{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F7XBCM7LBFYTR5FXZSHQVZRW5Z","short_pith_number":"pith:F7XBCM7L","schema_version":"1.0","canonical_sha256":"2fee1133eb097138f4b7cc8f0ae636ee56a66f7989b2e896bd37df16690b7e0a","source":{"kind":"arxiv","id":"2506.04929","version":2},"attestation_state":"computed","paper":{"title":"ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mieszko Rutkowski, Miko{\\l}aj Koszowski, Miko{\\l}aj Pokrywka, Wojciech Kusa","submitted_at":"2025-06-05T12:02:01Z","abstract_excerpt":"Neural Machine Translation (NMT) has improved translation by using Transformer-based models, but it still struggles with word ambiguity and context. This problem is especially important in domain-specific applications, which often have problems with unclear sentences or poor data quality. Our research explores how adding information to models can improve translations in the context of e-commerce data. To this end we create ConECT -- a new Czech-to-Polish e-commerce product translation dataset coupled with images and product metadata consisting of 11,400 sentence pairs. We then investigate and "},"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":"2506.04929","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T12:02:01Z","cross_cats_sorted":[],"title_canon_sha256":"998ee621f388fdafe94e156f6fff0fd7d3a2fa44210af3a8cbe29d6f2ff1c1ef","abstract_canon_sha256":"1b0aeacf707b7e5aa3389237e8308e6431328bd388e44237a2d4ec6869c93f31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:23.200533Z","signature_b64":"GNjDc3DMbXG1pxTZszVPQx27Mzsnh4PaZ9dz93UHTbarJuJ6/QNFv6aUB6c0Y1miMRgxETOIbZfL7PGO3nrSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fee1133eb097138f4b7cc8f0ae636ee56a66f7989b2e896bd37df16690b7e0a","last_reissued_at":"2026-07-05T11:18:23.200036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:23.200036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mieszko Rutkowski, Miko{\\l}aj Koszowski, Miko{\\l}aj Pokrywka, Wojciech Kusa","submitted_at":"2025-06-05T12:02:01Z","abstract_excerpt":"Neural Machine Translation (NMT) has improved translation by using Transformer-based models, but it still struggles with word ambiguity and context. This problem is especially important in domain-specific applications, which often have problems with unclear sentences or poor data quality. Our research explores how adding information to models can improve translations in the context of e-commerce data. To this end we create ConECT -- a new Czech-to-Polish e-commerce product translation dataset coupled with images and product metadata consisting of 11,400 sentence pairs. We then investigate and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04929","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/2506.04929/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":"2506.04929","created_at":"2026-07-05T11:18:23.200096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04929v2","created_at":"2026-07-05T11:18:23.200096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04929","created_at":"2026-07-05T11:18:23.200096+00:00"},{"alias_kind":"pith_short_12","alias_value":"F7XBCM7LBFYT","created_at":"2026-07-05T11:18:23.200096+00:00"},{"alias_kind":"pith_short_16","alias_value":"F7XBCM7LBFYTR5FX","created_at":"2026-07-05T11:18:23.200096+00:00"},{"alias_kind":"pith_short_8","alias_value":"F7XBCM7L","created_at":"2026-07-05T11:18:23.200096+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/F7XBCM7LBFYTR5FXZSHQVZRW5Z","json":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z.json","graph_json":"https://pith.science/api/pith-number/F7XBCM7LBFYTR5FXZSHQVZRW5Z/graph.json","events_json":"https://pith.science/api/pith-number/F7XBCM7LBFYTR5FXZSHQVZRW5Z/events.json","paper":"https://pith.science/paper/F7XBCM7L"},"agent_actions":{"view_html":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z","download_json":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z.json","view_paper":"https://pith.science/paper/F7XBCM7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04929&json=true","fetch_graph":"https://pith.science/api/pith-number/F7XBCM7LBFYTR5FXZSHQVZRW5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/F7XBCM7LBFYTR5FXZSHQVZRW5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/action/storage_attestation","attest_author":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/action/author_attestation","sign_citation":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/action/citation_signature","submit_replication":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/action/replication_record"}},"created_at":"2026-07-05T11:18:23.200096+00:00","updated_at":"2026-07-05T11:18:23.200096+00:00"}