{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F7XBCM7LBFYTR5FXZSHQVZRW5Z","short_pith_number":"pith:F7XBCM7L","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"},"canonical_sha256":"2fee1133eb097138f4b7cc8f0ae636ee56a66f7989b2e896bd37df16690b7e0a","source":{"kind":"arxiv","id":"2506.04929","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F7XBCM7LBFYTR5FXZSHQVZRW5Z","target":"record","payload":{"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"},"canonical_sha256":"2fee1133eb097138f4b7cc8f0ae636ee56a66f7989b2e896bd37df16690b7e0a","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"},"source_kind":"arxiv","source_id":"2506.04929","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gkTLvOothEtW+d53ZLGS1/8yJ7bxmiQXYEMu/NFZAC4+kl80k0V+FoY/C9M7mrhP1A3bOf+zwtEGDorBPvjjDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:18:13.651687Z"},"content_sha256":"2d225f45d1396800e6e4c80b42d024ae14722eeb8e3e299f95bc1f7a255ebed9","schema_version":"1.0","event_id":"sha256:2d225f45d1396800e6e4c80b42d024ae14722eeb8e3e299f95bc1f7a255ebed9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F7XBCM7LBFYTR5FXZSHQVZRW5Z","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75gm7V2GL4oS+OkLHwvM5shOag9G3VSFwayxKV1pUIlXXJ+ubDJgMR6N187gomcqFBYYUT1Xkv0vSvTJS3jnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:18:13.652365Z"},"content_sha256":"6eb6ac9414be33a4444ef339f902c00974a08b3f8dda0c5060d990b5bd90dc97","schema_version":"1.0","event_id":"sha256:6eb6ac9414be33a4444ef339f902c00974a08b3f8dda0c5060d990b5bd90dc97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/bundle.json","state_url":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T19:18:13Z","links":{"resolver":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z","bundle":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/bundle.json","state":"https://pith.science/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7XBCM7LBFYTR5FXZSHQVZRW5Z/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUjH7LnxlFp60FtrwK7fXardJSiiTDApPiufFn+Sx+LhMFPjjbTKIgnOI3CWTvuGlzUh5GZjiUKqFanRGgOMAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:18:13.658226Z","bundle_sha256":"1467e93df9c8c223b2eacc5f92775dfe705d9f3b2ee6e611680ad1294724a044"}}