{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KJWBSESAUTQHBHYBXM6K6O6CDA","short_pith_number":"pith:KJWBSESA","canonical_record":{"source":{"id":"2011.03281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T11:00:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"328eaebd164f8a0346090a3b375d32660f45d65f5ea227813bb8bec9d6ce1006","abstract_canon_sha256":"afaefca4a855c83704acdaf6c6876846f1cfe4e93d8ceed50f9a3c03caadb161"},"schema_version":"1.0"},"canonical_sha256":"526c191240a4e0709f01bb3caf3bc21831b5ee7a29cdf6d1e96a1130e912873c","source":{"kind":"arxiv","id":"2011.03281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03281","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03281v1","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03281","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"KJWBSESAUTQH","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"KJWBSESAUTQHBHYB","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"KJWBSESA","created_at":"2026-07-05T01:49:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KJWBSESAUTQHBHYBXM6K6O6CDA","target":"record","payload":{"canonical_record":{"source":{"id":"2011.03281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T11:00:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"328eaebd164f8a0346090a3b375d32660f45d65f5ea227813bb8bec9d6ce1006","abstract_canon_sha256":"afaefca4a855c83704acdaf6c6876846f1cfe4e93d8ceed50f9a3c03caadb161"},"schema_version":"1.0"},"canonical_sha256":"526c191240a4e0709f01bb3caf3bc21831b5ee7a29cdf6d1e96a1130e912873c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:41.659064Z","signature_b64":"vbQzzeb7xN+CXJim7D+67BRjiAtjU8+388TN5H8nmViHfolvd0N/YBPjjbkJuGNY8GUnA4XfCxqNg/emAUmlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"526c191240a4e0709f01bb3caf3bc21831b5ee7a29cdf6d1e96a1130e912873c","last_reissued_at":"2026-07-05T01:49:41.658688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:41.658688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.03281","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":"2026-07-05T01:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cHQ68e3iWze2aXRcd4oprrclJwFTxETiO2gsKs1HVMjoCMRWXMMyuI8wiaV+6U9XiwZmrGC0Ed1UJRuYBkBBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:35:04.458528Z"},"content_sha256":"552874864fed019226f738f0a1d4e6cfd5d9a6e075b253c0806ac6ebb02166da","schema_version":"1.0","event_id":"sha256:552874864fed019226f738f0a1d4e6cfd5d9a6e075b253c0806ac6ebb02166da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KJWBSESAUTQHBHYBXM6K6O6CDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Corpora Compared: The Case of the Swedish Gigaword & Wikipedia Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Foteini Liwicki, Marcus Liwicki, Tosin P. Adewumi","submitted_at":"2020-11-06T11:00:47Z","abstract_excerpt":"In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size. Natural language processing (NLP) tasks usually perform better with embeddings from bigger corpora. However, broadness of covered domain and noise can play important roles. We evaluate embeddings based on two Swedish corpora: The Gigaword and Wikipedia, in analogy (intrinsic) tests and discover that the embeddings from the Wikipedia corpus generally outperform those from the Gigaword corpus, which is a bigger corpus. Downstream"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03281","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/2011.03281/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":"2026-07-05T01:49:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CpfAkdNHEiG1Wm4qtbDlx0tb6WpfvFU8kZw5tmBe3Qg2jV0VBmd+625FLYCRm3QseQI3pvz53yvrgk4eaE2aCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:35:04.459110Z"},"content_sha256":"70ac0500e57751991bd3429bdcf83a30f1f08f239f4b9e053802272bdc5e6e38","schema_version":"1.0","event_id":"sha256:70ac0500e57751991bd3429bdcf83a30f1f08f239f4b9e053802272bdc5e6e38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJWBSESAUTQHBHYBXM6K6O6CDA/bundle.json","state_url":"https://pith.science/pith/KJWBSESAUTQHBHYBXM6K6O6CDