{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:64GQ6KVHKB5QKXTCMWS4HG6RAQ","short_pith_number":"pith:64GQ6KVH","canonical_record":{"source":{"id":"2010.10472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-20T17:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"6c7eff0b20c896929749d266c5b8c10e4b96ce72f38b01642930a00d892e57dc","abstract_canon_sha256":"f32341945893720df9012ce776a347d3da37bf610564efecc513883bfc59d247"},"schema_version":"1.0"},"canonical_sha256":"f70d0f2aa7507b055e6265a5c39bd1043189cded50686546884fc8558646d9cd","source":{"kind":"arxiv","id":"2010.10472","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10472","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10472v1","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10472","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"64GQ6KVHKB5Q","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"pith_short_16","alias_value":"64GQ6KVHKB5QKXTC","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"pith_short_8","alias_value":"64GQ6KVH","created_at":"2026-07-05T01:44:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:64GQ6KVHKB5QKXTCMWS4HG6RAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.10472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-20T17:31:07Z","cross_cats_sorted":[],"title_canon_sha256":"6c7eff0b20c896929749d266c5b8c10e4b96ce72f38b01642930a00d892e57dc","abstract_canon_sha256":"f32341945893720df9012ce776a347d3da37bf610564efecc513883bfc59d247"},"schema_version":"1.0"},"canonical_sha256":"f70d0f2aa7507b055e6265a5c39bd1043189cded50686546884fc8558646d9cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:30.721284Z","signature_b64":"Ps9yod3SlE7WJXPsHWeqOIoI2VuOKRHaJUzVpCk4bpTYKBhC+PnBihGiSpDX9y1Np0iKtvTudo7k2rbXJGg1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f70d0f2aa7507b055e6265a5c39bd1043189cded50686546884fc8558646d9cd","last_reissued_at":"2026-07-05T01:44:30.720885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:30.720885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.10472","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":"2026-07-05T01:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jLNrdzd8bWcqQIa510lp/uLOVW9okzEA4lMc5A/JZTNt83oTvUc9o5vYvcfLLqxDVjWV8wPVYEbalDammFuJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:41:43.641983Z"},"content_sha256":"2ad4d6b8247bc5c6b4413f20264635d70769143a91551d27a04ed54cf5c0d1f4","schema_version":"1.0","event_id":"sha256:2ad4d6b8247bc5c6b4413f20264635d70769143a91551d27a04ed54cf5c0d1f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:64GQ6KVHKB5QKXTCMWS4HG6RAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Antonios Anastasopoulos, Yiyuan Li","submitted_at":"2020-10-20T17:31:07Z","abstract_excerpt":"Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict and large corpora are usually required to collect enough examples. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected, for example within a chat app. Such models are designed to be incrementally improved as feedback is given from users. In this work, we design a knowledge-base an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10472","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/2010.10472/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":"2026-07-05T01:44:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pvhq3hXLjs5PriY12upDXSoiA+mBkEu1VWcn83mO+/Qxq4jDR4yJlB7DOo/jL31PAIkVNRVKLj60+piNDaIYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:41:43.642819Z"},"content_sha256":"20710304b4a1d8d19c09fe5abc67ae38df005c25ea03525968da23551eb0f085","schema_version":"1.0","event_id":"sha256:20710304b4a1d8d19c09fe5abc67ae38df005c25ea03525968da23551eb0f085"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ/bundle.json","state_url":"https://pith.science/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ/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":"2026-08-03T18:41:43Z","links":{"resolver":"https://pith.science/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ","bundle":"https://pith.science/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ/bundle.json","state":"https://pith.science/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/64GQ6KVHKB5QKXTCMWS4HG6RAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:64GQ6KVHKB5QKXTCMWS4HG6RAQ","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":"f32341945893720df9012ce776a347d3da37bf610564efecc513883bfc59d247","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-20T17:31:07Z","title_canon_sha256":"6c7eff0b20c896929749d266c5b8c10e4b96ce72f38b01642930a00d892e57dc"},"schema_version":"1.0","source":{"id":"2010.10472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10472","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10472v1","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10472","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"64GQ6KVHKB5Q","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"pith_short_16","alias_value":"64GQ6KVHKB5QKXTC","created_at":"2026-07-05T01:44:30Z"},{"alias_kind":"pith_short_8","alias_value":"64GQ6KVH","created_at":"2026-07-05T01:44:30Z"}],"graph_snapshots":[{"event_id":"sha256:20710304b4a1d8d19c09fe5abc67ae38df005c25ea03525968da23551eb0f085","target":"graph","created_at":"2026-07-05T01:44:30Z","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/2010.10472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict and large corpora are usually required to collect enough examples. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected, for example within a chat app. Such models are designed to be incrementally improved as feedback is given from users. In this work, we design a knowledge-base an","authors_text":"Alan W Black, Antonios Anastasopoulos, Yiyuan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-20T17:31:07Z","title":"Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10472","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":"sha256:2ad4d6b8247bc5c6b4413f20264635d70769143a91551d27a04ed54cf5c0d1f4","target":"record","created_at":"2026-07-05T01:44:30Z","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":"f32341945893720df9012ce776a347d3da37bf610564efecc513883bfc59d247","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-20T17:31:07Z","title_canon_sha256":"6c7eff0b20c896929749d266c5b8c10e4b96ce72f38b01642930a00d892e57dc"},"schema_version":"1.0","source":{"id":"2010.10472","kind":"arxiv","version":1}},"canonical_sha256":"f70d0f2aa7507b055e6265a5c39bd1043189cded50686546884fc8558646d9cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f70d0f2aa7507b055e6265a5c39bd1043189cded50686546884fc8558646d9cd","first_computed_at":"2026-07-05T01:44:30.720885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:30.720885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ps9yod3SlE7WJXPsHWeqOIoI2VuOKRHaJUzVpCk4bpTYKBhC+PnBihGiSpDX9y1Np0iKtvTudo7k2rbXJGg1Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:30.721284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.10472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ad4d6b8247bc5c6b4413f20264635d70769143a91551d27a04ed54cf5c0d1f4","sha256:20710304b4a1d8d19c09fe5abc67ae38df005c25ea03525968da23551eb0f085"],"state_sha256":"9385b3830f9d2d18016a538d37676b79db00c9ccd4fa2c91c55af5a998f20b06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BqA2TEovMfQ3g+3LwGSMxZzmmOl4jwT2a1wZRhwNeEmUZCEdjNUpiI3urRUql5tmbPro5/J3A0klw5xa+neZBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:41:43.647828Z","bundle_sha256":"4047b5471f68558cb9f1fc1e751db9089c774a68d5d7129b67901cab06f61b90"}}