{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CIPSNAUCJ2KNDPXOKCQDJWZRAB","short_pith_number":"pith:CIPSNAUC","canonical_record":{"source":{"id":"2005.05477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-11T22:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"1666731cf51963093db9f2777ff907e860205c587986e3fa74b79c29463540bb","abstract_canon_sha256":"0953023be51fc7bf805b6739003f55506df8f61a103f2bbf9e82aa77bd9817b7"},"schema_version":"1.0"},"canonical_sha256":"121f2682824e94d1beee50a034db31005ba33a0c6f759feb7f39a331de20d9df","source":{"kind":"arxiv","id":"2005.05477","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05477","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05477v2","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05477","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"CIPSNAUCJ2KN","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"CIPSNAUCJ2KNDPXO","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"CIPSNAUC","created_at":"2026-07-05T01:02:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CIPSNAUCJ2KNDPXOKCQDJWZRAB","target":"record","payload":{"canonical_record":{"source":{"id":"2005.05477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-11T22:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"1666731cf51963093db9f2777ff907e860205c587986e3fa74b79c29463540bb","abstract_canon_sha256":"0953023be51fc7bf805b6739003f55506df8f61a103f2bbf9e82aa77bd9817b7"},"schema_version":"1.0"},"canonical_sha256":"121f2682824e94d1beee50a034db31005ba33a0c6f759feb7f39a331de20d9df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:30.694390Z","signature_b64":"CWEGXdge7hH+zJeyCF3lvB/UXatB4wqm2ePJ2z7l30g6don9DOsJa4w5LjX88voK6gxoj2tXwyKMKK1iDDVdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"121f2682824e94d1beee50a034db31005ba33a0c6f759feb7f39a331de20d9df","last_reissued_at":"2026-07-05T01:02:30.693914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:30.693914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.05477","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Eg8Dsi0PDodXMZgYH03njToM8gkoW3VxqLKiAuHsTotbOrRJlgRQX2dXjRL7ytKog1lA+15hN0KpZHp7RMhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:10:43.264767Z"},"content_sha256":"60200cd016fc074c987d24e0845050504e8a1c81881127a0c30685d682f19f83","schema_version":"1.0","event_id":"sha256:60200cd016fc074c987d24e0845050504e8a1c81881127a0c30685d682f19f83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CIPSNAUCJ2KNDPXOKCQDJWZRAB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Polysynthetic Language Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aldrian Obaja Muis, Chi-kiu Lo, Christo Kirov, Coleman Haley, Emily Prud'hommeaux, Francis Tyers, Han Liu, Hyunji Hayley Park, Jeffrey Micher, Jong Hyuk Park, Katherine J. Zhang, Kenneth Steimel, Lane Schwartz, Lonny Strunk, Lori Levin, Naoki Otani, Patrick Littell, Rebecca Knowles, Robbie Jimmerson, Vasilisa Andriyanets, Zhisong Zhang","submitted_at":"2020-05-11T22:57:04Z","abstract_excerpt":"Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are \"language agnostic\". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05477","kind":"arxiv","version":2},"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/2005.05477/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":"2026-07-05T01:02:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KGk6kMAVdJ9tuDk9tAuuo8pDg64jqNTgHKaj4bdkUcQOqujTsT4PBhCzbU1WK68FVzcVYL4oBQPbfhhotVKTDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:10:43.265271Z"},"content_sha256":"7c6c47861240368b4ba7c83eb8d7887d0c4c862a82d0d5c9f876992c271a7323","schema_version":"1.0","event_id":"sha256:7c6c47861240368b4ba7c83eb8d7887d0c4c862a82d0d5c9f876992c271a7323"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB/bundle.json","state_url":"https://pith.science/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB/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":"2026-08-03T16:10:43Z","links":{"resolver":"https://pith.science/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB","bundle":"https://pith.science/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB/bundle.json","state":"https://pith.science/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CIPSNAUCJ2KNDPXOKCQDJWZRAB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CIPSNAUCJ2KNDPXOKCQDJWZRAB","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":"0953023be51fc7bf805b6739003f55506df8f61a103f2bbf9e82aa77bd9817b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-11T22:57:04Z","title_canon_sha256":"1666731cf51963093db9f2777ff907e860205c587986e3fa74b79c29463540bb"},"schema_version":"1.0","source":{"id":"2005.05477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.05477","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2005.05477v2","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.05477","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"CIPSNAUCJ2KN","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"CIPSNAUCJ2KNDPXO","created_at":"2026-07-05T01:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"CIPSNAUC","created_at":"2026-07-05T01:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:7c6c47861240368b4ba7c83eb8d7887d0c4c862a82d0d5c9f876992c271a7323","target":"graph","created_at":"2026-07-05T01:02:30Z","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/2005.05477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research in natural language processing commonly assumes that approaches that work well for English and and other widely-used languages are \"language agnostic\". In high-resource languages, especially those that are analytic, a common approach is to treat morphologically-distinct variants of a common root as completely independent word types. This assumes, that there are limited morphological inflections per root, and that the majority will appear in a large enough corpus, so that the model can adequately learn statistics about each form. Approaches like stemming, lemmatization, or subword segm","authors_text":"Aldrian Obaja Muis, Chi-kiu Lo, Christo Kirov, Coleman Haley, Emily Prud'hommeaux, Francis Tyers, Han Liu, Hyunji Hayley Park, Jeffrey Micher, Jong Hyuk Park, Katherine J. Zhang, Kenneth Steimel, Lane Schwartz, Lonny Strunk, Lori Levin, Naoki Otani, Patrick Littell, Rebecca Knowles, Robbie Jimmerson, Vasilisa Andriyanets, Zhisong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-11T22:57:04Z","title":"Neural Polysynthetic Language Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.05477","kind":"arxiv","version":2},"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":"sha256:60200cd016fc074c987d24e0845050504e8a1c81881127a0c30685d682f19f83","target":"record","created_at":"2026-07-05T01:02:30Z","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":"0953023be51fc7bf805b6739003f55506df8f61a103f2bbf9e82aa77bd9817b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-11T22:57:04Z","title_canon_sha256":"1666731cf51963093db9f2777ff907e860205c587986e3fa74b79c29463540bb"},"schema_version":"1.0","source":{"id":"2005.05477","kind":"arxiv","version":2}},"canonical_sha256":"121f2682824e94d1beee50a034db31005ba33a0c6f759feb7f39a331de20d9df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"121f2682824e94d1beee50a034db31005ba33a0c6f759feb7f39a331de20d9df","first_computed_at":"2026-07-05T01:02:30.693914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:02:30.693914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWEGXdge7hH+zJeyCF3lvB/UXatB4wqm2ePJ2z7l30g6don9DOsJa4w5LjX88voK6gxoj2tXwyKMKK1iDDVdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:02:30.694390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.05477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60200cd016fc074c987d24e0845050504e8a1c81881127a0c30685d682f19f83","sha256:7c6c47861240368b4ba7c83eb8d7887d0c4c862a82d0d5c9f876992c271a7323"],"state_sha256":"cb96fc4b9301606d3554d148a8338ccb93dd777db211b91ee222a2a140a3179e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XGng7kguzrWO0AuK84QAIzqsZ9UINe8qeR7ycL32JiwCAj/VFYBsW0v2em0YQYMC7BvzkrGEtMPQi0h9MCXeDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:10:43.274426Z","bundle_sha256":"6babd3a2bec4249865846e262c829dca2b68d7fc6b4b0c52fbee3f001aba7cff"}}