{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Q4DVLKYKSV6XYIMQMLNHEF4UBW","short_pith_number":"pith:Q4DVLKYK","canonical_record":{"source":{"id":"2605.16922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T10:28:54Z","cross_cats_sorted":[],"title_canon_sha256":"dc4b4fe4b49c711d0c59111fcf9bbb1a89dfdfa61965ae5c2e9913556d214552","abstract_canon_sha256":"118518e5927c9eacf5a1ec9848943c97d806aa9900cd566f899eb956a3fde008"},"schema_version":"1.0"},"canonical_sha256":"870755ab0a957d7c219062da7217940db2bc02e19a1333fbdb88c5b1bb0c810b","source":{"kind":"arxiv","id":"2605.16922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16922","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16922v1","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16922","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"Q4DVLKYKSV6X","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"Q4DVLKYKSV6XYIMQ","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"Q4DVLKYK","created_at":"2026-05-20T00:03:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Q4DVLKYKSV6XYIMQMLNHEF4UBW","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T10:28:54Z","cross_cats_sorted":[],"title_canon_sha256":"dc4b4fe4b49c711d0c59111fcf9bbb1a89dfdfa61965ae5c2e9913556d214552","abstract_canon_sha256":"118518e5927c9eacf5a1ec9848943c97d806aa9900cd566f899eb956a3fde008"},"schema_version":"1.0"},"canonical_sha256":"870755ab0a957d7c219062da7217940db2bc02e19a1333fbdb88c5b1bb0c810b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:30.636149Z","signature_b64":"4bl4ckY5ci9695657CbEx5iMvIOOEkgOV96NvfDj3AkarDXyh7QqqaKpG29DGrmwakHExPEZK0qV5C17I8pbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"870755ab0a957d7c219062da7217940db2bc02e19a1333fbdb88c5b1bb0c810b","last_reissued_at":"2026-05-20T00:03:30.634945Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:30.634945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16922","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":"2026-05-20T00:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6K17S+MoWH28s1O8MTqTVrWVEa+VdlwUMEUJVqUTRbDsWHXkDgXR9KM4ADfWuKbgVBB/lW5EMYOX0vOTTUBBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T01:30:08.611133Z"},"content_sha256":"718850b2e278fef1b561b6015181788b106d50ae026f800361845d415c58107e","schema_version":"1.0","event_id":"sha256:718850b2e278fef1b561b6015181788b106d50ae026f800361845d415c58107e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Q4DVLKYKSV6XYIMQMLNHEF4UBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Dense image trajectories from point tracking refine static-dynamic labels for LiDAR scene flow.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gyeongrok Oh, Hyung-gun Chi, Hyunju Ryu, Jonghyun Choi, Jong Wook Kim, Sangpil Kim, SeungHyeon Kim, Seungryong Kim, Youngdong Jang","submitted_at":"2026-05-16T10:28:54Z","abstract_excerpt":"LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate the imbalance between static and dynamic points, deriving targeted supervision. However, existing methods rely on sparse geometric observations for this classification, making them vulnerable to data sparsity and occlusions. The resulting noisy labels provide incorrect motion guidance and degrade scene flow learning. To address this, we introduce TrackCue, a tracking-guided framework for improving dynamic object repre"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"TrackCue produces more accurate static-dynamic classification and provides more reliable supervision for scene flow learning, as shown by significantly improved precision and F1 score of dynamic labels leading to performance gains.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That dense image-space trajectories from point tracking can be accurately associated with and lifted to corresponding LiDAR points without introducing new errors from calibration, viewpoint differences, or tracking failures in occluded regions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Dense image trajectories from point tracking refine static-dynamic labels for LiDAR scene flow.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cc0adb06d0bbd6b90a2c33297f9eee6e15f64ab49555745cfdd5e62de49f96ef"},"source":{"id":"2605.16922","kind":"arxiv","version":1},"verdict":{"id":"c2a1b229-8cf6-40e2-871f-ddd830dbec04","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T21:05:44.476754Z","strongest_claim":"TrackCue produces more accurate static-dynamic classification and provides more reliable supervision for scene flow learning, as shown by significantly improved precision and F1 score of dynamic labels leading to performance gains.","one_line_summary":"TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That dense image-space trajectories from point tracking can be accurately associated with and lifted to corresponding LiDAR points without introducing new errors from calibration, viewpoint differences, or tracking failures in occluded regions.","pith_extraction_headline":"Dense image trajectories from point tracking refine static-dynamic labels for LiDAR scene flow."