{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H","short_pith_number":"pith:AAS5H6WR","canonical_record":{"source":{"id":"2605.15181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"bf8f241f814970b333036be9114bc2b37463e1f7f9f87fe4f7bf021354706150","abstract_canon_sha256":"9a53781f1c5961e660ff49946a7cb60b048666d463bd426a81f4b0d94f6a8e7e"},"schema_version":"1.0"},"canonical_sha256":"0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe","source":{"kind":"arxiv","id":"2605.15181","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15181","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15181v1","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"AAS5H6WR6BTU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"AAS5H6WR6BTUJYIR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"AAS5H6WR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"bf8f241f814970b333036be9114bc2b37463e1f7f9f87fe4f7bf021354706150","abstract_canon_sha256":"9a53781f1c5961e660ff49946a7cb60b048666d463bd426a81f4b0d94f6a8e7e"},"schema_version":"1.0"},"canonical_sha256":"0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe","last_reissued_at":"2026-05-17T21:57:18.530785Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.159506Z"},"source_kind":"arxiv","source_id":"2605.15181","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":"2026-05-17T21:18:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QrXpx9jnA25X2wpmzt2b1ZUga5pM9dnxeUqXbDElftFcGDGs6A1IR/yTqlAlVeJlHRZjfBfV1nXTAC38Ff+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T02:42:17.759091Z"},"content_sha256":"50e6d768acec7fd53d5690c918cd9c539f7e7baabb0a6be8c978b18a3e05f5c5","schema_version":"1.0","event_id":"sha256:50e6d768acec7fd53d5690c918cd9c539f7e7baabb0a6be8c978b18a3e05f5c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anirudh Sundara Rajan, Krishna Kumar Singh, Yong Jae Lee","submitted_at":"2026-05-14T17:58:19Z","abstract_excerpt":"Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"A vision-language judge can reliably provide accurate outcome-based rewards for both instruction adherence and visual quality across diverse editing tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5e75409e13b0d54d5778f7ff66906cb3caf1ea018739dee4f9559d473cb83b74"},"source":{"id":"2605.15181","kind":"arxiv","version":1},"verdict":{"id":"03a5af3b-4752-490b-9d98-176573c82df1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:17:29.103673Z","strongest_claim":"By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.","one_line_summary":"A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"A vision-language judge can reliably provide accurate outcome-based rewards for both instruction adherence and visual quality across diverse editing tasks.","pith_extraction_headline":"Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions."},"references":{"count":65,"sample":[{"doi":"","year":2025,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","ref_index":1,"cited_arxiv_id":"2511.21631","is_internal_anchor":true},{"doi":"","year":2023,"title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","work_id":"c74a3f49-dfa9-4aab-9ebc-8ab354db6d51","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"In: Proceed- ings of the IEEE/CVF International Conference on Computer Vision","work_id":"c01caa5e-e4f8-4277-8d53-3c05aa37b4c3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Emerging Properties in Unified Multimodal Pretraining","work_id":"e0cfd82c-f5d4-44fd-b531-ec73ab0a805b","ref_index":4,"cited_arxiv_id":"2505.14683","is_internal_anchor":true},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2309.17102 (2023)","work_id":"2bb3b94c-6b63-43cc-8c25-25ed4a0de29c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":65,"snapshot_sha256":"84e587fa0a178ca065ec274dd42bb9ff2e418a6df8dc85d67bc31d81048b33dc","internal_anchors":20},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2b12a0d4549333ff188fe8832a373dc30e238a3ef3d62d26b0a8a4879030dfac"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"03a5af3b-4752-490b-9d98-176573c82df1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zH+KdAQKIic8LGg3Gy/sM0rRs3tKUw2z55Ry7ubPmXGlkQjOq9buKdQ/Lj7t8/8mT7lPk5VhIsBIJMsGFcOoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T02:42:17.760037Z"},"content_sha256":"9b4d25e1c2cd54047f34ec2463219d2f040a159a6e5a583084c8c574d494a9a2","schema_version":"1.0","event_id":"sha256:9b4d25e1c2cd54047f34ec2463219d2f040a159a6e5a583084c8c574d494a9a2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H","target":"integrity","payload":{"note":"URL 