{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JQJ2RQJBQYASI4AKW3GQ2NIWQS","short_pith_number":"pith:JQJ2RQJB","canonical_record":{"source":{"id":"2605.16901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"50f104fd5abe006b6c103c9f7333854c3b5bcb5cc1b71a03c8e54b93cfe8eb47","abstract_canon_sha256":"852671bb7aa0c6dcc2ce53073a454b1de263183adede5685429d29f084749701"},"schema_version":"1.0"},"canonical_sha256":"4c13a8c121860124700ab6cd0d3516848bf989482cf23c8551c38ce6629b4820","source":{"kind":"arxiv","id":"2605.16901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16901","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16901v1","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16901","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"JQJ2RQJBQYAS","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"JQJ2RQJBQYASI4AK","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"JQJ2RQJB","created_at":"2026-05-20T00:03:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JQJ2RQJBQYASI4AKW3GQ2NIWQS","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:25:23Z","cross_cats_sorted":[],"title_canon_sha256":"50f104fd5abe006b6c103c9f7333854c3b5bcb5cc1b71a03c8e54b93cfe8eb47","abstract_canon_sha256":"852671bb7aa0c6dcc2ce53073a454b1de263183adede5685429d29f084749701"},"schema_version":"1.0"},"canonical_sha256":"4c13a8c121860124700ab6cd0d3516848bf989482cf23c8551c38ce6629b4820","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:29.168119Z","signature_b64":"dkczYL+Cuce8jkOQKgHYpVxK2+5AFK/cpM7RFfF623VUJCZFAHBOQwzYECdhU5NdLghZbP11IAWxbT1MUSbiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c13a8c121860124700ab6cd0d3516848bf989482cf23c8551c38ce6629b4820","last_reissued_at":"2026-05-20T00:03:29.167241Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:29.167241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16901","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":"2026-05-20T00:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0+QKJnV2uFYeguiaTXlPFo3Z6Nx3mg6qgrn311ISgRrwyqKOuIKAvJXBo82QOOjZWcb4/whYK6QDfELR1rQGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:59:13.718570Z"},"content_sha256":"52bfb23fede080836d233d404e2705294c432acd943f12d15818fbbe42fb9f7c","schema_version":"1.0","event_id":"sha256:52bfb23fede080836d233d404e2705294c432acd943f12d15818fbbe42fb9f7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JQJ2RQJBQYASI4AKW3GQ2NIWQS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CAR-SAM enables effective 4-bit post-training quantization of the Segment Anything Model by fixing decoder attention issues.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dawei Yang, Houji Wen, Jiangyong Yu, Jun Li","submitted_at":"2026-05-16T09:25:23Z","abstract_excerpt":"Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-Training Quantization (PTQ) is a widely used technique for model compression and acceleration. However, existing PTQ methods fail to consider the cross-attention architecture in the SAM decoder. This degradation primarily stems from the unique challenges posed by SAMs: (1) Attention dissipation, where the attention information in the decoder, which is crucial for repres"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CAR-SAM robustly quantizes SAM models down to 4-bit precision, surpassing existing methods by 14.6% and 6.6% mAP on SAM-B and SAM-L respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The primary degradation in existing PTQ for SAM stems from attention dissipation and reconstruction oscillation in the decoder, and that MAC and JCAR mechanisms directly mitigate these without introducing new instabilities or requiring model-specific retraining.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CAR-SAM introduces MatMul-Aware Compensation and Joint Cross-Attention Reconstruction to enable stable 4-bit post-training quantization of SAM, outperforming prior PTQ methods by 14.6% mAP on SAM-B and 6.6% on SAM-L.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CAR-SAM enables effective 4-bit post-training quantization of the Segment Anything Model by fixing decoder attention issues.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e5a40b937fb290b6777b25ce8232da705c1e8b55348f1f8a05d8cbe1fa81ef49"},"source":{"id":"2605.16901","kind":"arxiv","version":1},"verdict":{"id":"a7156ea7-26a7-4773-bf6c-e4dc47c48217","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:24:32.134695Z","strongest_claim":"CAR-SAM robustly quantizes SAM models down to 4-bit precision, surpassing existing methods by 14.6% and 6.6% mAP on SAM-B and SAM-L respectively.","one_line_summary":"CAR-SAM introduces MatMul-Aware Compensation and Joint Cross-Attention Reconstruction to enable stable 4-bit post-training quantization of SAM, outperforming prior PTQ methods by 14.6% mAP on SAM-B and 6.6% on SAM-L.