{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:53FO7AAM5J25EWKGM64HG34GY6","short_pith_number":"pith:53FO7AAM","canonical_record":{"source":{"id":"2605.15517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-15T01:27:50Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"243d8faf633db281828af59cf50f17c0ee5f6db5101d76db652382d4caeab95b","abstract_canon_sha256":"468d0d55f9777f70fb99bb5f892b82dbacd714ee7c0dd0ed642f35c556ff013c"},"schema_version":"1.0"},"canonical_sha256":"eecaef800cea75d2594667b8736f86c79ac8c73644b3f8f191df60b64f3de227","source":{"kind":"arxiv","id":"2605.15517","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15517","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15517v1","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15517","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"53FO7AAM5J25","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"53FO7AAM5J25EWKG","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"53FO7AAM","created_at":"2026-05-20T00:01:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:53FO7AAM5J25EWKGM64HG34GY6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-15T01:27:50Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"243d8faf633db281828af59cf50f17c0ee5f6db5101d76db652382d4caeab95b","abstract_canon_sha256":"468d0d55f9777f70fb99bb5f892b82dbacd714ee7c0dd0ed642f35c556ff013c"},"schema_version":"1.0"},"canonical_sha256":"eecaef800cea75d2594667b8736f86c79ac8c73644b3f8f191df60b64f3de227","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:02.744337Z","signature_b64":"RKuVyK5va5lXrfMJcroAwNzwqgRfRpBrNhnlfjPLH+fcOu7CBnEYVmNt1yrznlDSLvtmBmIZZ6OYCUW2QO1BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eecaef800cea75d2594667b8736f86c79ac8c73644b3f8f191df60b64f3de227","last_reissued_at":"2026-05-20T00:01:02.743486Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:02.743486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15517","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":"2026-05-20T00:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n1MarhmHYoNYhAIY4kV1WmakV9Ku+sPsmokNpls10nIvU6KWVUF+VxhxU7qF+8w4+G8amz7JikMm0SDQdA+6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T14:15:10.824832Z"},"content_sha256":"2f1339494e46e65eae2c1f155000d86be28ba162b915a2d5e0cb44eec09ff95a","schema_version":"1.0","event_id":"sha256:2f1339494e46e65eae2c1f155000d86be28ba162b915a2d5e0cb44eec09ff95a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:53FO7AAM5J25EWKGM64HG34GY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Modulating reference trajectories to fit terrain geometry inside RL training produces humanoid policies that track SE(2) velocity commands reliably on rough outdoor ground and stairs.","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Aaron D. Ames, William D. Compton, Zachary Olkin","submitted_at":"2026-05-15T01:27:50Z","abstract_excerpt":"We present a method for training reference-guided, perceptive reinforcement learning locomotion policies for humanoid robots in which reference trajectories are modulated in training to be consistent with terrain geometry. Aiming to deploy our method with standard navigation autonomy infrastructure, we synthesize SE(2)-controllable reference trajectories inside the RL training loop, projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain. The resulting policy exposes a clean SE(2) velocity interface compatible with standar"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Environmentally-conditioned references significantly improve reference tracking performance compared to environment agnostic references. On hardware, we integrate the policy with an MPC + control barrier function planner and demonstrate long-horizon (>70m) closed-loop autonomous navigation on the Unitree G1 through outdoor environments containing rough terrain and consecutive flights of stairs, with all sensing and computation onboard.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain inside the RL training loop produces stable, generalizable training signals that transfer to real hardware without introducing artifacts, instability, or poor reference tracking on unseen terrain geometries.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Modulating reference trajectories to fit terrain geometry inside RL training produces humanoid policies that track SE(2) velocity commands reliably on rough outdoor ground and stairs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a112348fdb95ecad076eacca590f328aecc665a1fcb66e9d7d8299af38119770"},"source":{"id":"2605.15517","kind":"arxiv","version":1},"verdict":{"id":"f05900c8-7189-440f-bf7b-c5a77b467e3f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:18:39.611045Z","strongest_claim":"Environmentally-conditioned references significantly improve reference tracking performance compared to environment agnostic references. On hardware, we integrate the policy with an MPC + control barrier function planner and demonstrate long-horizon (>70m) closed-loop autonomous navigation on the Unitree G1 through outdoor environments containing rough terrain and consecutive flights of stairs, with all sensing and computation onboard.","one_line_summary":"Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain inside the RL training loop produces stable, generalizable training signals that transfer to real hardware without introducing artifacts, instability, or poor reference tracking on unseen terrain geometries.","pith_extraction_headline":"Modulating reference trajectories to fit terrain geometry inside RL training produces humanoid policies that track SE(2) velocity commands reliably on rough outdoor ground and stairs."