{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GUXV6W7X6KLXQ7L5TELWI56WK5","short_pith_number":"pith:GUXV6W7X","canonical_record":{"source":{"id":"2605.25326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:16:19Z","cross_cats_sorted":[],"title_canon_sha256":"f9ff3e488b64f82fca0b1c5011cee6bb7b6153e78c7c0ddae874fcf6aa5d4ebe","abstract_canon_sha256":"06c11f8ef6d0b37110b54a8f3b004b0c535507824b22d179582b5fecdbbb4dd6"},"schema_version":"1.0"},"canonical_sha256":"352f5f5bf7f297787d7d99176477d657773b0df97f7020cafaee18f600d925ad","source":{"kind":"arxiv","id":"2605.25326","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25326","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25326v1","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25326","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"GUXV6W7X6KLX","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"GUXV6W7X6KLXQ7L5","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"GUXV6W7X","created_at":"2026-05-26T02:04:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GUXV6W7X6KLXQ7L5TELWI56WK5","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:16:19Z","cross_cats_sorted":[],"title_canon_sha256":"f9ff3e488b64f82fca0b1c5011cee6bb7b6153e78c7c0ddae874fcf6aa5d4ebe","abstract_canon_sha256":"06c11f8ef6d0b37110b54a8f3b004b0c535507824b22d179582b5fecdbbb4dd6"},"schema_version":"1.0"},"canonical_sha256":"352f5f5bf7f297787d7d99176477d657773b0df97f7020cafaee18f600d925ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:29.021340Z","signature_b64":"dEMr7XW1sbPtaFMXtBUZs/c2+tj3yU61aSSs3pXBr5gcfw+sgHtadouQgWvs9wu1BstlIrsYmE7EI3nNKbT9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352f5f5bf7f297787d7d99176477d657773b0df97f7020cafaee18f600d925ad","last_reissued_at":"2026-05-26T02:04:29.020608Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:29.020608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25326","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SlqO100newVYS8hc99b4wBiB5KDN98/JIPhgE8TMHcNwfJerSErD8GwcGFvJWN8/lJLlsPYws0aBbJ2OxfmTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T15:58:32.433690Z"},"content_sha256":"54c7924aa150a42aa2959689c8a344ae3f3c4907b67d1b6b6b5774f026d12c97","schema_version":"1.0","event_id":"sha256:54c7924aa150a42aa2959689c8a344ae3f3c4907b67d1b6b6b5774f026d12c97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GUXV6W7X6KLXQ7L5TELWI56WK5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Junwei Zhou, Yu-Wing Tai","submitted_at":"2026-05-25T01:16:19Z","abstract_excerpt":"Building structured 3D scene layouts from a single image requires reconciling visual observations with physical and spatial constraints, a challenge that is difficult to address with direct prediction alone. In this work, we formulate monocular 3D layout estimation as a perceive-then-plan problem with vision-language models, where a Perceiver first grounds the 3D objects and then a Planner iteratively refines the scene hypothesis through actions that improve physical plausibility while preserving consistency with the input image. We propose Layout-as-Policy (LaP), which casts the planning stag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25326","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/2605.25326/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YTVUmIy5ADSKeikDkAZuIUuwF7oACTKBCxJHNmzkBc2nUBFEwIUOR/WAcf7vfuwzeIYg3vw8l2OghBpQ7hP3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T15:58:32.434385Z"},"content_sha256":"f422fb3742c7d01decd419d38edd77b6f2337d40b72ea45fe1f2a40989a1acb8","schema_version":"1.0","event_id":"sha256:f422fb3742c7d01decd419d38edd77b6f2337d40b72ea45fe1f2a40989a1acb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUXV6W7X6KLXQ7L5TELWI56WK5/bundle.json","state_url":"https://pith.science/pith/GUXV6W7X6KLXQ7L5TELWI56WK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUXV6W7X6KLXQ7L5TELWI56WK5