'https://arxiv.org/abs/2512' returned status 404 (Not Found) at last check.","snippet":null,"arxiv_id":"2605.15181","detector":"external_links","evidence":{"url":"https://arxiv.org/abs/2512","final_url":"https://arxiv.org/abs/2512","host_kind":"arxiv","status_code":404,"status_text":"Not Found","verdict_class":"incontrovertible","checked_at_unix":1779190340.0186324},"severity":"advisory","ref_index":null,"audited_at":"2026-05-19T11:32:20.181640Z","event_type":"pith.integrity.v1","detected_doi":null,"detector_url":"https://pith.science/pith-integrity-protocol#external_links","external_url":"https://arxiv.org/abs/2512","finding_type":"dead_url","evidence_hash":"c5d13d1a6ada24cc32281bdf429bb98afde99a77d9b11457992ae5ceb6ad28f3","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1068,"payload_sha256":"dfdea0bd8c9860192f83e02340d3802ee6e8330cb045494418701b3cf7882ebd","signature_b64":"d095PHVAJdZRzwtri3/7IXn19qa98yqHU2OUnwfkPMbWNJC7bZCNhcpfXGPhcsS35IHsLg30HLERVTJLoLdeBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T11:37:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fDguBHyNLI/ocNHdBK6P7yDhIYWnQn9kVgC5Qe/LIBjft7DXUe4XYK2nbONJtwxdTltBUVOQ56JKl6XJKPgLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T02:42:17.761892Z"},"content_sha256":"d762de7a2371fb9c30b3bb57ac3b9deb6e8fe1876c55969add66c692b18fabf2","schema_version":"1.0","event_id":"sha256:d762de7a2371fb9c30b3bb57ac3b9deb6e8fe1876c55969add66c692b18fabf2"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H","target":"integrity","payload":{"note":"URL 'https://gemini.google.com/(2025' returned status 404 (Not Found) at last check.","snippet":null,"arxiv_id":"2605.15181","detector":"external_links","evidence":{"url":"https://gemini.google.com/(2025","final_url":"https://gemini.google.com/(2025","host_kind":"website","status_code":404,"status_text":"Not Found","verdict_class":"incontrovertible","checked_at_unix":1779190339.7984369},"severity":"advisory","ref_index":null,"audited_at":"2026-05-19T11:32:20.181640Z","event_type":"pith.integrity.v1","detected_doi":null,"detector_url":"https://pith.science/pith-integrity-protocol#external_links","external_url":"https://gemini.google.com/(2025","finding_type":"dead_url","evidence_hash":"1823ea861af6a12fc2b8e5438f4b8d1bbc5825b953e0df2c80ae99fe7e719f71","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":1067,"payload_sha256":"18081e1aee32a894cc239b2e1e6f7ff9e428222fd09d8cead4bd4aa4ba8362cb","signature_b64":"l+Bmn51e26P42DnxfQi3VsTXP/qqllOeerF0vn7RNM7qeclVkMOVwGd0TSUBqmB0CIazdMxM5h/d9F+KJgV9AA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-19T11:37:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0YEClnS7AC9CcrLn4aZnmJpCNXC2A1sF5YNVZH2nB/1t2A/NdCbhElRSKCU1Dt+1VCCbxsrxSdeMaLNqhmYcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T02:42:17.762450Z"},"content_sha256":"8187ecaf5176987da59d1c5c69943638674dd15a95ef1da2c19424a97016a98f","schema_version":"1.0","event_id":"sha256:8187ecaf5176987da59d1c5c69943638674dd15a95ef1da2c19424a97016a98f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H/bundle.json","state_url":"https://pith.science/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H/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":"2026-05-25T02:42:17Z","links":{"resolver":"https://pith.science/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H","bundle":"https://pith.science/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H/bundle.json","state":"https://pith.science/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AAS5H6WR6BTUJYIRHJ4U7HKY5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AAS5H6WR6BTUJYIRHJ4U7HKY5H","merge_version":"pith-open-graph-merge-v1","event_count":4,"valid_event_count":4,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9a53781f1c5961e660ff49946a7cb60b048666d463bd426a81f4b0d94f6a8e7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:58:19Z","title_canon_sha256":"bf8f241f814970b333036be9114bc2b37463e1f7f9f87fe4f7bf021354706150"},"schema_version":"1.0","source":{"id":"2605.15181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15181","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15181v1","created_at":"2026-05-17T21:18:32Z"},{"alias_kind":"pith_short_12","alias_value":"AAS5H6WR6BTU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"AAS5H6WR6BTUJYIR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"AAS5H6WR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9b4d25e1c2cd54047f34ec2463219d2f040a159a6e5a583084c8c574d494a9a2","target":"graph","created_at":"2026-05-17T21:57:18Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"A vision-language judge can reliably provide accurate outcome-based rewards for both instruction adherence and visual quality across diverse editing tasks."