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJWBSESAUTQHBHYBXM6K6O6CDA/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":"2026-08-19T22:35:04Z","links":{"resolver":"https://pith.science/pith/KJWBSESAUTQHBHYBXM6K6O6CDA","bundle":"https://pith.science/pith/KJWBSESAUTQHBHYBXM6K6O6CDA/bundle.json","state":"https://pith.science/pith/KJWBSESAUTQHBHYBXM6K6O6CDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJWBSESAUTQHBHYBXM6K6O6CDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KJWBSESAUTQHBHYBXM6K6O6CDA","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":"afaefca4a855c83704acdaf6c6876846f1cfe4e93d8ceed50f9a3c03caadb161","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T11:00:47Z","title_canon_sha256":"328eaebd164f8a0346090a3b375d32660f45d65f5ea227813bb8bec9d6ce1006"},"schema_version":"1.0","source":{"id":"2011.03281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03281","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03281v1","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03281","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"pith_short_12","alias_value":"KJWBSESAUTQH","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"pith_short_16","alias_value":"KJWBSESAUTQHBHYB","created_at":"2026-07-05T01:49:41Z"},{"alias_kind":"pith_short_8","alias_value":"KJWBSESA","created_at":"2026-07-05T01:49:41Z"}],"graph_snapshots":[{"event_id":"sha256:70ac0500e57751991bd3429bdcf83a30f1f08f239f4b9e053802272bdc5e6e38","target":"graph","created_at":"2026-07-05T01:49:41Z","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/2011.03281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we show that the difference in performance of embeddings from differently sourced data for a given language can be due to other factors besides data size. Natural language processing (NLP) tasks usually perform better with embeddings from bigger corpora. However, broadness of covered domain and noise can play important roles. We evaluate embeddings based on two Swedish corpora: The Gigaword and Wikipedia, in analogy (intrinsic) tests and discover that the embeddings from the Wikipedia corpus generally outperform those from the Gigaword corpus, which is a bigger corpus. Downstream","authors_text":"Foteini Liwicki, Marcus Liwicki, Tosin P. Adewumi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T11:00:47Z","title":"Corpora Compared: The Case of the Swedish Gigaword & Wikipedia Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03281","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":"sha256:552874864fed019226f738f0a1d4e6cfd5d9a6e075b253c0806ac6ebb02166da","target":"record","created_at":"2026-07-05T01:49:41Z","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":"afaefca4a855c83704acdaf6c6876846f1cfe4e93d8ceed50f9a3c03caadb161","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T11:00:47Z","title_canon_sha256":"328eaebd164f8a0346090a3b375d32660f45d65f5ea227813bb8bec9d6ce1006"},"schema_version":"1.0","source":{"id":"2011.03281","kind":"arxiv","version":1}},"canonical_sha256":"526c191240a4e0709f01bb3caf3bc21831b5ee7a29cdf6d1e96a1130e912873c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"526c191240a4e0709f01bb3caf3bc21831b5ee7a29cdf6d1e96a1130e912873c","first_computed_at":"2026-07-05T01:49:41.658688Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:41.658688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vbQzzeb7xN+CXJim7D+67BRjiAtjU8+388TN5H8nmViHfolvd0N/YBPjjbkJuGNY8GUnA4XfCxqNg/emAUmlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:41.659064Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:552874864fed019226f738f0a1d4e6cfd5d9a6e075b253c0806ac6ebb02166da","sha256:70ac0500e57751991bd3429bdcf83a30f1f08f239f4b9e053802272bdc5e6e38"],"state_sha256":"12d894ae8bab52ca18d481ddb648b26fd9cb79e55c3cb606535587c5224104da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bo/UmBiMC1wKnMt5zLnS6F7UXX8ZkCWwSpYZvxSsHq/J6FXEDOBEnVqqbfhJbvJInZhghtpOGDC6PVyiw+lfDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:35:04.463340Z","bundle_sha256":"879afb771aec6dd4a93323770c553c291c66f6bbbffac77c8b5f1b8854a0c713"}}