schema_version":"1.0","event_id":"sha256:177f01faaede7da0dc7e9d9f6fc9ff631a400940a4973c6ec37d796083286f43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UPP6UOQQJB7D6VDLR6HYVP37O/bundle.json","state_url":"https://pith.science/pith/7UPP6UOQQJB7D6VDLR6HYVP37O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UPP6UOQQJB7D6VDLR6HYVP37O/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":"2026-08-12T21:06:03Z","links":{"resolver":"https://pith.science/pith/7UPP6UOQQJB7D6VDLR6HYVP37O","bundle":"https://pith.science/pith/7UPP6UOQQJB7D6VDLR6HYVP37O/bundle.json","state":"https://pith.science/pith/7UPP6UOQQJB7D6VDLR6HYVP37O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UPP6UOQQJB7D6VDLR6HYVP37O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7UPP6UOQQJB7D6VDLR6HYVP37O","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":"bc4b4de0e3fa384abcdfd5c9d166445c44233fc9d66a598703bfa8660269c43d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-09T13:16:42Z","title_canon_sha256":"1fd03f7e5c74bea72ec95f7c823b8a9610badd08e52b08548b876d01dba8a70f"},"schema_version":"1.0","source":{"id":"2112.04886","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04886","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04886v1","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04886","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_12","alias_value":"7UPP6UOQQJB7","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_16","alias_value":"7UPP6UOQQJB7D6VD","created_at":"2026-07-05T10:16:30Z"},{"alias_kind":"pith_short_8","alias_value":"7UPP6UOQ","created_at":"2026-07-05T10:16:30Z"}],"graph_snapshots":[{"event_id":"sha256:177f01faaede7da0dc7e9d9f6fc9ff631a400940a4973c6ec37d796083286f43","target":"graph","created_at":"2026-07-05T10:16:30Z","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/2112.04886/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we approach the problem of semantic search by framing the search task as paraphrase span detection, i.e. given a segment of text as a query phrase, the task is to identify its paraphrase in a given document, the same modelling setup as typically used in extractive question answering. On the Turku Paraphrase Corpus of 100,000 manually extracted Finnish paraphrase pairs including their original document context, we find that our paraphrase span detection model outperforms two strong retrieval baselines (lexical similarity and BERT sentence embeddings) by 31.9pp and 22.4pp respecti","authors_text":"Filip Ginter, Hanna Kitti, Jenna Kanerva, Li-Hsin Chang, Mathias Creutz, Teemu Vahtola","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-09T13:16:42Z","title":"Semantic Search as Extractive Paraphrase Span Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04886","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:d37e6953e644ff79c8db78e949d5f39137fb5737958c83f0d511c7efea0bdc23","target":"record","created_at":"2026-07-05T10:16:30Z","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":"bc4b4de0e3fa384abcdfd5c9d166445c44233fc9d66a598703bfa8660269c43d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-09T13:16:42Z","title_canon_sha256":"1fd03f7e5c74bea72ec95f7c823b8a9610badd08e52b08548b876d01dba8a70f"},"schema_version":"1.0","source":{"id":"2112.04886","kind":"arxiv","version":1}},"canonical_sha256":"fd1eff51d08243f1faa35c7c7c55fbfb9c2fdb01978386b375ed3f79bda2af1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1eff51d08243f1faa35c7c7c55fbfb9c2fdb01978386b375ed3f79bda2af1a","first_computed_at":"2026-07-05T10:16:30.415047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:30.415047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"neoa1WcrUWBrwMD0WI5nUW2W0KAcDxRjNeQ0JzjjN2lbv+4+ulzU+eAogJl2egnVBguyQq/69t4SCv6VC5MrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:30.415527Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04886","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d37e6953e644ff79c8db78e949d5f39137fb5737958c83f0d511c7efea0bdc23","sha256:177f01faaede7da0dc7e9d9f6fc9ff631a400940a4973c6ec37d796083286f43"],"state_sha256":"1e29d4fc1bdd5318a6776bda9817766faf2992ec5c1b279c74e66c5a1ad41f61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IoBbNtU9wIFEQGVQF8r3aLD8v/R7IsfjVuau7Z8E1f0be9DIZt3XgFdDUQ4n6WNgMh4Jg4HZ6JipjdQ5Pi1jBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:06:03.370185Z","bundle_sha256":"73e0e6deaf5e4424fc13dc05467b0f0f499e071fc91ad217f408cbeaec8ebff8"}}