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T15:58:32Z","links":{"resolver":"https://pith.science/pith/GUXV6W7X6KLXQ7L5TELWI56WK5","bundle":"https://pith.science/pith/GUXV6W7X6KLXQ7L5TELWI56WK5/bundle.json","state":"https://pith.science/pith/GUXV6W7X6KLXQ7L5TELWI56WK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUXV6W7X6KLXQ7L5TELWI56WK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GUXV6W7X6KLXQ7L5TELWI56WK5","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":"06c11f8ef6d0b37110b54a8f3b004b0c535507824b22d179582b5fecdbbb4dd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:16:19Z","title_canon_sha256":"f9ff3e488b64f82fca0b1c5011cee6bb7b6153e78c7c0ddae874fcf6aa5d4ebe"},"schema_version":"1.0","source":{"id":"2605.25326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25326","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25326v1","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25326","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_12","alias_value":"GUXV6W7X6KLX","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_16","alias_value":"GUXV6W7X6KLXQ7L5","created_at":"2026-05-26T02:04:29Z"},{"alias_kind":"pith_short_8","alias_value":"GUXV6W7X","created_at":"2026-05-26T02:04:29Z"}],"graph_snapshots":[{"event_id":"sha256:f422fb3742c7d01decd419d38edd77b6f2337d40b72ea45fe1f2a40989a1acb8","target":"graph","created_at":"2026-05-26T02:04:29Z","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/2605.25326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building structured 3D scene layouts from a single image requires reconciling visual observations with physical and spatial constraints, a challenge that is difficult to address with direct prediction alone. In this work, we formulate monocular 3D layout estimation as a perceive-then-plan problem with vision-language models, where a Perceiver first grounds the 3D objects and then a Planner iteratively refines the scene hypothesis through actions that improve physical plausibility while preserving consistency with the input image. We propose Layout-as-Policy (LaP), which casts the planning stag","authors_text":"Junwei Zhou, Yu-Wing Tai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:16:19Z","title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25326","kind":"arxiv","version":1},"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":"sha256:54c7924aa150a42aa2959689c8a344ae3f3c4907b67d1b6b6b5774f026d12c97","target":"record","created_at":"2026-05-26T02:04:29Z","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":"06c11f8ef6d0b37110b54a8f3b004b0c535507824b22d179582b5fecdbbb4dd6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T01:16:19Z","title_canon_sha256":"f9ff3e488b64f82fca0b1c5011cee6bb7b6153e78c7c0ddae874fcf6aa5d4ebe"},"schema_version":"1.0","source":{"id":"2605.25326","kind":"arxiv","version":1}},"canonical_sha256":"352f5f5bf7f297787d7d99176477d657773b0df97f7020cafaee18f600d925ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"352f5f5bf7f297787d7d99176477d657773b0df97f7020cafaee18f600d925ad","first_computed_at":"2026-05-26T02:04:29.020608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:29.020608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dEMr7XW1sbPtaFMXtBUZs/c2+tj3yU61aSSs3pXBr5gcfw+sgHtadouQgWvs9wu1BstlIrsYmE7EI3nNKbT9Cg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:29.021340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54c7924aa150a42aa2959689c8a344ae3f3c4907b67d1b6b6b5774f026d12c97","sha256:f422fb3742c7d01decd419d38edd77b6f2337d40b72ea45fe1f2a40989a1acb8"],"state_sha256":"a4372d3887efe0a95557ac4a040d059d01d416f812175e5faafaee9662ee2f04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQQVaQjnt8wuuchDblPLiZ50vciYveZ+2t7VgqWcPqWmftYzrMnlOD75ve45I9BrXI0vRycQiH54elbXE0jJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T15:58:32.438479Z","bundle_sha256":"6d9682fd1fca45e997c36c5a697b6c3b89f00f8961a0b7277c1e79cc1d8ec8c9"}}