{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V6AFODQWB6RMKC5W2F6CZZE4RD","short_pith_number":"pith:V6AFODQW","canonical_record":{"source":{"id":"2605.15816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-15T10:12:42Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"878240c9a7b1ca1bfa630d94d497f02aab33c7f22827b900a4d31515460fdc43","abstract_canon_sha256":"ace14513057e3275a4c20c893703b258e453391aef919753fa00182f728fe2ff"},"schema_version":"1.0"},"canonical_sha256":"af80570e160fa2c50bb6d17c2ce49c88ea90f12fb3438bef6ed5c9f2e040c06c","source":{"kind":"arxiv","id":"2605.15816","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15816","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15816v1","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15816","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"V6AFODQWB6RM","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"V6AFODQWB6RMKC5W","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"V6AFODQW","created_at":"2026-05-20T00:01:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V6AFODQWB6RMKC5W2F6CZZE4RD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-15T10:12:42Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"878240c9a7b1ca1bfa630d94d497f02aab33c7f22827b900a4d31515460fdc43","abstract_canon_sha256":"ace14513057e3275a4c20c893703b258e453391aef919753fa00182f728fe2ff"},"schema_version":"1.0"},"canonical_sha256":"af80570e160fa2c50bb6d17c2ce49c88ea90f12fb3438bef6ed5c9f2e040c06c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:20.056911Z","signature_b64":"9aF6jgxgc/6tGzs39mR1i9loBwyuB/FRh1nBqO94q6Pvsb7XBItM8YL9Fa7sZw5RzymTYew/kQTEz6YQQGE0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af80570e160fa2c50bb6d17c2ce49c88ea90f12fb3438bef6ed5c9f2e040c06c","last_reissued_at":"2026-05-20T00:01:20.054995Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:20.054995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15816","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":"2026-05-20T00:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9TGBIRYTErn5VJBVJpumQyrqf4AMeGbFtgr0r+W35ijJv0lZkNgL/egzXuz9DSHacnLUkt7dvj7aB5Mn6L2SAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:02:06.863337Z"},"content_sha256":"0a0576cc3bd3eb12153f99ba7720866c09a229b843ec700dbd5dfb9c35426123","schema_version":"1.0","event_id":"sha256:0a0576cc3bd3eb12153f99ba7720866c09a229b843ec700dbd5dfb9c35426123"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V6AFODQWB6RMKC5W2F6CZZE4RD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A diffusion-based sampler produces capacity-constrained stipples for any target density using a single trained checkpoint.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.GR","authors_text":"Aleksander Plocharski, Andrei Sharf, Ofir Gilad, Przemyslaw Musialski","submitted_at":"2026-05-15T10:12:42Z","abstract_excerpt":"Stipple patterns, point sets whose local density tracks a target image, are traditionally produced by per-density iterative optimizers, which are slow, non-differentiable, and must be re-run from scratch for each new target. Learned alternatives have so far addressed only unconditional point generation; capacity-constrained, image-conditioned stippling has remained out of reach. We present the first diffusion-based sampler that simultaneously satisfies a learned local point-distribution prior and a continuous, image-defined capacity constraint at inference. The method is a ControlNet branch bu"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count. On the Icons-50 benchmark, our learned sampler reaches parity with per-density-optimized baselines on every reported metric while remaining differentiable end-to-end.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that restricting training and inference to the late-stage denoising regime, initializing from a density-weighted rejection sample, and replacing zero-convolution injection with a sigmoid-gated 1x1 projection is sufficient to preserve the base model's blue-noise structure under hard density signals.