{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GLKGAV5X7GZ6UH2YYO37LRJV2K","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3a48833869f746eaac78a46ed321385724be23d5f93032fea15757fc92230924","cross_cats_sorted":["cs.CL","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T07:49:02Z","title_canon_sha256":"a128506afe8c73951c8e331fd6c453891df8ef56af1a64c089f3bee35fb2b36f"},"schema_version":"1.0","source":{"id":"2604.22851","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.22851","created_at":"2026-07-08T01:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"2604.22851v2","created_at":"2026-07-08T01:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.22851","created_at":"2026-07-08T01:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"GLKGAV5X7GZ6","created_at":"2026-07-08T01:19:13Z"},{"alias_kind":"pith_short_16","alias_value":"GLKGAV5X7GZ6UH2Y","created_at":"2026-07-08T01:19:13Z"},{"alias_kind":"pith_short_8","alias_value":"GLKGAV5X","created_at":"2026-07-08T01:19:13Z"}],"graph_snapshots":[{"event_id":"sha256:af05f831f4161c2ac3c22fbe986b97489cfd04b3a7e9ef102b9fda158e669fa2","target":"graph","created_at":"2026-07-08T01:19:13Z","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":"This failure persists across model scales and domain-specific training, indicating a structural deficit in how current architectures couple visual perception with physical reasoning. We demonstrate that providing explicit trajectory encodings substantially restores physical consistency across all evaluated models, revealing a functional disentanglement between vision and language: egomotion logic is derived almost exclusively from the language modality, while visual observations contribute negligible additional signal."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The deterministic oracle accurately and unbiasedly maps continuous vehicle kinematics to discrete motion concepts, and the benchmark tasks isolate perception from other model capabilities without introducing confounding factors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vision-centric foundation models fail to align physical ego-motion concepts with visual observations in autonomous driving."}],"snapshot_sha256":"57a800bd2a72b8ac5441a1571d74d9d318f7dd39ec2d5620f2f1e5fbaae6cd0e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":false,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T14:43:42.791562Z","status":"completed","version":"1.0.0"},{"findings_count":1,"name":"doi_compliance","ran_at":"2026-05-20T02:06:04.415398Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.22851/integrity.json","findings":[{"audited_at":"2026-05-20T02:06:04.415398Z","detected_arxiv_id":null,"detected_doi":"10.1016/0004-3702(81","detector":"doi_compliance","finding_type":"recoverable_identifier","note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1016/0004-3702(81) was visible in the surrounding text but could not be confirmed against doi.org as printed.","ref_index":12,"severity":"advisory","verdict_class":"incontrovertible"}],"snapshot_sha256":"c1905117ebb7fa685ab0136bde82614a3ebc595b9a699c054246fb4f5caf059d","summary":{"advisory":1,"by_detector":{"doi_compliance":{"advisory":1,"critical":0,"informational":0,"total":1}},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Vision-Language Models (VLMs) have advanced high-level reasoning in autonomous driving, their ability to ground this reasoning in the underlying physics of ego-motion remains poorly understood. We introduce EgoDyn-Bench [Project page: (https://tum-avs.github.io/EgoDyn-Bench-Website/), Code: (https://github.com/TUM-AVS/EgoDyn-Bench), Dataset: (https://huggingface.co/datasets/fnc1901/EgoDyn-Bench)], a diagnostic benchmark for evaluating the semantic ego-motion understanding of vision-centric foundation models. By mapping continuous vehicle kinematics to discrete motion concepts via a deter","authors_text":"Dingrui Wang, Finn Rasmus Sch\\\"afer, Johannes Betz, Mattia Piccinini, Sebastian Schmidt, Stephan G\\\"unnemann, Thomas Stauner, Yuan Gao","cross_cats":["cs.CL","cs.RO"],"headline":"Vision-centric foundation models fail to align physical ego-motion concepts with visual observations in autonomous driving.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T07:49:02Z","title":"EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.22851","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T00:06:08.396622Z","id":"96daf71d-32f3-4fc8-b5c4-37c76086a788","model_set":{"reader":"grok-4.3"},"one_line_summary":"EgoDyn-Bench reveals a perception bottleneck in vision-centric foundation models: ego-motion logic derives from language while visual input adds negligible signal, with explicit trajectories restoring consistency.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Vision-centric foundation models fail to align physical ego-motion concepts with visual observations in autonomous driving.","strongest_claim":"This failure persists across model scales and domain-specific training, indicating a structural deficit in how current architectures couple visual perception with physical reasoning. We demonstrate that providing explicit trajectory encodings substantially restores physical consistency across all evaluated models, revealing a functional disentanglement between vision and language: egomotion logic is derived almost exclusively from the language modality, while visual observations contribute negligible additional signal.","weakest_assumption":"The deterministic oracle accurately and unbiasedly maps continuous vehicle kinematics to discrete motion concepts, and the benchmark tasks isolate perception from other model capabilities without introducing confounding factors."}},"verdict_id":"96daf71d-32f3-4fc8-b5c4-37c76086a788"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4a4f8fee20848c4b6f3b5c2720f8cf2c0fcc7eeef956146ed048856cf5e1d6f9","target":"record","created_at":"2026-07-08T01:19:13Z","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":"3a48833869f746eaac78a46ed321385724be23d5f93032fea15757fc92230924","cross_cats_sorted":["cs.CL","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-22T07:49:02Z","title_canon_sha256":"a128506afe8c73951c8e331fd6c453891df8ef56af1a64c089f3bee35fb2b36f"},"schema_version":"1.0","source":{"id":"2604.22851","kind":"arxiv","version":2}},"canonical_sha256":"32d46057b7f9b3ea1f58c3b7f5c535d29bd03f025b0062d741117e1c65a4537d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32d46057b7f9b3ea1f58c3b7f5c535d29bd03f025b0062d741117e1c65a4537d","first_computed_at":"2026-07-08T01:19:13.427070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:19:13.427070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ncI6RqE3PJE2LIgac1ke+Hv1cJFxObbkDtweDdLuk3cIp3IjNSQifmwxt4n36XxV5IcfMp5+5kL8uiUikeTWBA==","signature_status":"signed_v1","signed_at":"2026-07-08T01:19:13.427749Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.22851","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecfbab9590b349b31751c712ec3084e91971c0ae8bc5612633308eca9d3824cb","sha256:4a4f8fee20848c4b6f3b5c2720f8cf2c0fcc7eeef956146ed048856cf5e1d6f9","sha256:af05f831f4161c2ac3c22fbe986b97489cfd04b3a7e9ef102b9fda158e669fa2"],"state_sha256":"6a7b1394aaaba7b7cfacd64b0abf653d382ad213a33cb020a15e5f59c9b4dab9"}