{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2L4IJG76JVDGA2GEYMQXX5OKIK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e19bfc2a02845c4267884c569171f8fbe1860b466cc2f3603f71189b3edd45df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T04:23:24Z","title_canon_sha256":"ffbad15cfcda0154220fd04f47461dfdd8e305ae02f416c8c4809acc79b18dfb"},"schema_version":"1.0","source":{"id":"2403.06090","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06090","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06090v4","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06090","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"2L4IJG76JVDG","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"2L4IJG76JVDGA2GE","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"2L4IJG76","created_at":"2026-07-05T09:42:23Z"}],"graph_snapshots":[{"event_id":"sha256:7f18e3676baf0e9e52381e94e7df4ea0f9eefcfde13d9df659a9e8c3cd9732cd","target":"graph","created_at":"2026-07-05T09:42:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.06090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extensive pre-training with large data is indispensable for downstream geometry and semantic visual perception tasks. Thanks to large-scale text-to-image (T2I) pretraining, recent works show promising results by simply fine-tuning T2I diffusion models for dense perception tasks. However, several crucial design decisions in this process still lack comprehensive justification, encompassing the necessity of the multi-step stochastic diffusion mechanism, training strategy, inference ensemble strategy, and fine-tuning data quality. In this work, we conduct a thorough investigation into critical fac","authors_text":"Chengxiang Fan, Chunhua Shen, Guangkai Xu, Hao Chen, Kangyang Xie, Mingyu Liu, Yongtao Ge, Zhiyue Zhao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T04:23:24Z","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06090","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7c66e422db4eb69686b3b59e743ddbf37eeaac8853a407f2866e08e0c320bee5","target":"record","created_at":"2026-07-05T09:42:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e19bfc2a02845c4267884c569171f8fbe1860b466cc2f3603f71189b3edd45df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-10T04:23:24Z","title_canon_sha256":"ffbad15cfcda0154220fd04f47461dfdd8e305ae02f416c8c4809acc79b18dfb"},"schema_version":"1.0","source":{"id":"2403.06090","kind":"arxiv","version":4}},"canonical_sha256":"d2f8849bfe4d466068c4c3217bf5ca428316f6dcb48c75000d137274c548b24d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2f8849bfe4d466068c4c3217bf5ca428316f6dcb48c75000d137274c548b24d","first_computed_at":"2026-07-05T09:42:23.663143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:23.663143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ar4L/lJt8fkH3Oonixxyp6YzuYAIaO9DLU2PE+uZLaHTLiD+x1mx7bwDrsBsJDToKXmj5ZSXfAQR5DZE3D2ZCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:23.663637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06090","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c66e422db4eb69686b3b59e743ddbf37eeaac8853a407f2866e08e0c320bee5","sha256:7f18e3676baf0e9e52381e94e7df4ea0f9eefcfde13d9df659a9e8c3cd9732cd"],"state_sha256":"7bb3aa71f9cd0aae2b70d182acdda3988a1ac50cdf702f3263f2a94cadaf11fc"}