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"StippleDiffusion is a late-stage denoising ControlNet on an optimal-transport point-set diffusion baseline that produces capacity-constrained stipples from arbitrary density maps, generalizes to unseen point budgets, and matches optimization baselines on Icons-50 while remaining end-to-end trainable","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A diffusion-based sampler produces capacity-constrained stipples for any target density using a single trained checkpoint.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"50a3de3c6fff82c3df0602a4e2f10ddec530196f0adba2ad86fe28f2f719d075"},"source":{"id":"2605.15816","kind":"arxiv","version":1},"verdict":{"id":"2c080273-6f13-4b22-b17e-780a49f189fa","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:35:38.495093Z","strongest_claim":"A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count. On the Icons-50 benchmark, our learned sampler reaches parity with per-density-optimized baselines on every reported metric while remaining differentiable end-to-end.","one_line_summary":"StippleDiffusion is a late-stage denoising ControlNet on an optimal-transport point-set diffusion baseline that produces capacity-constrained stipples from arbitrary density maps, generalizes to unseen point budgets, and matches optimization baselines on Icons-50 while remaining end-to-end trainable","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that restricting training and inference to the late-stage denoising regime, initializing from a density-weighted rejection sample, and replacing zero-convolution injection with a sigmoid-gated 1x1 projection is sufficient to preserve the base model's blue-noise structure under hard density signals.","pith_extraction_headline":"A diffusion-based sampler produces capacity-constrained stipples for any target density using a single trained checkpoint."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15816/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.010762Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:41:19.064468Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.727604Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.880310Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"79bdfbd0a3fce9ca2d805395e550f6aa13474290709933efb2eaee1396076b68"},"references":{"count":50,"sample":[{"doi":"10.1145/1576246.1531392","year":2009,"title":"Capacity-constrained point distributions: a variant of Lloyd's method , year =","work_id":"242766a8-4f59-446a-83d4-b27864a414d4","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/1730804.1730985","year":2010,"title":"and Fu, Chi-Wing , title =","work_id":"f28cc203-b088-4f5b-806f-384ff10e4888","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/508530.508537","year":2002,"title":"Proceedings of the 2nd International Symposium on Non-Photorealistic Animation and Rendering , pages =","work_id":"e3c09a48-c0fd-4e0b-968d-227d05a7dd13","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3550454.3555519","year":2022,"title":"Ahmed, Abdalla G. M. and Ren, Jing and Wonka, Peter , title =. 2022 , issue_date =. doi:10.1145/3550454.3555519 , journal =","work_id":"4329a3fc-f320-40a3-9e50-3ea63161aa52","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Blue Noise through Optimal Transport , author =. ACM Trans. Graph. (SIGGRAPH Asia) , volume=","work_id":"af520dd3-ca95-492b-bf06-5b1599594ee4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":50,"snapshot_sha256":"cafa2d265a7ddac0bb4f15d606075251330b729507f23bafd834e0ad88124983","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"cf15406429afb567bff54a2748896ef038e76cf7c380a92a2b2ff739f3848248"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2c080273-6f13-4b22-b17e-780a49f189fa"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tl8BiJ1MmjBpVB+na7+wp6+f1yfXH/tvXrmjMlAtm/qyARPjbj6plWfW42PtQ1DKER44CST6/L8043IODXsIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:02:06.864692Z"},"content_sha256":"ffe96f0bde528c5b640beb09b3f8410e1126f0a20a447bc5c101d0d02faa4ba8","schema_version":"1.0","event_id":"sha256:ffe96f0bde528c5b640beb09b3f8410e1126f0a20a447bc5c101d0d02faa4ba8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6AFODQWB6RMKC5W2F6CZZE4RD/bundle.json","state_url":"https://pith.science/pith/V6AFODQWB6RMKC5W2F6CZZE4RD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6AFODQWB6RMKC5W2F6CZZE4RD/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":"2026-05-23T16:02:06Z","links":{"resolver":"https://pith.science/pith/V6AFODQWB6RMKC5W2F6CZZE4RD