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The primary degradation in existing PTQ for SAM stems from attention dissipation and reconstruction oscillation in the decoder, and that MAC and JCAR mechanisms directly mitigate these without introducing new instabilities or requiring model-specific retraining.","pith_extraction_headline":"CAR-SAM enables effective 4-bit post-training quantization of the Segment Anything Model by fixing decoder attention issues."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16901/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.177730Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:30:53.139970Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T20:52:23.455391Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.276532Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.355562Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d2e38e37fb9e74cf1438d437c772915d6f0ad1cb6e6969d3c6d3ce60a753aa25"},"references":{"count":29,"sample":[{"doi":"","year":2020,"title":"Lsq+: Improving low-bit quantization through learnable offsets and better initializa- tion","work_id":"217e9b6d-bd0c-4b1b-83aa-f99b47202891","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Slimsam: 0.1% data makes segment anything slim","work_id":"ca75805e-ee7f-42ab-a074-9fc92e8f038f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1902,"title":"Learned step size quantization","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","work_id":"19ed8c44-202a-48f6-8169-637d5a5f2408","ref_index":4,"cited_arxiv_id":"2210.17323","is_internal_anchor":true},{"doi":"","year":2023,"title":"Segment any- thing","work_id":"ed377056-362a-456e-829c-8277945208d9","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"9fb47f31029b22f3bdbf3ad21e5bcca6f681d1e7e6ba6760caf600e105a0b2c0","internal_anchors":4},"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":"a7156ea7-26a7-4773-bf6c-e4dc47c48217"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bRMl+v+R+ovv1yYs3IQ11fxOYmFUsHh4ABBes83fUr0b2iRFsObfU32yY0BB0YpQAv1QMSdz2u5M3kgTmJ8oBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T11:59:13.719604Z"},"content_sha256":"b19f3f8b32dd148187646049779f55b59851b8d27b079da54e51014614875588","schema_version":"1.0","event_id":"sha256:b19f3f8b32dd148187646049779f55b59851b8d27b079da54e51014614875588"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS/bundle.json","state_url":"https://pith.science/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS/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":"2026-05-27T11:59:13Z","links":{"resolver":"https://pith.science/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS","bundle":"https://pith.science/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS/bundle.json","state":"https://pith.science/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQJ2RQJBQYASI4AKW3GQ2NIWQS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JQJ2RQJBQYASI4AKW3GQ2NIWQS","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":"852671bb7aa0c6dcc2ce53073a454b1de263183adede5685429d29f084749701","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:25:23Z","title_canon_sha256":"50f104fd5abe006b6c103c9f7333854c3b5bcb5cc1b71a03c8e54b93cfe8eb47"},"schema_version":"1.0","source":{"id":"2605.16901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16901","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16901v1","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16901","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"pith_short_12","alias_value":"JQJ2RQJBQYAS","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"pith_short_16","alias_value":"JQJ2RQJBQYASI4AK","created_at":"2026-05-20T00:03:29Z"},{"alias_kind":"pith_short_8","alias_value":"JQJ2RQJB","created_at":"2026-05-20T00:03:29Z"}],"graph_snapshots":[{"event_id":"sha256:b19f3f8b32dd148187646049779f55b59851b8d27b079da54e51014614875588","target":"graph","created_at":"2026-05-20T00:03:29Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"CAR-SAM robustly quantizes SAM models down to 4-bit precision, surpassing existing methods by 14.6% and 6.6% mAP on SAM-B and SAM-L respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The primary degradation in existing PTQ for SAM stems from attention dissipation and reconstruction oscillation in the decoder, and that MAC and JCAR mechanisms directly mitigate these without introducing new instabilities or requiring model-specific retraining."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CAR-SAM introduces MatMul-Aware Compensation and Joint Cross-Attention Reconstruction to enable stable 4-bit post-training quantization of SAM, outperforming prior PTQ methods by 14.6% mAP on SAM-B and 6.6% on SAM-L."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CAR-SAM enables effective 4-bit post-training quantization of the Segment Anything Model by fixing decoder attention issues."