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16922/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.138819Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T21:10:56.175411Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T20:22:27.057257Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.261038Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.341644Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"c83fe81d563c61015e9c386b9408e24ea7417cb4a4a24f1d874b6d697d75fb90"},"references":{"count":53,"sample":[{"doi":"","year":2021,"title":"Neural scene flow prior.Advances in Neural Information Processing Systems, 34:7838–7851, 2021","work_id":"083b4078-a288-4e67-9a43-01f7954fdb11","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Fast neural scene flow","work_id":"e2be1a56-280f-4dd3-8154-07ca1a7d5c1e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Uniflow: Towards zero-shot lidar scene flow for autonomous vehicles via cross-domain generalization, 2025","work_id":"de34a055-e71a-46ef-b933-be45ea091cec","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Deltaflow: An efficient multi-frame scene flow estimation method","work_id":"f42f0102-b3f5-4e46-afc6-bb02735589c9","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Neural eulerian scene flow fields","work_id":"d50c852a-c7a1-499b-ae77-4df2d1f60f4b","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":53,"snapshot_sha256":"797483aea64f930cbec65895f1d80262e5bdd7ab478d7d68e1879794183a1ec3","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3110d8980aa78b0f3deb7dc3118b2addc6c5d0c8dfd4af9e7ed275a777b95eea"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"c2a1b229-8cf6-40e2-871f-ddd830dbec04"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDGVlSSne92BGfNLJYpyA8HFYSRxwNPdLiu5nfOi8HPosQBcbx4baIr1xpbSSYU45qjTf3/nk0eDkNWfNEMdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T01:30:08.612421Z"},"content_sha256":"11a4226299875c982b981d42b74eb4197b1452e13331570c892aadf353ce01fa","schema_version":"1.0","event_id":"sha256:11a4226299875c982b981d42b74eb4197b1452e13331570c892aadf353ce01fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW/bundle.json","state_url":"https://pith.science/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW/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":"2026-05-23T01:30:08Z","links":{"resolver":"https://pith.science/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW","bundle":"https://pith.science/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW/bundle.json","state":"https://pith.science/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q4DVLKYKSV6XYIMQMLNHEF4UBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Q4DVLKYKSV6XYIMQMLNHEF4UBW","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":"118518e5927c9eacf5a1ec9848943c97d806aa9900cd566f899eb956a3fde008","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T10:28:54Z","title_canon_sha256":"dc4b4fe4b49c711d0c59111fcf9bbb1a89dfdfa61965ae5c2e9913556d214552"},"schema_version":"1.0","source":{"id":"2605.16922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16922","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16922v1","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16922","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"Q4DVLKYKSV6X","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"Q4DVLKYKSV6XYIMQ","created_at":"2026-05-20T00:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"Q4DVLKYK","created_at":"2026-05-20T00:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:11a4226299875c982b981d42b74eb4197b1452e13331570c892aadf353ce01fa","target":"graph","created_at":"2026-05-20T00:03:30Z","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":"TrackCue produces more accurate static-dynamic classification and provides more reliable supervision for scene flow learning, as shown by significantly improved precision and F1 score of dynamic labels leading to performance gains."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That dense image-space trajectories from point tracking can be accurately associated with and lifted to corresponding LiDAR points without introducing new errors from calibration, viewpoint differences, or tracking failures in occluded regions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Dense image trajectories from point tracking refine static-dynamic labels for LiDAR scene flow."