{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LO5BPYEGQGSJHTVVY4WAFAQSFL","short_pith_number":"pith:LO5BPYEG","canonical_record":{"source":{"id":"2605.16745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"e81542ff15bc1f6f5509b3fe4842b5b48c686b3d1b03fed83f8524096c3ede09","abstract_canon_sha256":"499a72a158fbe86ee84d8621bbbb168bf7da06e44a56bf595a23c08d3c99c033"},"schema_version":"1.0"},"canonical_sha256":"5bba17e08681a493ceb5c72c0282122ae8dc119b204e9c2dc78ae592a76f2ad5","source":{"kind":"arxiv","id":"2605.16745","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16745","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16745v1","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16745","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"LO5BPYEGQGSJ","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"LO5BPYEGQGSJHTVV","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"LO5BPYEG","created_at":"2026-05-20T00:02:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LO5BPYEGQGSJHTVVY4WAFAQSFL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"e81542ff15bc1f6f5509b3fe4842b5b48c686b3d1b03fed83f8524096c3ede09","abstract_canon_sha256":"499a72a158fbe86ee84d8621bbbb168bf7da06e44a56bf595a23c08d3c99c033"},"schema_version":"1.0"},"canonical_sha256":"5bba17e08681a493ceb5c72c0282122ae8dc119b204e9c2dc78ae592a76f2ad5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:39.528330Z","signature_b64":"lgVeEEHzondM3P4YiBLqFSo2YoQKxv4iYGWsVYrIu7RsJuF3lohZ2XP1uKEbNMGTRM/E1fnoGM1agObwgwEdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bba17e08681a493ceb5c72c0282122ae8dc119b204e9c2dc78ae592a76f2ad5","last_reissued_at":"2026-05-20T00:02:39.527485Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:39.527485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16745","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":"2026-05-20T00:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpfea1kQ6Z2ekwIaFt3+XSVUN5L8AmjeYkO9PfunXxPnFtdl/SqnyLLc6FM0OZGkA2/WSdTcZYuXlyjVWnN8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:37:15.357754Z"},"content_sha256":"cc10912e7efc6314580f32a73cb1cdd7f1fcf3f1e8583d52d28346834142a37a","schema_version":"1.0","event_id":"sha256:cc10912e7efc6314580f32a73cb1cdd7f1fcf3f1e8583d52d28346834142a37a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LO5BPYEGQGSJHTVVY4WAFAQSFL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"EVA01 integrates 3D meshes as a native modality inside multimodal language models using a mixture-of-transformers split.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baolin Liu, Bocheng Li, Chenzhuo Fan, Mingjing Yi, Shimu Wang, Wanli Ma, Yingde Song, Yongping Xiong, Yuke Lou, Zhengdong Guo, Zongyuan Yang","submitted_at":"2026-05-16T01:55:03Z","abstract_excerpt":"This paper addresses the challenge of integrating 3D meshes as a native modality within Multimodal Large Language Models (MLLMs). Diffusion-based large reconstruction models decouple semantic understanding from geometric reasoning, operating as stateless reconstructors conditioned on dense 2D pixel priors. Recent MLLM-based methods treat the 3D modality as an external output rather than a native component of the multimodal sequence, making incremental adaptations without a systematic analysis of how geometric manifolds align with MLLM feature spaces. We introduce EVA01, a unified framework tha"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EVA01 achieves state-of-the-art native text-to-3D generation fidelity and unlocks robust long-context multi-turn geometric editing with identity preservation, a capability fundamentally inaccessible to stateless reconstruction pipelines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that decoupling into a pre-trained Understanding Expert and a structurally mirrored Generation Expert, coupled through shared global self-attention with hard modality routing, will align the semantic latent space of the MLLM backbone with the geometric manifold without performance loss or the need for intermediate 2D representations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EVA01 integrates 3D meshes as a native modality inside multimodal language models using a mixture-of-transformers split.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ac27ce6371b0a894f587382b295671f811bff0dd8bcdfe642790e121eae87902"},"source":{"id":"2605.16745","kind":"arxiv","version":1},"verdict":{"id":"eed022b1-7a92-4f7e-8f74-0fc019656e51","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:20:55.777240Z","strongest_claim":"EVA01 achieves state-of-the-art native text-to-3D generation fidelity and unlocks robust long-context multi-turn geometric editing with identity preservation, a capability fundamentally inaccessible to stateless reconstruction pipelines.","one_line_summary":"EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that decoupling into a pre-trained Understanding Expert and a structurally mirrored Generation Expert, coupled through shared global self-attention with hard modality routing, will align the semantic latent space of the MLLM backbone with the geometric manifold without performance loss or the need for intermediate 2D representations.","pith_extraction_headline":"EVA01 integrates 3D meshes as a native modality inside multimodal language models using a mixture-of-transformers split."