{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PSK6OG2EYJ5HE5T4XM56G6X4UE","short_pith_number":"pith:PSK6OG2E","canonical_record":{"source":{"id":"2606.04233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T21:33:28Z","cross_cats_sorted":[],"title_canon_sha256":"0cedb4665219e8d6df0bc137e8e668b10bb64c22456b542dffcf34bef57c8977","abstract_canon_sha256":"8b6b85ea38a73fe2bdc2dcd25f9ddfdff49c3e3e1d32c636706635cfeaeada7a"},"schema_version":"1.0"},"canonical_sha256":"7c95e71b44c27a72767cbb3be37afca125f9c06fce866966bdad02e5681b6a70","source":{"kind":"arxiv","id":"2606.04233","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04233","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04233v1","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04233","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"PSK6OG2EYJ5H","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"PSK6OG2EYJ5HE5T4","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"PSK6OG2E","created_at":"2026-06-04T01:08:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PSK6OG2EYJ5HE5T4XM56G6X4UE","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04233","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T21:33:28Z","cross_cats_sorted":[],"title_canon_sha256":"0cedb4665219e8d6df0bc137e8e668b10bb64c22456b542dffcf34bef57c8977","abstract_canon_sha256":"8b6b85ea38a73fe2bdc2dcd25f9ddfdff49c3e3e1d32c636706635cfeaeada7a"},"schema_version":"1.0"},"canonical_sha256":"7c95e71b44c27a72767cbb3be37afca125f9c06fce866966bdad02e5681b6a70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:59.572388Z","signature_b64":"3qu77hZp5UEYCaUVKP7PcAu9PMygWlDHSr6rdqsMYR70v72X+Bhr4HXrIQFYLKusR9pJ9V3OYNh7Ty72iWY4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c95e71b44c27a72767cbb3be37afca125f9c06fce866966bdad02e5681b6a70","last_reissued_at":"2026-06-04T01:08:59.571899Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:59.571899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04233","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":"2026-06-04T01:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XcCLpJuQsgWsqFz3wX9w3NOH51GihkWAd1Bn4w4sq6fXZsKsmurqnY8JwYDgTkgfG6CohJ3LH9VhZN0og4DoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T00:10:30.672920Z"},"content_sha256":"4ae6fdcb7602467ff32628b73109c4edd0075484169a14c3e54fdbc6fec6b281","schema_version":"1.0","event_id":"sha256:4ae6fdcb7602467ff32628b73109c4edd0075484169a14c3e54fdbc6fec6b281"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PSK6OG2EYJ5HE5T4XM56G6X4UE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Are We Actually Benchmarking in Robot Manipulation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Luzhe Sun, Matthew Walter, Samuel Wheeler, Tewodros W. Ayalew, Tianchong Jiang, Xiangshan Tan","submitted_at":"2026-06-02T21:33:28Z","abstract_excerpt":"A robotics benchmark score measures success under one fixed evaluation setup, yet is routinely treated as evidence of general manipulation capability. We identify four failure modes, each of which weakens or invalidates a benchmark's role as a valid proxy for that capability: shortcut solvability, lack of statistical significance, creeping overfitting, and data-source dependence. We propose one diagnostic per failure mode. We audit LIBERO, CALVIN, SimplerEnv, RoboCasa, and RoboTwin 2.0 under these diagnostics. LIBERO and CALVIN fail multiple diagnostics. RoboCasa and RoboTwin 2.0 fail fewer, d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04233","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04233/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZzrrhJsF7Mlt2TjhQ0L27MaMB3OJgC550Au6tkGZFXKhPdu7lifi5DiBB8+2vW/KwjJB4/gwBeEMUuYWfivfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T00:10:30.673301Z"},"content_sha256":"b9002f8078627b49b28bb4f33491d40f21441cabdb98814646cd1c03d6de2b59","schema_version":"1.0","event_id":"sha256:b9002f8078627b49b28bb4f33491d40f21441cabdb98814646cd1c03d6de2b59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE/bundle.json","state_url":"https://pith.science/