","bundle":"https://pith.science/pith/V6AFODQWB6RMKC5W2F6CZZE4RD/bundle.json","state":"https://pith.science/pith/V6AFODQWB6RMKC5W2F6CZZE4RD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6AFODQWB6RMKC5W2F6CZZE4RD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V6AFODQWB6RMKC5W2F6CZZE4RD","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":"ace14513057e3275a4c20c893703b258e453391aef919753fa00182f728fe2ff","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-15T10:12:42Z","title_canon_sha256":"878240c9a7b1ca1bfa630d94d497f02aab33c7f22827b900a4d31515460fdc43"},"schema_version":"1.0","source":{"id":"2605.15816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15816","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15816v1","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15816","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"pith_short_12","alias_value":"V6AFODQWB6RM","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"pith_short_16","alias_value":"V6AFODQWB6RMKC5W","created_at":"2026-05-20T00:01:20Z"},{"alias_kind":"pith_short_8","alias_value":"V6AFODQW","created_at":"2026-05-20T00:01:20Z"}],"graph_snapshots":[{"event_id":"sha256:ffe96f0bde528c5b640beb09b3f8410e1126f0a20a447bc5c101d0d02faa4ba8","target":"graph","created_at":"2026-05-20T00:01:20Z","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":"A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count. On the Icons-50 benchmark, our learned sampler reaches parity with per-density-optimized baselines on every reported metric while remaining differentiable end-to-end."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that restricting training and inference to the late-stage denoising regime, initializing from a density-weighted rejection sample, and replacing zero-convolution injection with a sigmoid-gated 1x1 projection is sufficient to preserve the base model's blue-noise structure under hard density signals."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"StippleDiffusion is a late-stage denoising ControlNet on an optimal-transport point-set diffusion baseline that produces capacity-constrained stipples from arbitrary density maps, generalizes to unseen point budgets, and matches optimization baselines on Icons-50 while remaining end-to-end trainable"},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A diffusion-based sampler produces capacity-constrained stipples for any target density using a single trained checkpoint."}],"snapshot_sha256":"50a3de3c6fff82c3df0602a4e2f10ddec530196f0adba2ad86fe28f2f719d075"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"cf15406429afb567bff54a2748896ef038e76cf7c380a92a2b2ff739f3848248"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.010762Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:41:19.064468Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.727604Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.880310Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15816/integrity.json","findings":[],"snapshot_sha256":"79bdfbd0a3fce9ca2d805395e550f6aa13474290709933efb2eaee1396076b68","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stipple patterns, point sets whose local density tracks a target image, are traditionally produced by per-density iterative optimizers, which are slow, non-differentiable, and must be re-run from scratch for each new target. Learned alternatives have so far addressed only unconditional point generation; capacity-constrained, image-conditioned stippling has remained out of reach. We present the first diffusion-based sampler that simultaneously satisfies a learned local point-distribution prior and a continuous, image-defined capacity constraint at inference. The method is a ControlNet branch bu","authors_text":"Aleksander Plocharski, Andrei Sharf, Ofir Gilad, Przemyslaw Musialski","cross_cats":["cs.CV","cs.LG"],"headline":"A diffusion-based sampler produces capacity-constrained stipples for any target density using a single trained checkpoint.