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15517/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.708504Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:30:34.893772Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T14:22:03.552000Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.050234Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.845019Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.383770Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.630970Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9b4c4e860a2605ad5f1765d10609f6e47ba3ec56d5c5d5dc6cfc2386e95fa0d1"},"references":{"count":37,"sample":[{"doi":"","year":2024,"title":"Dtc: Deep tracking control,","work_id":"c081076b-cd08-4908-943e-0640b0529002","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Beamdojo: Learning agile humanoid locomotion on sparse footholds","work_id":"945a1504-fdc0-4912-ac06-c76e73d29c9d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Benet al.Gallant: V oxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains","work_id":"5b87b8bc-381d-448f-9fa3-987b870f05b6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Learning humanoid locomotion with perceptive internal model,","work_id":"347fe515-b7cf-41d4-9601-7ef0b609cc14","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Attention-based map encoding for learning generalized legged loco- motion","work_id":"305584c6-675c-4025-9f6f-f507b6ee57b3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"ebae83a05d434a4a9c0af792af75ac8c58ceec42ee44d4c0a0cd0f450a9cb0aa","internal_anchors":3},"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":"f05900c8-7189-440f-bf7b-c5a77b467e3f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/kEw27ExPA/cx+iBUhH/DGaX+d1X9WvIjjr4yF+h09Tc+25bpf8+o+OAU+yumAA3l2KO9D2F7Uz9RxtzQCesDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T14:15:10.826373Z"},"content_sha256":"2c4b615fa6c7ac55bf3c6f1a282463154db2a431d070bb934da720fa02886fc9","schema_version":"1.0","event_id":"sha256:2c4b615fa6c7ac55bf3c6f1a282463154db2a431d070bb934da720fa02886fc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/53FO7AAM5J25EWKGM64HG34GY6/bundle.json","state_url":"https://pith.science/pith/53FO7AAM5J25EWKGM64HG34GY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/53FO7AAM5J25EWKGM64HG34GY6/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":"2026-05-24T14:15:10Z","links":{"resolver":"https://pith.science/pith/53FO7AAM5J25EWKGM64HG34GY6","bundle":"https://pith.science/pith/53FO7AAM5J25EWKGM64HG34GY6/bundle.json","state":"https://pith.science/pith/53FO7AAM5J25EWKGM64HG34GY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/53FO7AAM5J25EWKGM64HG34GY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:53FO7AAM5J25EWKGM64HG34GY6","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":"468d0d55f9777f70fb99bb5f892b82dbacd714ee7c0dd0ed642f35c556ff013c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-15T01:27:50Z","title_canon_sha256":"243d8faf633db281828af59cf50f17c0ee5f6db5101d76db652382d4caeab95b"},"schema_version":"1.0","source":{"id":"2605.15517","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15517","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15517v1","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15517","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"53FO7AAM5J25","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"53FO7AAM5J25EWKG","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"53FO7AAM","created_at":"2026-05-20T00:01:02Z"}],"graph_snapshots":[{"event_id":"sha256:2c4b615fa6c7ac55bf3c6f1a282463154db2a431d070bb934da720fa02886fc9","target":"graph","created_at":"2026-05-20T00:01:02Z","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":"Environmentally-conditioned references significantly improve reference tracking performance compared to environment agnostic references. On hardware, we integrate the policy with an MPC + control barrier function planner and demonstrate long-horizon (>70m) closed-loop autonomous navigation on the Unitree G1 through outdoor environments containing rough terrain and consecutive flights of stairs, with all sensing and computation onboard."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain inside the RL training loop produces stable, generalizable training signals that transfer to real hardware without introducing artifacts, instability, or poor reference tracking on unseen terrain geometries."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Modulating reference trajectories to fit terrain geometry inside RL training produces humanoid policies that track SE(2) velocity commands reliably on rough outdoor ground and stairs."