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16745/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.388825Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:31:15.256218Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.331028Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.461039Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"5096c211e3a6740ba9a11abcfee541ee07dc279d59b470125d8341bd3b1d120f"},"references":{"count":77,"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":2005,"title":"METEOR : An automatic metric for MT evaluation with improved correlation with human judgments","work_id":"8ef377b6-8e72-424b-9cca-582931404df4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Instant3DiT : Multiview inpainting for fast editing of 3D objects","work_id":"7870fecc-1a60-4a03-82c4-67dde070210a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","work_id":"5e9b3ddf-5b6b-4042-b640-d0d8757bfe14","ref_index":4,"cited_arxiv_id":"2604.12012","is_internal_anchor":true},{"doi":"","year":1918,"title":"ShapeNet: An Information-Rich 3D Model Repository","work_id":"b2ac5b60-daa9-435b-9369-12271e126edd","ref_index":5,"cited_arxiv_id":"1512.03012","is_internal_anchor":true}],"resolved_work":77,"snapshot_sha256":"b15689ee741e1a9089a564fef7de8ea19ac3b7209e0f83b88389668c9f9100c3","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f73224ace45fc37e41361f5897d8e99e8833124e1119b6acea0027bcc3348e21"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"eed022b1-7a92-4f7e-8f74-0fc019656e51"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIvuHH7KLAeYHhJ40x4mfSFat9IXv5EumIw0TE+DExnE7oOE5VR9ArxSmja5cdP2Eu5hryyKxZ4ZpQ52eIXPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T03:37:15.358920Z"},"content_sha256":"16fe8b5cf65748a66526a374b2d0b6a9a34bda57ebfe077956e4da62a0bcd344","schema_version":"1.0","event_id":"sha256:16fe8b5cf65748a66526a374b2d0b6a9a34bda57ebfe077956e4da62a0bcd344"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL/bundle.json","state_url":"https://pith.science/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL/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":"2026-05-22T03:37:15Z","links":{"resolver":"https://pith.science/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL","bundle":"https://pith.science/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL/bundle.json","state":"https://pith.science/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LO5BPYEGQGSJHTVVY4WAFAQSFL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LO5BPYEGQGSJHTVVY4WAFAQSFL","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":"499a72a158fbe86ee84d8621bbbb168bf7da06e44a56bf595a23c08d3c99c033","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:55:03Z","title_canon_sha256":"e81542ff15bc1f6f5509b3fe4842b5b48c686b3d1b03fed83f8524096c3ede09"},"schema_version":"1.0","source":{"id":"2605.16745","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16745","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16745v1","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16745","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"LO5BPYEGQGSJ","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_16","alias_value":"LO5BPYEGQGSJHTVV","created_at":"2026-05-20T00:02:39Z"},{"alias_kind":"pith_short_8","alias_value":"LO5BPYEG","created_at":"2026-05-20T00:02:39Z"}],"graph_snapshots":[{"event_id":"sha256:16fe8b5cf65748a66526a374b2d0b6a9a34bda57ebfe077956e4da62a0bcd344","target":"graph","created_at":"2026-05-20T00:02:39Z","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":"EVA01 achieves state-of-the-art native text-to-3D generation fidelity and unlocks robust long-context multi-turn geometric editing with identity preservation, a capability fundamentally inaccessible to stateless reconstruction pipelines."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that decoupling into a pre-trained Understanding Expert and a structurally mirrored Generation Expert, coupled through shared global self-attention with hard modality routing, will align the semantic latent space of the MLLM backbone with the geometric manifold without performance loss or the need for intermediate 2D representations."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"EVA01 integrates 3D meshes as a native modality inside multimodal language models using a mixture-of-transformers split."