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-15T10:12:42Z","title":"StippleDiffusion: Capacity-Constrained Stippling using Controlled Diffusion"},"references":{"count":50,"internal_anchors":0,"resolved_work":50,"sample":[{"cited_arxiv_id":"","doi":"10.1145/1576246.1531392","is_internal_anchor":false,"ref_index":1,"title":"Capacity-constrained point distributions: a variant of Lloyd's method , year =","work_id":"242766a8-4f59-446a-83d4-b27864a414d4","year":2009},{"cited_arxiv_id":"","doi":"10.1145/1730804.1730985","is_internal_anchor":false,"ref_index":2,"title":"and Fu, Chi-Wing , title =","work_id":"f28cc203-b088-4f5b-806f-384ff10e4888","year":2010},{"cited_arxiv_id":"","doi":"10.1145/508530.508537","is_internal_anchor":false,"ref_index":3,"title":"Proceedings of the 2nd International Symposium on Non-Photorealistic Animation and Rendering , pages =","work_id":"e3c09a48-c0fd-4e0b-968d-227d05a7dd13","year":2002},{"cited_arxiv_id":"","doi":"10.1145/3550454.3555519","is_internal_anchor":false,"ref_index":4,"title":"Ahmed, Abdalla G. M. and Ren, Jing and Wonka, Peter , title =. 2022 , issue_date =. doi:10.1145/3550454.3555519 , journal =","work_id":"4329a3fc-f320-40a3-9e50-3ea63161aa52","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Blue Noise through Optimal Transport , author =. ACM Trans. Graph. (SIGGRAPH Asia) , volume=","work_id":"af520dd3-ca95-492b-bf06-5b1599594ee4","year":null}],"snapshot_sha256":"cafa2d265a7ddac0bb4f15d606075251330b729507f23bafd834e0ad88124983"},"source":{"id":"2605.15816","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T18:35:38.495093Z","id":"2c080273-6f13-4b22-b17e-780a49f189fa","model_set":{"reader":"grok-4.3"},"one_line_summary":"StippleDiffusion is a late-stage denoising ControlNet on an optimal-transport point-set diffusion baseline that produces capacity-constrained stipples from arbitrary density maps, generalizes to unseen point budgets, and matches optimization baselines on Icons-50 while remaining end-to-end trainable","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A diffusion-based sampler produces capacity-constrained stipples for any target density using a single trained checkpoint.","strongest_claim":"A single trained checkpoint accepts arbitrary target densities at inference, generalizes to point budgets that were not seen during training, and produces stipples in time nearly independent of the output point count. On the Icons-50 benchmark, our learned sampler reaches parity with per-density-optimized baselines on every reported metric while remaining differentiable end-to-end.","weakest_assumption":"The assumption that restricting training and inference to the late-stage denoising regime, initializing from a density-weighted rejection sample, and replacing zero-convolution injection with a sigmoid-gated 1x1 projection is sufficient to preserve the base model's blue-noise structure under hard density signals."}},"verdict_id":"2c080273-6f13-4b22-b17e-780a49f189fa"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0a0576cc3bd3eb12153f99ba7720866c09a229b843ec700dbd5dfb9c35426123","target":"record","created_at":"2026-05-20T00:01:20Z","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":"ace14513057e3275a4c20c893703b258e453391aef919753fa00182f728fe2ff","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-15T10:12:42Z","title_canon_sha256":"878240c9a7b1ca1bfa630d94d497f02aab33c7f22827b900a4d31515460fdc43"},"schema_version":"1.0","source":{"id":"2605.15816","kind":"arxiv","version":1}},"canonical_sha256":"af80570e160fa2c50bb6d17c2ce49c88ea90f12fb3438bef6ed5c9f2e040c06c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af80570e160fa2c50bb6d17c2ce49c88ea90f12fb3438bef6ed5c9f2e040c06c","first_computed_at":"2026-05-20T00:01:20.054995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:20.054995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9aF6jgxgc/6tGzs39mR1i9loBwyuB/FRh1nBqO94q6Pvsb7XBItM8YL9Fa7sZw5RzymTYew/kQTEz6YQQGE0Aw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:20.056911Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a0576cc3bd3eb12153f99ba7720866c09a229b843ec700dbd5dfb9c35426123","sha256:ffe96f0bde528c5b640beb09b3f8410e1126f0a20a447bc5c101d0d02faa4ba8"],"state_sha256":"d96e10e41fe20019ff2e2d5a114125be949c17f78a6033db569ba80c747cc434"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k+JWABfnKAhpjXYTbqzRFHSpWTb/ywnym6Glx67KDBlezH+BjpyB5KERO+sEv45YHGprjoO870nKdpXQ5qQpAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T16:02:06.870336Z","bundle_sha256":"efdf5f59c7a1aafa0f9cde26194ee6b8dbf10f0fc1c741f857cdcf90d4c11d5e"}}