}],"snapshot_sha256":"a112348fdb95ecad076eacca590f328aecc665a1fcb66e9d7d8299af38119770"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.708504Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:30:34.893772Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T14:22:03.552000Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.050234Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.845019Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.383770Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.630970Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15517/integrity.json","findings":[],"snapshot_sha256":"9b4c4e860a2605ad5f1765d10609f6e47ba3ec56d5c5d5dc6cfc2386e95fa0d1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a method for training reference-guided, perceptive reinforcement learning locomotion policies for humanoid robots in which reference trajectories are modulated in training to be consistent with terrain geometry. Aiming to deploy our method with standard navigation autonomy infrastructure, we synthesize SE(2)-controllable reference trajectories inside the RL training loop, projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain. The resulting policy exposes a clean SE(2) velocity interface compatible with standar","authors_text":"Aaron D. Ames, William D. Compton, Zachary Olkin","cross_cats":["cs.SY","eess.SY"],"headline":"Modulating reference trajectories to fit terrain geometry inside RL training produces humanoid policies that track SE(2) velocity commands reliably on rough outdoor ground and stairs.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-15T01:27:50Z","title":"Terrain Consistent Reference-Guided RL for Humanoid Navigation Autonomy"},"references":{"count":37,"internal_anchors":3,"resolved_work":37,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Dtc: Deep tracking control,","work_id":"c081076b-cd08-4908-943e-0640b0529002","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Beamdojo: Learning agile humanoid locomotion on sparse footholds","work_id":"945a1504-fdc0-4912-ac06-c76e73d29c9d","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Benet al.Gallant: V oxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains","work_id":"5b87b8bc-381d-448f-9fa3-987b870f05b6","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Learning humanoid locomotion with perceptive internal model,","work_id":"347fe515-b7cf-41d4-9601-7ef0b609cc14","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Attention-based map encoding for learning generalized legged loco- motion","work_id":"305584c6-675c-4025-9f6f-f507b6ee57b3","year":2025}],"snapshot_sha256":"ebae83a05d434a4a9c0af792af75ac8c58ceec42ee44d4c0a0cd0f450a9cb0aa"},"source":{"id":"2605.15517","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:18:39.611045Z","id":"f05900c8-7189-440f-bf7b-c5a77b467e3f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Terrain-consistent reference modulation during RL training yields SE(2)-controllable humanoid locomotion policies that improve tracking in simulation and enable over 70 m closed-loop autonomous navigation on rough terrain and stairs on the Unitree G1 with onboard computation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Modulating reference trajectories to fit terrain geometry inside RL training produces humanoid policies that track SE(2) velocity commands reliably on rough outdoor ground and stairs.","strongest_claim":"Environmentally-conditioned references significantly improve reference tracking performance compared to environment agnostic references. On hardware, we integrate the policy with an MPC + control barrier function planner and demonstrate long-horizon (>70m) closed-loop autonomous navigation on the Unitree G1 through outdoor environments containing rough terrain and consecutive flights of stairs, with all sensing and computation onboard.","weakest_assumption":"That projecting desired footsteps onto valid footholds and adjusting swing-foot and center-of-mass trajectories to match the terrain inside the RL training loop produces stable, generalizable training signals that transfer to real hardware without introducing artifacts, instability, or poor reference tracking on unseen terrain geometries."}},"verdict_id":"f05900c8-7189-440f-bf7b-c5a77b467e3f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f1339494e46e65eae2c1f155000d86be28ba162b915a2d5e0cb44eec09ff95a","target":"record","created_at":"2026-05-20T00:01:02Z","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":"468d0d55f9777f70fb99bb5f892b82dbacd714ee7c0dd0ed642f35c556ff013c","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-15T01:27:50Z","title_canon_sha256":"243d8faf633db281828af59cf50f17c0ee5f6db5101d76db652382d4caeab95b"},"schema_version":"1.0","source":{"id":"2605.15517","kind":"arxiv","version":1}},"canonical_sha256":"eecaef800cea75d2594667b8736f86c79ac8c73644b3f8f191df60b64f3de227","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eecaef800cea75d2594667b8736f86c79ac8c73644b3f8f191df60b64f3de227","first_computed_at":"2026-05-20T00:01:02.743486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:02.743486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RKuVyK5va5lXrfMJcroAwNzwqgRfRpBrNhnlfjPLH+fcOu7CBnEYVmNt1yrznlDSLvtmBmIZZ6OYCUW2QO1BBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:02.744337Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15517","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f1339494e46e65eae2c1f155000d86be28ba162b915a2d5e0cb44eec09ff95a","sha256:2c4b615fa6c7ac55bf3c6f1a282463154db2a431d070bb934da720fa02886fc9"],"state_sha256":"03dd24af9d2f181fe0d8102f3d267f2c6623f4bc32e5704d5f8f37722585dc2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P7FkKvtdEpXKgirPtgDlPTNcWDBAKrFl4DLlcliZ0yHZwZjN3lkcsKb2ZI/NC2y4j7hUn8/kEN+w5ztIi5UTAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T14:15:10.831088Z","bundle_sha256":"bf7c11153f3acf8b6d52eb0b1d920c62065c339c40e5ec873e1a434f7ccf4f28"}}