{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EEVSKW7K5DAKJCLAU4LT5VLGR6","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":"1a02b0b9efb4542c1fda9c9390c92db534429f3c1749ac1e9763f8a2901007d6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T12:32:13Z","title_canon_sha256":"43e9cfdc4cb18c587cc96f5cb8261b005e2b709b20ddc1e704057153b2e426f6"},"schema_version":"1.0","source":{"id":"2608.13167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.13167","created_at":"2026-08-14T01:00:31Z"},{"alias_kind":"arxiv_version","alias_value":"2608.13167v1","created_at":"2026-08-14T01:00:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13167","created_at":"2026-08-14T01:00:31Z"},{"alias_kind":"pith_short_12","alias_value":"EEVSKW7K5DAK","created_at":"2026-08-14T01:00:31Z"},{"alias_kind":"pith_short_16","alias_value":"EEVSKW7K5DAKJCLA","created_at":"2026-08-14T01:00:31Z"},{"alias_kind":"pith_short_8","alias_value":"EEVSKW7K","created_at":"2026-08-14T01:00:31Z"}],"graph_snapshots":[{"event_id":"sha256:fb7f0ac869437f93e5b8ba6bd25493d7a96bdd6ccf90391686df88e1566f6da9","target":"graph","created_at":"2026-08-14T01:00:31Z","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/2608.13167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distinguish when abstention is required, but fail to express it anyway. We introduce TRAPSBench, a procedurally generated video benchmark of 1,404 matched physics pairs in which a single targeted change renders the outcome undeterminable from the visual evidence. Furthermore, we introduce Penalized Epistemic Calibration Score (PECS), a new robust metric that requires models to both answer correctly when the outcome is knowable, and abstain when the outcom","authors_text":"Fnu Pramono, John Cai, Sourabh Kulkarni","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T12:32:13Z","title":"TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13167","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":"sha256:7e6ffcfa4a260df2141f6affdfc6496ad1cc32535c43efd886c4aa5d21feed16","target":"record","created_at":"2026-08-14T01:00:31Z","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":"1a02b0b9efb4542c1fda9c9390c92db534429f3c1749ac1e9763f8a2901007d6","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T12:32:13Z","title_canon_sha256":"43e9cfdc4cb18c587cc96f5cb8261b005e2b709b20ddc1e704057153b2e426f6"},"schema_version":"1.0","source":{"id":"2608.13167","kind":"arxiv","version":1}},"canonical_sha256":"212b255beae8c0a48960a7173ed5668fab6347799943cd33c5bdbc160c41d8e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"212b255beae8c0a48960a7173ed5668fab6347799943cd33c5bdbc160c41d8e4","first_computed_at":"2026-08-14T01:00:31.940324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T01:00:31.940324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mzzasCR6VzHUbb1j/BoGjB6eeT7lWCBoTYsG79fBDQIeFlXhuR0kex1smbElbT6i52Se5NGfb/z6b80+rJ+mDg==","signature_status":"signed_v1","signed_at":"2026-08-14T01:00:31.942248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.13167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e6ffcfa4a260df2141f6affdfc6496ad1cc32535c43efd886c4aa5d21feed16","sha256:fb7f0ac869437f93e5b8ba6bd25493d7a96bdd6ccf90391686df88e1566f6da9"],"state_sha256":"bde2ee72a906c08f80ae9c3f19688d4ac9a6a37a13a55b21dd4087797f605244"}