}],"snapshot_sha256":"ac27ce6371b0a894f587382b295671f811bff0dd8bcdfe642790e121eae87902"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f73224ace45fc37e41361f5897d8e99e8833124e1119b6acea0027bcc3348e21"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.388825Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:31:15.256218Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.331028Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.461039Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16745/integrity.json","findings":[],"snapshot_sha256":"5096c211e3a6740ba9a11abcfee541ee07dc279d59b470125d8341bd3b1d120f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the challenge of integrating 3D meshes as a native modality within Multimodal Large Language Models (MLLMs). Diffusion-based large reconstruction models decouple semantic understanding from geometric reasoning, operating as stateless reconstructors conditioned on dense 2D pixel priors. Recent MLLM-based methods treat the 3D modality as an external output rather than a native component of the multimodal sequence, making incremental adaptations without a systematic analysis of how geometric manifolds align with MLLM feature spaces. We introduce EVA01, a unified framework tha","authors_text":"Baolin Liu, Bocheng Li, Chenzhuo Fan, Mingjing Yi, Shimu Wang, Wanli Ma, Yingde Song, Yongping Xiong, Yuke Lou, Zhengdong Guo, Zongyuan Yang","cross_cats":[],"headline":"EVA01 integrates 3D meshes as a native modality inside multimodal language models using a mixture-of-transformers split.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:55:03Z","title":"EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers"},"references":{"count":77,"internal_anchors":13,"resolved_work":77,"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":"METEOR : An automatic metric for MT evaluation with improved correlation with human judgments","work_id":"8ef377b6-8e72-424b-9cca-582931404df4","year":2005},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Instant3DiT : Multiview inpainting for fast editing of 3D objects","work_id":"7870fecc-1a60-4a03-82c4-67dde070210a","year":2025},{"cited_arxiv_id":"2604.12012","doi":"","is_internal_anchor":true,"ref_index":4,"title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","work_id":"5e9b3ddf-5b6b-4042-b640-d0d8757bfe14","year":2026},{"cited_arxiv_id":"1512.03012","doi":"","is_internal_anchor":true,"ref_index":5,"title":"ShapeNet: An Information-Rich 3D Model Repository","work_id":"b2ac5b60-daa9-435b-9369-12271e126edd","year":1918}],"snapshot_sha256":"b15689ee741e1a9089a564fef7de8ea19ac3b7209e0f83b88389668c9f9100c3"},"source":{"id":"2605.16745","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:20:55.777240Z","id":"eed022b1-7a92-4f7e-8f74-0fc019656e51","model_set":{"reader":"grok-4.3"},"one_line_summary":"EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"EVA01 integrates 3D meshes as a native modality inside multimodal language models using a mixture-of-transformers split.","strongest_claim":"EVA01 achieves state-of-the-art native text-to-3D generation fidelity and unlocks robust long-context multi-turn geometric editing with identity preservation, a capability fundamentally inaccessible to stateless reconstruction pipelines.","weakest_assumption":"The assumption that decoupling into a pre-trained Understanding Expert and a structurally mirrored Generation Expert, coupled through shared global self-attention with hard modality routing, will align the semantic latent space of the MLLM backbone with the geometric manifold without performance loss or the need for intermediate 2D representations."}},"verdict_id":"eed022b1-7a92-4f7e-8f74-0fc019656e51"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc10912e7efc6314580f32a73cb1cdd7f1fcf3f1e8583d52d28346834142a37a","target":"record","created_at":"2026-05-20T00:02:39Z","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":"499a72a158fbe86ee84d8621bbbb168bf7da06e44a56bf595a23c08d3c99c033","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T01:55:03Z","title_canon_sha256":"e81542ff15bc1f6f5509b3fe4842b5b48c686b3d1b03fed83f8524096c3ede09"},"schema_version":"1.0","source":{"id":"2605.16745","kind":"arxiv","version":1}},"canonical_sha256":"5bba17e08681a493ceb5c72c0282122ae8dc119b204e9c2dc78ae592a76f2ad5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bba17e08681a493ceb5c72c0282122ae8dc119b204e9c2dc78ae592a76f2ad5","first_computed_at":"2026-05-20T00:02:39.527485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:39.527485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lgVeEEHzondM3P4YiBLqFSo2YoQKxv4iYGWsVYrIu7RsJuF3lohZ2XP1uKEbNMGTRM/E1fnoGM1agObwgwEdCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:39.528330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16745","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc10912e7efc6314580f32a73cb1cdd7f1fcf3f1e8583d52d28346834142a37a","sha256:16fe8b5cf65748a66526a374b2d0b6a9a34bda57ebfe077956e4da62a0bcd344"],"state_sha256":"2c3fbf30f58018d01f67eb71174c3ee57b49cb37efaa0cdb573c648875ea6d8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QqlmEvSDV1I8TkrCd332KoOTINws4EEfgzfSQvs6druDMOi7Nb/xR7kgLTQQ9rMhEGY6agI5Q0datgCVBreAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T03:37:15.363916Z","bundle_sha256":"0bf4d93c22f44663b59d3da5be3c0a749b93f0126e47cde83582711a76c811ab"}}