{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OOH5VDMHCL5RI7NWOMVOI5R4IJ","short_pith_number":"pith:OOH5VDMH","schema_version":"1.0","canonical_sha256":"738fda8d8712fb147db6732ae4763c426294df48470eb64bc4261e1145463ff2","source":{"kind":"arxiv","id":"2109.04513","version":2},"attestation_state":"computed","paper":{"title":"Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asaf Yehudai, Benny Saret, Gabriel Stanovsky, Koren Lazar, Nathan Wasserman, Wayne Horowitz","submitted_at":"2021-09-09T18:58:14Z","abstract_excerpt":"We present models which complete missing text given transliterations of ancient Mesopotamian documents, originally written on cuneiform clay tablets (2500 BCE - 100 CE). Due to the tablets' deterioration, scholars often rely on contextual cues to manually fill in missing parts in the text in a subjective and time-consuming process. We identify that this challenge can be formulated as a masked language modelling task, used mostly as a pretraining objective for contextualized language models. Following, we develop several architectures focusing on the Akkadian language, the lingua franca of the "},"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":"2109.04513","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-09T18:58:14Z","cross_cats_sorted":[],"title_canon_sha256":"2cbd41d777953b1efbc9e6e73f3a499b41a5e7e90789d9c3f1163c0ab2e73bd0","abstract_canon_sha256":"b9ae94191cab9a408e974575668cd55a360fe57d6de90a2c71f97e0bb9016474"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:17.302668Z","signature_b64":"G1Y3XNtZaO6XSZ1dJCSlGUzZPm1e+wIMYk3HI/iw3DSbVWWumu/haTlAZ7ny9N0cSjpI1Sef9OmkHSgBgcL1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738fda8d8712fb147db6732ae4763c426294df48470eb64bc4261e1145463ff2","last_reissued_at":"2026-07-05T03:25:17.302178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:17.302178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asaf Yehudai, Benny Saret, Gabriel Stanovsky, Koren Lazar, Nathan Wasserman, Wayne Horowitz","submitted_at":"2021-09-09T18:58:14Z","abstract_excerpt":"We present models which complete missing text given transliterations of ancient Mesopotamian documents, originally written on cuneiform clay tablets (2500 BCE - 100 CE). Due to the tablets' deterioration, scholars often rely on contextual cues to manually fill in missing parts in the text in a subjective and time-consuming process. We identify that this challenge can be formulated as a masked language modelling task, used mostly as a pretraining objective for contextualized language models. Following, we develop several architectures focusing on the Akkadian language, the lingua franca of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04513","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/2109.04513/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":"2109.04513","created_at":"2026-07-05T03:25:17.302229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.04513v2","created_at":"2026-07-05T03:25:17.302229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04513","created_at":"2026-07-05T03:25:17.302229+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOH5VDMHCL5R","created_at":"2026-07-05T03:25:17.302229+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOH5VDMHCL5RI7NW","created_at":"2026-07-05T03:25:17.302229+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOH5VDMH","created_at":"2026-07-05T03:25:17.302229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05108","citing_title":"Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ","json":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ.json","graph_json":"https://pith.science/api/pith-number/OOH5VDMHCL5RI7NWOMVOI5R4IJ/graph.json","events_json":"https://pith.science/api/pith-number/OOH5VDMHCL5RI7NWOMVOI5R4IJ/events.json","paper":"https://pith.science/paper/OOH5VDMH"},"agent_actions":{"view_html":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ","download_json":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ.json","view_paper":"https://pith.science/paper/OOH5VDMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.04513&json=true","fetch_graph":"https://pith.science/api/pith-number/OOH5VDMHCL5RI7NWOMVOI5R4IJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OOH5VDMHCL5RI7NWOMVOI5R4IJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ/action/storage_attestation","attest_author":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ/action/author_attestation","sign_citation":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ/action/citation_signature","submit_replication":"https://pith.science/pith/OOH5VDMHCL5RI7NWOMVOI5R4IJ/action/replication_record"}},"created_at":"2026-07-05T03:25:17.302229+00:00","updated_at":"2026-07-05T03:25:17.302229+00:00"}