}],"snapshot_sha256":"e5a40b937fb290b6777b25ce8232da705c1e8b55348f1f8a05d8cbe1fa81ef49"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.177730Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:30:53.139970Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T20:52:23.455391Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.276532Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.355562Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16901/integrity.json","findings":[],"snapshot_sha256":"d2e38e37fb9e74cf1438d437c772915d6f0ad1cb6e6969d3c6d3ce60a753aa25","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-Training Quantization (PTQ) is a widely used technique for model compression and acceleration. However, existing PTQ methods fail to consider the cross-attention architecture in the SAM decoder. This degradation primarily stems from the unique challenges posed by SAMs: (1) Attention dissipation, where the attention information in the decoder, which is crucial for repres","authors_text":"Dawei Yang, Houji Wen, Jiangyong Yu, Jun Li","cross_cats":[],"headline":"CAR-SAM enables effective 4-bit post-training quantization of the Segment Anything Model by fixing decoder attention issues.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:25:23Z","title":"CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model"},"references":{"count":29,"internal_anchors":4,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Lsq+: Improving low-bit quantization through learnable offsets and better initializa- tion","work_id":"217e9b6d-bd0c-4b1b-83aa-f99b47202891","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Slimsam: 0.1% data makes segment anything slim","work_id":"ca75805e-ee7f-42ab-a074-9fc92e8f038f","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Learned step size quantization","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},{"cited_arxiv_id":"2210.17323","doi":"","is_internal_anchor":true,"ref_index":4,"title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","work_id":"19ed8c44-202a-48f6-8169-637d5a5f2408","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Segment any- thing","work_id":"ed377056-362a-456e-829c-8277945208d9","year":2023}],"snapshot_sha256":"9fb47f31029b22f3bdbf3ad21e5bcca6f681d1e7e6ba6760caf600e105a0b2c0"},"source":{"id":"2605.16901","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:24:32.134695Z","id":"a7156ea7-26a7-4773-bf6c-e4dc47c48217","model_set":{"reader":"grok-4.3"},"one_line_summary":"CAR-SAM introduces MatMul-Aware Compensation and Joint Cross-Attention Reconstruction to enable stable 4-bit post-training quantization of SAM, outperforming prior PTQ methods by 14.6% mAP on SAM-B and 6.6% on SAM-L.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CAR-SAM enables effective 4-bit post-training quantization of the Segment Anything Model by fixing decoder attention issues.","strongest_claim":"CAR-SAM robustly quantizes SAM models down to 4-bit precision, surpassing existing methods by 14.6% and 6.6% mAP on SAM-B and SAM-L respectively.","weakest_assumption":"The primary degradation in existing PTQ for SAM stems from attention dissipation and reconstruction oscillation in the decoder, and that MAC and JCAR mechanisms directly mitigate these without introducing new instabilities or requiring model-specific retraining."}},"verdict_id":"a7156ea7-26a7-4773-bf6c-e4dc47c48217"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:52bfb23fede080836d233d404e2705294c432acd943f12d15818fbbe42fb9f7c","target":"record","created_at":"2026-05-20T00:03:29Z","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":"852671bb7aa0c6dcc2ce53073a454b1de263183adede5685429d29f084749701","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T09:25:23Z","title_canon_sha256":"50f104fd5abe006b6c103c9f7333854c3b5bcb5cc1b71a03c8e54b93cfe8eb47"},"schema_version":"1.0","source":{"id":"2605.16901","kind":"arxiv","version":1}},"canonical_sha256":"4c13a8c121860124700ab6cd0d3516848bf989482cf23c8551c38ce6629b4820","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c13a8c121860124700ab6cd0d3516848bf989482cf23c8551c38ce6629b4820","first_computed_at":"2026-05-20T00:03:29.167241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:29.167241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dkczYL+Cuce8jkOQKgHYpVxK2+5AFK/cpM7RFfF623VUJCZFAHBOQwzYECdhU5NdLghZbP11IAWxbT1MUSbiAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:29.168119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52bfb23fede080836d233d404e2705294c432acd943f12d15818fbbe42fb9f7c","sha256:b19f3f8b32dd148187646049779f55b59851b8d27b079da54e51014614875588"],"state_sha256":"67391487cba620715c1def703c3523d4cdd7f944014a71abac43f21e554eedae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Zbq7lnxhw4P4iRQhhqL3jSlFvb/SgQ50gq1whdX4NjhXW6c3yv0YkcQ2S0El+OaWsjzINuSqbPd2F5r2WXaAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T11:59:13.723396Z","bundle_sha256":"71d543b1d29bc5fceb3fe6ed4f9fe04fc94f812af215dc43cb9309c3d2d45fd7"}}