{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OFV2HG6MBP33LKZ3PLTOXAZCDL","short_pith_number":"pith:OFV2HG6M","schema_version":"1.0","canonical_sha256":"716ba39bcc0bf7b5ab3b7ae6eb83221ad1ea0b16fd3cf3f500b06dd1de229079","source":{"kind":"arxiv","id":"2108.05682","version":2},"attestation_state":"computed","paper":{"title":"(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Guriel, Omer Goldman, Reut Tsarfaty","submitted_at":"2021-08-12T12:06:47Z","abstract_excerpt":"In the domain of Morphology, Inflection is a fundamental and important task that gained a lot of traction in recent years, mostly via SIGMORPHON's shared-tasks. With average accuracy above 0.9 over the scores of all languages, the task is considered mostly solved using relatively generic neural seq2seq models, even with little data provided. In this work, we propose to re-evaluate morphological inflection models by employing harder train-test splits that will challenge the generalization capacity of the models. In particular, as opposed to the na{\\\"i}ve split-by-form, we propose a split-by-lem"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2108.05682","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-08-12T12:06:47Z","cross_cats_sorted":[],"title_canon_sha256":"9a10f3bffbc4760c27605f7801c08bb500adc093eb850da51921ba93a5f06fc7","abstract_canon_sha256":"ef9860f0816ea7fb7ba79f18292719f14f1e010c0b25c6bbbc1ac2d5f3fc81be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:44.465871Z","signature_b64":"9oExfMzUeBgS5UD5dYfSTG44qIgFVOyKTG68K2Y0yiS2++pO+n4Bg8ZhNVAwVXcUJVhQf3pa4sLlvakjebbIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"716ba39bcc0bf7b5ab3b7ae6eb83221ad1ea0b16fd3cf3f500b06dd1de229079","last_reissued_at":"2026-07-05T04:06:44.465433Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:44.465433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' Performance","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Guriel, Omer Goldman, Reut Tsarfaty","submitted_at":"2021-08-12T12:06:47Z","abstract_excerpt":"In the domain of Morphology, Inflection is a fundamental and important task that gained a lot of traction in recent years, mostly via SIGMORPHON's shared-tasks. With average accuracy above 0.9 over the scores of all languages, the task is considered mostly solved using relatively generic neural seq2seq models, even with little data provided. In this work, we propose to re-evaluate morphological inflection models by employing harder train-test splits that will challenge the generalization capacity of the models. In particular, as opposed to the na{\\\"i}ve split-by-form, we propose a split-by-lem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.05682","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/2108.05682/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2108.05682","created_at":"2026-07-05T04:06:44.465483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.05682v2","created_at":"2026-07-05T04:06:44.465483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.05682","created_at":"2026-07-05T04:06:44.465483+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFV2HG6MBP33","created_at":"2026-07-05T04:06:44.465483+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFV2HG6MBP33LKZ3","created_at":"2026-07-05T04:06:44.465483+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFV2HG6M","created_at":"2026-07-05T04:06:44.465483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL","json":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL.json","graph_json":"https://pith.science/api/pith-number/OFV2HG6MBP33LKZ3PLTOXAZCDL/graph.json","events_json":"https://pith.science/api/pith-number/OFV2HG6MBP33LKZ3PLTOXAZCDL/events.json","paper":"https://pith.science/paper/OFV2HG6M"},"agent_actions":{"view_html":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL","download_json":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL.json","view_paper":"https://pith.science/paper/OFV2HG6M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.05682&json=true","fetch_graph":"https://pith.science/api/pith-number/OFV2HG6MBP33LKZ3PLTOXAZCDL/graph.json","fetch_events":"https://pith.science/api/pith-number/OFV2HG6MBP33LKZ3PLTOXAZCDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL/action/storage_attestation","attest_author":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL/action/author_attestation","sign_citation":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL/action/citation_signature","submit_replication":"https://pith.science/pith/OFV2HG6MBP33LKZ3PLTOXAZCDL/action/replication_record"}},"created_at":"2026-07-05T04:06:44.465483+00:00","updated_at":"2026-07-05T04:06:44.465483+00:00"}