{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F7XBCM7LBFYTR5FXZSHQVZRW5Z","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":"1b0aeacf707b7e5aa3389237e8308e6431328bd388e44237a2d4ec6869c93f31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T12:02:01Z","title_canon_sha256":"998ee621f388fdafe94e156f6fff0fd7d3a2fa44210af3a8cbe29d6f2ff1c1ef"},"schema_version":"1.0","source":{"id":"2506.04929","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.04929","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.04929v2","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04929","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"F7XBCM7LBFYT","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"F7XBCM7LBFYTR5FX","created_at":"2026-07-05T11:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"F7XBCM7L","created_at":"2026-07-05T11:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:6eb6ac9414be33a4444ef339f902c00974a08b3f8dda0c5060d990b5bd90dc97","target":"graph","created_at":"2026-07-05T11:18:23Z","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/2506.04929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Mieszko Rutkowski, Miko{\\l}aj Koszowski, Miko{\\l}aj Pokrywka, Wojciech Kusa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T12:02:01Z","title":"ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04929","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":"sha256:2d225f45d1396800e6e4c80b42d024ae14722eeb8e3e299f95bc1f7a255ebed9","target":"record","created_at":"2026-07-05T11:18:23Z","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":"1b0aeacf707b7e5aa3389237e8308e6431328bd388e44237a2d4ec6869c93f31","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-05T12:02:01Z","title_canon_sha256":"998ee621f388fdafe94e156f6fff0fd7d3a2fa44210af3a8cbe29d6f2ff1c1ef"},"schema_version":"1.0","source":{"id":"2506.04929","kind":"arxiv","version":2}},"canonical_sha256":"2fee1133eb097138f4b7cc8f0ae636ee56a66f7989b2e896bd37df16690b7e0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fee1133eb097138f4b7cc8f0ae636ee56a66f7989b2e896bd37df16690b7e0a","first_computed_at":"2026-07-05T11:18:23.200036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:23.200036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GNjDc3DMbXG1pxTZszVPQx27Mzsnh4PaZ9dz93UHTbarJuJ6/QNFv6aUB6c0Y1miMRgxETOIbZfL7PGO3nrSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:23.200533Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.04929","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d225f45d1396800e6e4c80b42d024ae14722eeb8e3e299f95bc1f7a255ebed9","sha256:6eb6ac9414be33a4444ef339f902c00974a08b3f8dda0c5060d990b5bd90dc97"],"state_sha256":"d3244c730783afd0c2a35836f9a740f60a26f23ff82b2e49f91d0f34d43f0b8e"}