{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SNCSLI2KCMFR573XBVRU5VLOLA","short_pith_number":"pith:SNCSLI2K","schema_version":"1.0","canonical_sha256":"934525a34a130b1eff770d634ed56e5837e607c6e3e5e7464f4ba52ccb3895f0","source":{"kind":"arxiv","id":"2411.16128","version":1},"attestation_state":"computed","paper":{"title":"CIA: Controllable Image Augmentation Framework Based on Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benoit Macq, Dany Rimez, Hamed Razavi Khosroshahi, Horacio Tellez, Matei Mancas, Mohamed Benkedadra, Natarajan Chidambaram, Sidi Ahmed Mahmoudi, Tiffanie Godelaine","submitted_at":"2024-11-25T06:29:51Z","abstract_excerpt":"Computer vision tasks such as object detection and segmentation rely on the availability of extensive, accurately annotated datasets. In this work, We present CIA, a modular pipeline, for (1) generating synthetic images for dataset augmentation using Stable Diffusion, (2) filtering out low quality samples using defined quality metrics, (3) forcing the existence of specific patterns in generated images using accurate prompting and ControlNet. In order to show how CIA can be used to search for an optimal augmentation pipeline of training data, we study human object detection in a data constraine"},"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":"2411.16128","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T06:29:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f811c47a99a8722195923961b11e9daef01670e930b6ac80eebcf0a928ab25d2","abstract_canon_sha256":"2c1d078309835c78847f743c2b2c40eb5eaed0fe719f6cceb4c7932baac50f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:04.654132Z","signature_b64":"IZWLRPr02+f2buIGPJNRqC5ZcNUe/KqdzE+DquIh6GFt2simjqR5Ar+Wh3UsqDBJF7anpDV6Sm7ZYEV6TG6mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"934525a34a130b1eff770d634ed56e5837e607c6e3e5e7464f4ba52ccb3895f0","last_reissued_at":"2026-07-05T09:40:04.653754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:04.653754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CIA: Controllable Image Augmentation Framework Based on Stable Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benoit Macq, Dany Rimez, Hamed Razavi Khosroshahi, Horacio Tellez, Matei Mancas, Mohamed Benkedadra, Natarajan Chidambaram, Sidi Ahmed Mahmoudi, Tiffanie Godelaine","submitted_at":"2024-11-25T06:29:51Z","abstract_excerpt":"Computer vision tasks such as object detection and segmentation rely on the availability of extensive, accurately annotated datasets. In this work, We present CIA, a modular pipeline, for (1) generating synthetic images for dataset augmentation using Stable Diffusion, (2) filtering out low quality samples using defined quality metrics, (3) forcing the existence of specific patterns in generated images using accurate prompting and ControlNet. In order to show how CIA can be used to search for an optimal augmentation pipeline of training data, we study human object detection in a data constraine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16128","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/2411.16128/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":"2411.16128","created_at":"2026-07-05T09:40:04.653810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16128v1","created_at":"2026-07-05T09:40:04.653810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16128","created_at":"2026-07-05T09:40:04.653810+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNCSLI2KCMFR","created_at":"2026-07-05T09:40:04.653810+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNCSLI2KCMFR573X","created_at":"2026-07-05T09:40:04.653810+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNCSLI2K","created_at":"2026-07-05T09:40:04.653810+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/SNCSLI2KCMFR573XBVRU5VLOLA","json":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA.json","graph_json":"https://pith.science/api/pith-number/SNCSLI2KCMFR573XBVRU5VLOLA/graph.json","events_json":"https://pith.science/api/pith-number/SNCSLI2KCMFR573XBVRU5VLOLA/events.json","paper":"https://pith.science/paper/SNCSLI2K"},"agent_actions":{"view_html":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA","download_json":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA.json","view_paper":"https://pith.science/paper/SNCSLI2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16128&json=true","fetch_graph":"https://pith.science/api/pith-number/SNCSLI2KCMFR573XBVRU5VLOLA/graph.json","fetch_events":"https://pith.science/api/pith-number/SNCSLI2KCMFR573XBVRU5VLOLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA/action/storage_attestation","attest_author":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA/action/author_attestation","sign_citation":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA/action/citation_signature","submit_replication":"https://pith.science/pith/SNCSLI2KCMFR573XBVRU5VLOLA/action/replication_record"}},"created_at":"2026-07-05T09:40:04.653810+00:00","updated_at":"2026-07-05T09:40:04.653810+00:00"}