{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AEO2O74PDFYZT6Q7QQX44GLUMJ","short_pith_number":"pith:AEO2O74P","schema_version":"1.0","canonical_sha256":"011da77f8f197199fa1f842fce197462649d8d87ae9f1552b24aa07f147cf171","source":{"kind":"arxiv","id":"2210.09814","version":1},"attestation_state":"computed","paper":{"title":"Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Naumann, Benchun Zhou, Felix Hertlein, Kai Furmans, Laura D\\\"orr","submitted_at":"2022-10-18T12:49:04Z","abstract_excerpt":"State-of-the-art approaches in computer vision heavily rely on sufficiently large training datasets. For real-world applications, obtaining such a dataset is usually a tedious task. In this paper, we present a fully automated pipeline to generate a synthetic dataset for instance segmentation in four steps. In contrast to existing work, our pipeline covers every step from data acquisition to the final dataset. We first scrape images for the objects of interest from popular image search engines and since we rely only on text-based queries the resulting data comprises a wide variety of images. He"},"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":"2210.09814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-18T12:49:04Z","cross_cats_sorted":[],"title_canon_sha256":"3f304937464ce17d02fbb5792477983220eb63983c9d8c96013c17199e25b0a2","abstract_canon_sha256":"089d4463754f525866cdf20cc3956c5f02f5a914a7f176c86621e41f23916052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:00.580596Z","signature_b64":"XjYfqVkJH/bOxB8tyokedLjTax0vBfNhzDdQuOgwWmJKxmzwS9wXp89mRMbU9I0LpGMOuvT9ig2SXp/gVQcxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"011da77f8f197199fa1f842fce197462649d8d87ae9f1552b24aa07f147cf171","last_reissued_at":"2026-07-05T06:02:00.580150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:00.580150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Naumann, Benchun Zhou, Felix Hertlein, Kai Furmans, Laura D\\\"orr","submitted_at":"2022-10-18T12:49:04Z","abstract_excerpt":"State-of-the-art approaches in computer vision heavily rely on sufficiently large training datasets. For real-world applications, obtaining such a dataset is usually a tedious task. In this paper, we present a fully automated pipeline to generate a synthetic dataset for instance segmentation in four steps. In contrast to existing work, our pipeline covers every step from data acquisition to the final dataset. We first scrape images for the objects of interest from popular image search engines and since we rely only on text-based queries the resulting data comprises a wide variety of images. He"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09814","kind":"arxiv","version":1},"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/2210.09814/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":"2210.09814","created_at":"2026-07-05T06:02:00.580212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09814v1","created_at":"2026-07-05T06:02:00.580212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09814","created_at":"2026-07-05T06:02:00.580212+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEO2O74PDFYZ","created_at":"2026-07-05T06:02:00.580212+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEO2O74PDFYZT6Q7","created_at":"2026-07-05T06:02:00.580212+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEO2O74P","created_at":"2026-07-05T06:02:00.580212+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/AEO2O74PDFYZT6Q7QQX44GLUMJ","json":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ.json","graph_json":"https://pith.science/api/pith-number/AEO2O74PDFYZT6Q7QQX44GLUMJ/graph.json","events_json":"https://pith.science/api/pith-number/AEO2O74PDFYZT6Q7QQX44GLUMJ/events.json","paper":"https://pith.science/paper/AEO2O74P"},"agent_actions":{"view_html":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ","download_json":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ.json","view_paper":"https://pith.science/paper/AEO2O74P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09814&json=true","fetch_graph":"https://pith.science/api/pith-number/AEO2O74PDFYZT6Q7QQX44GLUMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AEO2O74PDFYZT6Q7QQX44GLUMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ/action/storage_attestation","attest_author":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ/action/author_attestation","sign_citation":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ/action/citation_signature","submit_replication":"https://pith.science/pith/AEO2O74PDFYZT6Q7QQX44GLUMJ/action/replication_record"}},"created_at":"2026-07-05T06:02:00.580212+00:00","updated_at":"2026-07-05T06:02:00.580212+00:00"}