{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GTA3IY6NGW5TLSLLI24ZGTBL7P","short_pith_number":"pith:GTA3IY6N","canonical_record":{"source":{"id":"2606.08394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T01:11:36Z","cross_cats_sorted":[],"title_canon_sha256":"7cdda5abb0ac50a56bf50fb80e380f63349ab186ba186b95e7c5e1944cbb32f4","abstract_canon_sha256":"4226f9db8b8799cea896fabb6e7fa1a3d2d97448e04d397b61f39e8b8edc70ad"},"schema_version":"1.0"},"canonical_sha256":"34c1b463cd35bb35c96b46b9934c2bfbd74d97ee571176deefb242b32004774d","source":{"kind":"arxiv","id":"2606.08394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08394","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08394v1","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08394","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"GTA3IY6NGW5T","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"GTA3IY6NGW5TLSLL","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"GTA3IY6N","created_at":"2026-06-09T01:05:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GTA3IY6NGW5TLSLLI24ZGTBL7P","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T01:11:36Z","cross_cats_sorted":[],"title_canon_sha256":"7cdda5abb0ac50a56bf50fb80e380f63349ab186ba186b95e7c5e1944cbb32f4","abstract_canon_sha256":"4226f9db8b8799cea896fabb6e7fa1a3d2d97448e04d397b61f39e8b8edc70ad"},"schema_version":"1.0"},"canonical_sha256":"34c1b463cd35bb35c96b46b9934c2bfbd74d97ee571176deefb242b32004774d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:35.540047Z","signature_b64":"MrAGZCbt24DDQy/turJmiKkt2murR2XlykCKfzLt6VQCpgEa9oyjlQ0fKxnCk27hQEn8cPXiJA1YvoXKTORaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34c1b463cd35bb35c96b46b9934c2bfbd74d97ee571176deefb242b32004774d","last_reissued_at":"2026-06-09T01:05:35.539650Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:35.539650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08394","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":"2026-06-09T01:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0iKSPuVLCX6z12RvKZdZdCRiO2CtMRznI1txi5sLX53o6X7VpOjsTss65eKd3vyS/Occ3QnIedr6BvEVyAUuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T09:40:48.232041Z"},"content_sha256":"00668b6e89237e6163b19d6fec0e53ad48637eec13b15e6c700f451f230a432a","schema_version":"1.0","event_id":"sha256:00668b6e89237e6163b19d6fec0e53ad48637eec13b15e6c700f451f230a432a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GTA3IY6NGW5TLSLLI24ZGTBL7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eduard Hovy, Haoran Zhao, Soyeon Caren Han","submitted_at":"2026-06-07T01:11:36Z","abstract_excerpt":"Multimodal language models are typically evaluated through external behavior: selecting the correct image--text match, rejecting unsupported captions, or answering visual queries correctly. However, correct behavior alone does not show that the model's internal decision state remains stable under controlled semantic stress. We study this gap through S$^3$E (Structured Semantic Stress Evaluation), a framework for analyzing behavior-internal decoupling in multimodal language models. S$^3$E uses a positive-anchored A/B forced-choice setup in which an image-supported caption is contrasted against "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08394","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/2606.08394/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":"2026-06-09T01:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ffk/238GWjPZ8PaNc+zsx+lh8qlfKJ1c4OezT2qhskv+aj/0hRn913UhmxKprRf8NAebOaafjQyP9FTd4hfyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T09:40:48.232428Z"},"content_sha256":"160e04beb9e20fc710c92807667a62a9c20e6ff2fb8f6e7dc36dd2a8ffb599f2","schema_version":"1.0","event_id":"sha256:160e04beb9e20fc710c92807667a62a9c20e6ff2fb8f6e7dc36dd2a8ffb599f2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P/bundle.json","state_url":"https://pith.science/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P/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":"2026-06-29T09:40:48Z","links":{"resolver":"https://pith.science/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P","bundle":"https://pith.science/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P/bundle.json","state":"https://pith.science/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GTA3IY6NGW5TLSLLI24ZGTBL7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GTA3IY6NGW5TLSLLI24ZGTBL7P","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":"4226f9db8b8799cea896fabb6e7fa1a3d2d97448e04d397b61f39e8b8edc70ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T01:11:36Z","title_canon_sha256":"7cdda5abb0ac50a56bf50fb80e380f63349ab186ba186b95e7c5e1944cbb32f4"},"schema_version":"1.0","source":{"id":"2606.08394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08394","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08394v1","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08394","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"GTA3IY6NGW5T","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"GTA3IY6NGW5TLSLL","created_at":"2026-06-09T01:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"GTA3IY6N","created_at":"2026-06-09T01:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:160e04beb9e20fc710c92807667a62a9c20e6ff2fb8f6e7dc36dd2a8ffb599f2","target":"graph","created_at":"2026-06-09T01:05:35Z","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/2606.08394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal language models are typically evaluated through external behavior: selecting the correct image--text match, rejecting unsupported captions, or answering visual queries correctly. However, correct behavior alone does not show that the model's internal decision state remains stable under controlled semantic stress. We study this gap through S$^3$E (Structured Semantic Stress Evaluation), a framework for analyzing behavior-internal decoupling in multimodal language models. S$^3$E uses a positive-anchored A/B forced-choice setup in which an image-supported caption is contrasted against ","authors_text":"Eduard Hovy, Haoran Zhao, Soyeon Caren Han","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T01:11:36Z","title":"When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08394","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":"sha256:00668b6e89237e6163b19d6fec0e53ad48637eec13b15e6c700f451f230a432a","target":"record","created_at":"2026-06-09T01:05:35Z","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":"4226f9db8b8799cea896fabb6e7fa1a3d2d97448e04d397b61f39e8b8edc70ad","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T01:11:36Z","title_canon_sha256":"7cdda5abb0ac50a56bf50fb80e380f63349ab186ba186b95e7c5e1944cbb32f4"},"schema_version":"1.0","source":{"id":"2606.08394","kind":"arxiv","version":1}},"canonical_sha256":"34c1b463cd35bb35c96b46b9934c2bfbd74d97ee571176deefb242b32004774d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34c1b463cd35bb35c96b46b9934c2bfbd74d97ee571176deefb242b32004774d","first_computed_at":"2026-06-09T01:05:35.539650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:35.539650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MrAGZCbt24DDQy/turJmiKkt2murR2XlykCKfzLt6VQCpgEa9oyjlQ0fKxnCk27hQEn8cPXiJA1YvoXKTORaDg==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:35.540047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00668b6e89237e6163b19d6fec0e53ad48637eec13b15e6c700f451f230a432a","sha256:160e04beb9e20fc710c92807667a62a9c20e6ff2fb8f6e7dc36dd2a8ffb599f2"],"state_sha256":"4d4b15ef239c5a45f6446cb408fca82ac7fd7f391cec6f01c683c227de6b85bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nN9J9vp4jZV+4Ud+NicbT3tnyFjm+XbKLb6dkhFrvpwzump4o3ZeyhRgrnuB9qYxumKgF83rgBQi6L9Am2toDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T09:40:48.234285Z","bundle_sha256":"c0f715e469fefb74768a0a75c5de3875d8bc94951d921dfc7fe779b40b74ce5a"}}