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions."}],"snapshot_sha256":"5e75409e13b0d54d5778f7ff66906cb3caf1ea018739dee4f9559d473cb83b74"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"2b12a0d4549333ff188fe8832a373dc30e238a3ef3d62d26b0a8a4879030dfac"},"paper":{"abstract_excerpt":"Modern image editing models produce realistic results but struggle with abstract, multi step instructions (e.g., ``make this advertisement more vegetarian-friendly''). Prior agent based methods decompose such tasks but rely on handcrafted pipelines or teacher imitation, limiting flexibility and decoupling learning from actual editing outcomes. We propose an experiential framework for long-horizon image editing, where a planner generates structured atomic decompositions and an orchestrator selects tools and regions to execute each step. A vision language judge provides outcome-based rewards for","authors_text":"Anirudh Sundara Rajan, Krishna Kumar Singh, Yong Jae Lee","cross_cats":[],"headline":"Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:58:19Z","title":"From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing"},"references":{"count":65,"internal_anchors":20,"resolved_work":65,"sample":[{"cited_arxiv_id":"2511.21631","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","work_id":"c74a3f49-dfa9-4aab-9ebc-8ab354db6d51","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"In: Proceed- ings of the IEEE/CVF International Conference on Computer Vision","work_id":"c01caa5e-e4f8-4277-8d53-3c05aa37b4c3","year":2023},{"cited_arxiv_id":"2505.14683","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Emerging Properties in Unified Multimodal Pretraining","work_id":"e0cfd82c-f5d4-44fd-b531-ec73ab0a805b","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2309.17102 (2023)","work_id":"2bb3b94c-6b63-43cc-8c25-25ed4a0de29c","year":2023}],"snapshot_sha256":"84e587fa0a178ca065ec274dd42bb9ff2e418a6df8dc85d67bc31d81048b33dc"},"source":{"id":"2605.15181","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:17:29.103673Z","id":"03a5af3b-4752-490b-9d98-176573c82df1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Coupling a planner with a reward-driven orchestrator enables reliable multi-step image editing from abstract instructions.","strongest_claim":"By tightly coupling planning with reward driven execution, our approach yields more coherent and reliable edits than single-step or rule-based multistep baselines.","weakest_assumption":"A vision-language judge can reliably provide accurate outcome-based rewards for both instruction adherence and visual quality across diverse editing tasks."}},"verdict_id":"03a5af3b-4752-490b-9d98-176573c82df1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50e6d768acec7fd53d5690c918cd9c539f7e7baabb0a6be8c978b18a3e05f5c5","target":"record","created_at":"2026-05-17T21:18:32Z","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":"9a53781f1c5961e660ff49946a7cb60b048666d463bd426a81f4b0d94f6a8e7e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T17:58:19Z","title_canon_sha256":"bf8f241f814970b333036be9114bc2b37463e1f7f9f87fe4f7bf021354706150"},"schema_version":"1.0","source":{"id":"2605.15181","kind":"arxiv","version":1}},"canonical_sha256":"0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0025d3fad1f06744e1113a794f9d58e9d3fbcd060b90873e4cad847620f61ffe","first_computed_at":"2026-05-17T21:40:25.159506Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:18.530785Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15181","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:8187ecaf5176987da59d1c5c69943638674dd15a95ef1da2c19424a97016a98f","sha256:d762de7a2371fb9c30b3bb57ac3b9deb6e8fe1876c55969add66c692b18fabf2"]}],"invalid_events":[],"applied_event_ids":["sha256:50e6d768acec7fd53d5690c918cd9c539f7e7baabb0a6be8c978b18a3e05f5c5","sha256:9b4d25e1c2cd54047f34ec2463219d2f040a159a6e5a583084c8c574d494a9a2"],"state_sha256":"19c02ea157f6633ef92d9669a4d13c85cbfd565cca790bc2cc71c498902bf993"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XLHVL0FF05nL+8DyJyhTFS/+fY7KRjVGm/nZPc5TM5B9/KVDzFWT1VO8GB+x9sb10MPK5Zc5AlAWOl655XqBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T02:42:17.766859Z","bundle_sha256":"0618c47ff9b706242684d657779ef39ac82bd76253af5987b1cd764ddf21bc19"}}