{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YYIXLSXIABU5SG5EB5BQJJHCKC","short_pith_number":"pith:YYIXLSXI","schema_version":"1.0","canonical_sha256":"c61175cae80069d91ba40f4304a4e250801addb3bd4ed8cef4de050eb4f87563","source":{"kind":"arxiv","id":"1812.02825","version":5},"attestation_state":"computed","paper":{"title":"Attending to Mathematical Language with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Artit Wangperawong","submitted_at":"2018-12-05T03:05:08Z","abstract_excerpt":"Mathematical expressions were generated, evaluated and used to train neural network models based on the transformer architecture. The expressions and their targets were analyzed as a character-level sequence transduction task in which the encoder and decoder are built on attention mechanisms. Three models were trained to understand and evaluate symbolic variables and expressions in mathematics: (1) the self-attentive and feed-forward transformer without recurrence or convolution, (2) the universal transformer with recurrence, and (3) the adaptive universal transformer with recurrence and adapt"},"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":"1812.02825","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T03:05:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"877d872f72e53a762506a4b7eae01c1d30f4e55d777c0e7477e9421f2d95efec","abstract_canon_sha256":"6b88b4aa785ea9a219d60ea0ceef95bd7c062c8da9da9f1ffdf7b617352a2bb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:38.940546Z","signature_b64":"5/urvXOSb/vBqrCFgegE28tniD3P2TkMQSDbqXr+4ubjzDNxBklc1nyUb4TmesYIscLnCigs9TwKp64ad5MEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c61175cae80069d91ba40f4304a4e250801addb3bd4ed8cef4de050eb4f87563","last_reissued_at":"2026-07-05T00:04:38.940151Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:38.940151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attending to Mathematical Language with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Artit Wangperawong","submitted_at":"2018-12-05T03:05:08Z","abstract_excerpt":"Mathematical expressions were generated, evaluated and used to train neural network models based on the transformer architecture. The expressions and their targets were analyzed as a character-level sequence transduction task in which the encoder and decoder are built on attention mechanisms. Three models were trained to understand and evaluate symbolic variables and expressions in mathematics: (1) the self-attentive and feed-forward transformer without recurrence or convolution, (2) the universal transformer with recurrence, and (3) the adaptive universal transformer with recurrence and adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02825","kind":"arxiv","version":5},"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/1812.02825/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":"1812.02825","created_at":"2026-07-05T00:04:38.940202+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02825v5","created_at":"2026-07-05T00:04:38.940202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02825","created_at":"2026-07-05T00:04:38.940202+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYIXLSXIABU5","created_at":"2026-07-05T00:04:38.940202+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYIXLSXIABU5SG5E","created_at":"2026-07-05T00:04:38.940202+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYIXLSXI","created_at":"2026-07-05T00:04:38.940202+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.04211","citing_title":"On Identifiability in Transformers","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC","json":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC.json","graph_json":"https://pith.science/api/pith-number/YYIXLSXIABU5SG5EB5BQJJHCKC/graph.json","events_json":"https://pith.science/api/pith-number/YYIXLSXIABU5SG5EB5BQJJHCKC/events.json","paper":"https://pith.science/paper/YYIXLSXI"},"agent_actions":{"view_html":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC","download_json":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC.json","view_paper":"https://pith.science/paper/YYIXLSXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02825&json=true","fetch_graph":"https://pith.science/api/pith-number/YYIXLSXIABU5SG5EB5BQJJHCKC/graph.json","fetch_events":"https://pith.science/api/pith-number/YYIXLSXIABU5SG5EB5BQJJHCKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC/action/storage_attestation","attest_author":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC/action/author_attestation","sign_citation":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC/action/citation_signature","submit_replication":"https://pith.science/pith/YYIXLSXIABU5SG5EB5BQJJHCKC/action/replication_record"}},"created_at":"2026-07-05T00:04:38.940202+00:00","updated_at":"2026-07-05T00:04:38.940202+00:00"}