{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B3SBCSP6RJPUO2OISPK4VJN3VH","short_pith_number":"pith:B3SBCSP6","schema_version":"1.0","canonical_sha256":"0ee41149fe8a5f4769c893d5caa5bba9d3458bbabd5684dde222fb24c03d926b","source":{"kind":"arxiv","id":"2309.05956","version":1},"attestation_state":"computed","paper":{"title":"Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Nlong Zhao, Jiashu Xu, Laurent Itti, Neel Joshi, Vibhav Vineet, Yunhao Ge","submitted_at":"2023-09-12T04:41:45Z","abstract_excerpt":"We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation into foreground object generation, and contextually coherent background generation. To generate foreground objects, we employ a straightforward textual template, incorporating the object class name as input prompts. This is fed into a text-to-image synthesis framework, producing various foreground images set against isolated backgrounds. A foreground-backgrou"},"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":"2309.05956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-12T04:41:45Z","cross_cats_sorted":[],"title_canon_sha256":"25a8e6f6d029858c2d6b3bde25292916b129c22e908f45144588ee5b2f9402ba","abstract_canon_sha256":"cc1e2fedefd71c54bc4a22f62604bad1b93b5acac23fb2da9f9ba34204fa0060"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:49.398237Z","signature_b64":"sJH37FOrYrB3+8sGOC4xTtnZFa3CRDFcPvoXXIvk6p09CH00PTcIpzD/hfEI3LAbQ+NosXoZPHwFE/tL12X1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ee41149fe8a5f4769c893d5caa5bba9d3458bbabd5684dde222fb24c03d926b","last_reissued_at":"2026-07-05T06:49:49.397774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:49.397774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Generation: Harnessing Text to Image Models for Object Detection and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Brian Nlong Zhao, Jiashu Xu, Laurent Itti, Neel Joshi, Vibhav Vineet, Yunhao Ge","submitted_at":"2023-09-12T04:41:45Z","abstract_excerpt":"We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation into foreground object generation, and contextually coherent background generation. To generate foreground objects, we employ a straightforward textual template, incorporating the object class name as input prompts. This is fed into a text-to-image synthesis framework, producing various foreground images set against isolated backgrounds. A foreground-backgrou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05956","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/2309.05956/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":"2309.05956","created_at":"2026-07-05T06:49:49.397825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05956v1","created_at":"2026-07-05T06:49:49.397825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05956","created_at":"2026-07-05T06:49:49.397825+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3SBCSP6RJPU","created_at":"2026-07-05T06:49:49.397825+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3SBCSP6RJPUO2OI","created_at":"2026-07-05T06:49:49.397825+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3SBCSP6","created_at":"2026-07-05T06:49:49.397825+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12222","citing_title":"Endangered Alert: A Field-Validated Self-Training Scheme for Detecting and Protecting Threatened Wildlife on Roads and Roadsides","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH","json":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH.json","graph_json":"https://pith.science/api/pith-number/B3SBCSP6RJPUO2OISPK4VJN3VH/graph.json","events_json":"https://pith.science/api/pith-number/B3SBCSP6RJPUO2OISPK4VJN3VH/events.json","paper":"https://pith.science/paper/B3SBCSP6"},"agent_actions":{"view_html":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH","download_json":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH.json","view_paper":"https://pith.science/paper/B3SBCSP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05956&json=true","fetch_graph":"https://pith.science/api/pith-number/B3SBCSP6RJPUO2OISPK4VJN3VH/graph.json","fetch_events":"https://pith.science/api/pith-number/B3SBCSP6RJPUO2OISPK4VJN3VH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH/action/storage_attestation","attest_author":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH/action/author_attestation","sign_citation":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH/action/citation_signature","submit_replication":"https://pith.science/pith/B3SBCSP6RJPUO2OISPK4VJN3VH/action/replication_record"}},"created_at":"2026-07-05T06:49:49.397825+00:00","updated_at":"2026-07-05T06:49:49.397825+00:00"}