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE/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":"2026-06-26T00:10:30Z","links":{"resolver":"https://pith.science/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE","bundle":"https://pith.science/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE/bundle.json","state":"https://pith.science/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PSK6OG2EYJ5HE5T4XM56G6X4UE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PSK6OG2EYJ5HE5T4XM56G6X4UE","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":"8b6b85ea38a73fe2bdc2dcd25f9ddfdff49c3e3e1d32c636706635cfeaeada7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T21:33:28Z","title_canon_sha256":"0cedb4665219e8d6df0bc137e8e668b10bb64c22456b542dffcf34bef57c8977"},"schema_version":"1.0","source":{"id":"2606.04233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04233","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04233v1","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04233","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"PSK6OG2EYJ5H","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"PSK6OG2EYJ5HE5T4","created_at":"2026-06-04T01:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"PSK6OG2E","created_at":"2026-06-04T01:08:59Z"}],"graph_snapshots":[{"event_id":"sha256:b9002f8078627b49b28bb4f33491d40f21441cabdb98814646cd1c03d6de2b59","target":"graph","created_at":"2026-06-04T01:08:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.04233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A robotics benchmark score measures success under one fixed evaluation setup, yet is routinely treated as evidence of general manipulation capability. We identify four failure modes, each of which weakens or invalidates a benchmark's role as a valid proxy for that capability: shortcut solvability, lack of statistical significance, creeping overfitting, and data-source dependence. We propose one diagnostic per failure mode. We audit LIBERO, CALVIN, SimplerEnv, RoboCasa, and RoboTwin 2.0 under these diagnostics. LIBERO and CALVIN fail multiple diagnostics. RoboCasa and RoboTwin 2.0 fail fewer, d","authors_text":"Luzhe Sun, Matthew Walter, Samuel Wheeler, Tewodros W. Ayalew, Tianchong Jiang, Xiangshan Tan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T21:33:28Z","title":"What Are We Actually Benchmarking in Robot Manipulation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04233","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ae6fdcb7602467ff32628b73109c4edd0075484169a14c3e54fdbc6fec6b281","target":"record","created_at":"2026-06-04T01:08:59Z","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":"8b6b85ea38a73fe2bdc2dcd25f9ddfdff49c3e3e1d32c636706635cfeaeada7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-02T21:33:28Z","title_canon_sha256":"0cedb4665219e8d6df0bc137e8e668b10bb64c22456b542dffcf34bef57c8977"},"schema_version":"1.0","source":{"id":"2606.04233","kind":"arxiv","version":1}},"canonical_sha256":"7c95e71b44c27a72767cbb3be37afca125f9c06fce866966bdad02e5681b6a70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c95e71b44c27a72767cbb3be37afca125f9c06fce866966bdad02e5681b6a70","first_computed_at":"2026-06-04T01:08:59.571899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:59.571899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3qu77hZp5UEYCaUVKP7PcAu9PMygWlDHSr6rdqsMYR70v72X+Bhr4HXrIQFYLKusR9pJ9V3OYNh7Ty72iWY4Cw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:59.572388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ae6fdcb7602467ff32628b73109c4edd0075484169a14c3e54fdbc6fec6b281","sha256:b9002f8078627b49b28bb4f33491d40f21441cabdb98814646cd1c03d6de2b59"],"state_sha256":"46bd68789c950d468b5e4af09b08523359b0312dc71c48f3109e7673b308340e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFdNM8RyGHcfjPP30jqYMWeLV0b7QNnXysLOrZhZklUSLbuxD5PEfGhay4E6zGXOV+6uPIIwzolU9PPe2IkTDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T00:10:30.675355Z","bundle_sha256":"b88d9a94be5e1004e047f1619ac953f9e7226650ba4b5dea67bcc2f35340bcb7"}}