{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YVKGAGO4IABQXT5ST4MRKWVMWI","short_pith_number":"pith:YVKGAGO4","schema_version":"1.0","canonical_sha256":"c5546019dc40030bcfb29f19155aacb2156f0bb72d299927d6f7f7b974500cff","source":{"kind":"arxiv","id":"2503.09221","version":1},"attestation_state":"computed","paper":{"title":"Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hannah Kniesel, Pedro Hermosilla, Timo Ropinski","submitted_at":"2025-03-12T10:09:27Z","abstract_excerpt":"Recent advances in conditional image generation from diffusion models have shown great potential in achieving impressive image quality while preserving the constraints introduced by the user. In particular, ControlNet enables precise alignment between ground truth segmentation masks and the generated image content, allowing the enhancement of training datasets in segmentation tasks. This raises a key question: Can ControlNet additionally be guided to generate the most informative synthetic samples for a specific task? Inspired by active learning, where the most informative real-world samples a"},"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":"2503.09221","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-12T10:09:27Z","cross_cats_sorted":[],"title_canon_sha256":"ab147709e8d19a8194dce22b1b11bf82999a11038f1c44a24ff25d6fc9955562","abstract_canon_sha256":"78ba0778843fbc5b35564c38c84a5813b1dc19fd7e08c049dc0f4953c46b64cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:52.002290Z","signature_b64":"ihOpKf8+r0lCDuZKDjoUFbQdgAdzCA2JtYkhdT4vnrYss0F3La5Fbcc1M4TyID4we93Obd16drEtmjCLn844DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5546019dc40030bcfb29f19155aacb2156f0bb72d299927d6f7f7b974500cff","last_reissued_at":"2026-07-05T10:29:52.001651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:52.001651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hannah Kniesel, Pedro Hermosilla, Timo Ropinski","submitted_at":"2025-03-12T10:09:27Z","abstract_excerpt":"Recent advances in conditional image generation from diffusion models have shown great potential in achieving impressive image quality while preserving the constraints introduced by the user. In particular, ControlNet enables precise alignment between ground truth segmentation masks and the generated image content, allowing the enhancement of training datasets in segmentation tasks. This raises a key question: Can ControlNet additionally be guided to generate the most informative synthetic samples for a specific task? Inspired by active learning, where the most informative real-world samples a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09221","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/2503.09221/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":"2503.09221","created_at":"2026-07-05T10:29:52.001722+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09221v1","created_at":"2026-07-05T10:29:52.001722+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09221","created_at":"2026-07-05T10:29:52.001722+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVKGAGO4IABQ","created_at":"2026-07-05T10:29:52.001722+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVKGAGO4IABQXT5S","created_at":"2026-07-05T10:29:52.001722+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVKGAGO4","created_at":"2026-07-05T10:29:52.001722+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31603","citing_title":"Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09699","citing_title":"A Real-Calibrated Synthetic-First Data Engine","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI","json":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI.json","graph_json":"https://pith.science/api/pith-number/YVKGAGO4IABQXT5ST4MRKWVMWI/graph.json","events_json":"https://pith.science/api/pith-number/YVKGAGO4IABQXT5ST4MRKWVMWI/events.json","paper":"https://pith.science/paper/YVKGAGO4"},"agent_actions":{"view_html":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI","download_json":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI.json","view_paper":"https://pith.science/paper/YVKGAGO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09221&json=true","fetch_graph":"https://pith.science/api/pith-number/YVKGAGO4IABQXT5ST4MRKWVMWI/graph.json","fetch_events":"https://pith.science/api/pith-number/YVKGAGO4IABQXT5ST4MRKWVMWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI/action/storage_attestation","attest_author":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI/action/author_attestation","sign_citation":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI/action/citation_signature","submit_replication":"https://pith.science/pith/YVKGAGO4IABQXT5ST4MRKWVMWI/action/replication_record"}},"created_at":"2026-07-05T10:29:52.001722+00:00","updated_at":"2026-07-05T10:29:52.001722+00:00"}