{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N6R7FMADA7436SZQP6UVDCCDC2","short_pith_number":"pith:N6R7FMAD","schema_version":"1.0","canonical_sha256":"6fa3f2b00307f9bf4b307fa951884316be73ee9e44975501ed120daf3ae5a0c5","source":{"kind":"arxiv","id":"2211.09788","version":2},"attestation_state":"computed","paper":{"title":"DiffusionDet: Diffusion Model for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peize Sun, Ping Luo, Shoufa Chen, Yibing Song","submitted_at":"2022-11-17T18:56:19Z","abstract_excerpt":"We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes diffuse from ground-truth boxes to random distribution, and the model learns to reverse this noising process. In inference, the model refines a set of randomly generated boxes to the output results in a progressive way. Our work possesses an appealing property of flexibility, which enables the dynamic number of boxes and iterative evaluation. The extensive experiments on the standard benchmarks show that DiffusionDe"},"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":"2211.09788","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T18:56:19Z","cross_cats_sorted":[],"title_canon_sha256":"4f73c8d5b7a6700ee8da3bba19837b19a9d4dd52e22c9176bb75db54bd17ea2a","abstract_canon_sha256":"6e1ff3aeedbc96db9419e39a9da29d53dd7ef0dd0e4afaac97539df7d45ca7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:40.688238Z","signature_b64":"nKSqVpvfflOzzxq9919wjGaNgx96qEOtgxzluo+kw21dXr9lUyShN0MUoWgEOgTeJlc4TFX2Pysj9pEKXbG4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fa3f2b00307f9bf4b307fa951884316be73ee9e44975501ed120daf3ae5a0c5","last_reissued_at":"2026-07-05T06:42:40.687753Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:40.687753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusionDet: Diffusion Model for Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Peize Sun, Ping Luo, Shoufa Chen, Yibing Song","submitted_at":"2022-11-17T18:56:19Z","abstract_excerpt":"We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes diffuse from ground-truth boxes to random distribution, and the model learns to reverse this noising process. In inference, the model refines a set of randomly generated boxes to the output results in a progressive way. Our work possesses an appealing property of flexibility, which enables the dynamic number of boxes and iterative evaluation. The extensive experiments on the standard benchmarks show that DiffusionDe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09788","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/2211.09788/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":"2211.09788","created_at":"2026-07-05T06:42:40.687811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09788v2","created_at":"2026-07-05T06:42:40.687811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09788","created_at":"2026-07-05T06:42:40.687811+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6R7FMADA743","created_at":"2026-07-05T06:42:40.687811+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6R7FMADA7436SZQ","created_at":"2026-07-05T06:42:40.687811+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6R7FMAD","created_at":"2026-07-05T06:42:40.687811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":138,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2","json":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2.json","graph_json":"https://pith.science/api/pith-number/N6R7FMADA7436SZQP6UVDCCDC2/graph.json","events_json":"https://pith.science/api/pith-number/N6R7FMADA7436SZQP6UVDCCDC2/events.json","paper":"https://pith.science/paper/N6R7FMAD"},"agent_actions":{"view_html":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2","download_json":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2.json","view_paper":"https://pith.science/paper/N6R7FMAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09788&json=true","fetch_graph":"https://pith.science/api/pith-number/N6R7FMADA7436SZQP6UVDCCDC2/graph.json","fetch_events":"https://pith.science/api/pith-number/N6R7FMADA7436SZQP6UVDCCDC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2/action/storage_attestation","attest_author":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2/action/author_attestation","sign_citation":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2/action/citation_signature","submit_replication":"https://pith.science/pith/N6R7FMADA7436SZQP6UVDCCDC2/action/replication_record"}},"created_at":"2026-07-05T06:42:40.687811+00:00","updated_at":"2026-07-05T06:42:40.687811+00:00"}