}],"snapshot_sha256":"cc0adb06d0bbd6b90a2c33297f9eee6e15f64ab49555745cfdd5e62de49f96ef"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3110d8980aa78b0f3deb7dc3118b2addc6c5d0c8dfd4af9e7ed275a777b95eea"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T21:31:19.138819Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:10:56.175411Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T20:22:27.057257Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T18:41:56.261038Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.341644Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16922/integrity.json","findings":[],"snapshot_sha256":"c83fe81d563c61015e9c386b9408e24ea7417cb4a4a24f1d874b6d697d75fb90","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LiDAR scene flow estimation is essential for autonomous driving, as it provides 3D motion for each point. Self-supervised approaches use static-dynamic classification to mitigate the imbalance between static and dynamic points, deriving targeted supervision. However, existing methods rely on sparse geometric observations for this classification, making them vulnerable to data sparsity and occlusions. The resulting noisy labels provide incorrect motion guidance and degrade scene flow learning. To address this, we introduce TrackCue, a tracking-guided framework for improving dynamic object repre","authors_text":"Gyeongrok Oh, Hyung-gun Chi, Hyunju Ryu, Jonghyun Choi, Jong Wook Kim, Sangpil Kim, SeungHyeon Kim, Seungryong Kim, Youngdong Jang","cross_cats":[],"headline":"Dense image trajectories from point tracking refine static-dynamic labels for LiDAR scene flow.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T10:28:54Z","title":"Motion Cues from Image-based Point Tracking for LiDAR Scene Flow Estimation"},"references":{"count":53,"internal_anchors":0,"resolved_work":53,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Neural scene flow prior.Advances in Neural Information Processing Systems, 34:7838–7851, 2021","work_id":"083b4078-a288-4e67-9a43-01f7954fdb11","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Fast neural scene flow","work_id":"e2be1a56-280f-4dd3-8154-07ca1a7d5c1e","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Uniflow: Towards zero-shot lidar scene flow for autonomous vehicles via cross-domain generalization, 2025","work_id":"de34a055-e71a-46ef-b933-be45ea091cec","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Deltaflow: An efficient multi-frame scene flow estimation method","work_id":"f42f0102-b3f5-4e46-afc6-bb02735589c9","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Neural eulerian scene flow fields","work_id":"d50c852a-c7a1-499b-ae77-4df2d1f60f4b","year":2025}],"snapshot_sha256":"797483aea64f930cbec65895f1d80262e5bdd7ab478d7d68e1879794183a1ec3"},"source":{"id":"2605.16922","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T21:05:44.476754Z","id":"c2a1b229-8cf6-40e2-871f-ddd830dbec04","model_set":{"reader":"grok-4.3"},"one_line_summary":"TrackCue uses dense image-space trajectories from point tracking and ego-motion compensation to improve static-dynamic classification and supervision for LiDAR scene flow estimation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Dense image trajectories from point tracking refine static-dynamic labels for LiDAR scene flow.","strongest_claim":"TrackCue produces more accurate static-dynamic classification and provides more reliable supervision for scene flow learning, as shown by significantly improved precision and F1 score of dynamic labels leading to performance gains.","weakest_assumption":"That dense image-space trajectories from point tracking can be accurately associated with and lifted to corresponding LiDAR points without introducing new errors from calibration, viewpoint differences, or tracking failures in occluded regions."}},"verdict_id":"c2a1b229-8cf6-40e2-871f-ddd830dbec04"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:718850b2e278fef1b561b6015181788b106d50ae026f800361845d415c58107e","target":"record","created_at":"2026-05-20T00:03:30Z","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":"118518e5927c9eacf5a1ec9848943c97d806aa9900cd566f899eb956a3fde008","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-16T10:28:54Z","title_canon_sha256":"dc4b4fe4b49c711d0c59111fcf9bbb1a89dfdfa61965ae5c2e9913556d214552"},"schema_version":"1.0","source":{"id":"2605.16922","kind":"arxiv","version":1}},"canonical_sha256":"870755ab0a957d7c219062da7217940db2bc02e19a1333fbdb88c5b1bb0c810b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"870755ab0a957d7c219062da7217940db2bc02e19a1333fbdb88c5b1bb0c810b","first_computed_at":"2026-05-20T00:03:30.634945Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:30.634945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4bl4ckY5ci9695657CbEx5iMvIOOEkgOV96NvfDj3AkarDXyh7QqqaKpG29DGrmwakHExPEZK0qV5C17I8pbDw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:30.636149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:718850b2e278fef1b561b6015181788b106d50ae026f800361845d415c58107e","sha256:11a4226299875c982b981d42b74eb4197b1452e13331570c892aadf353ce01fa"],"state_sha256":"133d227b63097be3b8d3f8d300d61b335f42dd39c446b6b4aa1de3868f7f95f0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPl25lb09Em6v9sylRAkZyGP3y1D0ngjXWReUiEqf6D2qTZLQzpyb5zrbUKSjEfobxjVBqWcsq1McV7dv6wMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T01:30:08.618101Z","bundle_sha256":"a40bccd690f3d92e26c1fa30209995d6ced161b7f754cb818507fc352456ac76"}}