{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5R2AVOPUOZJFC3ZRCV2EW6Y7E","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":"2ae0513e9ae8e85001445012a4a307aebe557169179dc7c9174d08394cec374e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T18:59:35Z","title_canon_sha256":"51f19318a090155b001dbb9746fe1ac3c03811d361528beb8447a36a3eb0da07"},"schema_version":"1.0","source":{"id":"2411.08034","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08034","created_at":"2026-07-05T09:36:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08034v3","created_at":"2026-07-05T09:36:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08034","created_at":"2026-07-05T09:36:16Z"},{"alias_kind":"pith_short_12","alias_value":"F5R2AVOPUOZJ","created_at":"2026-07-05T09:36:16Z"},{"alias_kind":"pith_short_16","alias_value":"F5R2AVOPUOZJFC3Z","created_at":"2026-07-05T09:36:16Z"},{"alias_kind":"pith_short_8","alias_value":"F5R2AVOP","created_at":"2026-07-05T09:36:16Z"}],"graph_snapshots":[{"event_id":"sha256:5899b18d0a55a0fc575cb6620a60c7199bf429794233041cd8c946e51f9a43e3","target":"graph","created_at":"2026-07-05T09:36:16Z","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/2411.08034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation under the framework of image-to-image translation, and show how diffusion models benefit from scaling training and test-time compute for these perceptual tasks. Through a careful analysis of these scaling properties, we formulate compute-optimal training and inference recipes to scale diffusion models for visual perception tasks. Our models achieve competitive ","authors_text":"Jathushan Rajasegaran, Jitendra Malik, Rahul Ravishankar, Zeeshan Patel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T18:59:35Z","title":"Scaling Properties of Diffusion Models for Perceptual Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08034","kind":"arxiv","version":3},"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":"sha256:23dd88329e3cd08d330e3107ad0ab8d027acda5a48454b61abc4e5c716a5e86c","target":"record","created_at":"2026-07-05T09:36:16Z","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":"2ae0513e9ae8e85001445012a4a307aebe557169179dc7c9174d08394cec374e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T18:59:35Z","title_canon_sha256":"51f19318a090155b001dbb9746fe1ac3c03811d361528beb8447a36a3eb0da07"},"schema_version":"1.0","source":{"id":"2411.08034","kind":"arxiv","version":3}},"canonical_sha256":"2f63a055cfa3b2928b7988aba25bd8f921cfd764d1483ad9cd1b1ebda9dfd63d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f63a055cfa3b2928b7988aba25bd8f921cfd764d1483ad9cd1b1ebda9dfd63d","first_computed_at":"2026-07-05T09:36:16.404038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:16.404038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D1lj3OT87In7vrgAAwA82kqb1V61Y+v7+t4S/0P5482XpGNs8kmcn2MPB/Pmin+l+G7B8mu9Ib7jeu9XUt0zBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:16.404560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08034","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23dd88329e3cd08d330e3107ad0ab8d027acda5a48454b61abc4e5c716a5e86c","sha256:5899b18d0a55a0fc575cb6620a60c7199bf429794233041cd8c946e51f9a43e3"],"state_sha256":"f773cfb5695cf1f8b9e3d671543799c50f0cbd00f560231432580c7f020e06d6"}