{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:HIN4TTLBHX6MZKPDJPPNRCWIPF","short_pith_number":"pith:HIN4TTLB","canonical_record":{"source":{"id":"2606.19965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T09:05:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3441c6445fc48166882afc7403cd9901168c99a65981c1c065b384a88a5ddd5","abstract_canon_sha256":"49eb4ecf5a30f4e9aa7d6c34209c6b37c81561a17a474bb92a0a6fd5e24aff0d"},"schema_version":"1.0"},"canonical_sha256":"3a1bc9cd613dfccca9e34bded88ac8794a843d0477fcdcc592f5d0c3dea870d3","source":{"kind":"arxiv","id":"2606.19965","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19965","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19965v1","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19965","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"HIN4TTLBHX6M","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_16","alias_value":"HIN4TTLBHX6MZKPD","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_8","alias_value":"HIN4TTLB","created_at":"2026-06-19T16:12:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:HIN4TTLBHX6MZKPDJPPNRCWIPF","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T09:05:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3441c6445fc48166882afc7403cd9901168c99a65981c1c065b384a88a5ddd5","abstract_canon_sha256":"49eb4ecf5a30f4e9aa7d6c34209c6b37c81561a17a474bb92a0a6fd5e24aff0d"},"schema_version":"1.0"},"canonical_sha256":"3a1bc9cd613dfccca9e34bded88ac8794a843d0477fcdcc592f5d0c3dea870d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:59.353770Z","signature_b64":"Y6vQLjDcxQqYJp7EMtVBmudlrUd0LuAvsabHElDFQ1HkEB0vzD+RnYX6418EPG9D+aiBza2Uf1q2HKDdlCAPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a1bc9cd613dfccca9e34bded88ac8794a843d0477fcdcc592f5d0c3dea870d3","last_reissued_at":"2026-06-19T16:12:59.353400Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:59.353400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19965","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":"2026-06-19T16:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mrxrPWUXc/L5FI/M1ABBrOg9lBhOIRYCfYL1qIb6i5p5JQ4ajQjigjjo9gwjWA6FI90nsp2XaLuPLCo+Q8nzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T20:53:00.658355Z"},"content_sha256":"894f70ef8b6eb72f812d50304b47ef38edd872df7d6d57f0c83c21dde9067fe2","schema_version":"1.0","event_id":"sha256:894f70ef8b6eb72f812d50304b47ef38edd872df7d6d57f0c83c21dde9067fe2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:HIN4TTLBHX6MZKPDJPPNRCWIPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jie Ren, Keze Wang, Yihao Wang, Zijian He","submitted_at":"2026-06-18T09:05:48Z","abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly expected to act on visual information, yet the same scene may require different actions under different task contexts. How reliably can a model turn the same visual evidence into the action required by the current context? To answer this question, we introduce \\textsc{ROSE} (\\textbf{R}eference-conditioned \\textbf{O}ddity and \\textbf{S}ymbolic \\textbf{E}xecution), a controlled benchmark that holds the visual scene fixed while varying region constraints and required symbolic outputs. Through coupled counting and coordinate-action tasks, \\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19965","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/2606.19965/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":"2026-06-19T16:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+J6mFACKPaYnFHEfAcPPdFxVMiVq8gxrLP4yASeuekKpvigdA3lGyYqIyneNbGsjk9Ulkl7RFxCtZrb/24GiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T20:53:00.658754Z"},"content_sha256":"5616a2c147864a61e76e2a2dc015f4940de072d73b2e3170f79ffbc7ac40e78e","schema_version":"1.0","event_id":"sha256:5616a2c147864a61e76e2a2dc015f4940de072d73b2e3170f79ffbc7ac40e78e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF/bundle.json","state_url":"https://pith.science/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF/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":"2026-07-02T20:53:00Z","links":{"resolver":"https://pith.science/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF","bundle":"https://pith.science/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF/bundle.json","state":"https://pith.science/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HIN4TTLBHX6MZKPDJPPNRCWIPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HIN4TTLBHX6MZKPDJPPNRCWIPF","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":"49eb4ecf5a30f4e9aa7d6c34209c6b37c81561a17a474bb92a0a6fd5e24aff0d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T09:05:48Z","title_canon_sha256":"a3441c6445fc48166882afc7403cd9901168c99a65981c1c065b384a88a5ddd5"},"schema_version":"1.0","source":{"id":"2606.19965","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19965","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19965v1","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19965","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"HIN4TTLBHX6M","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_16","alias_value":"HIN4TTLBHX6MZKPD","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_8","alias_value":"HIN4TTLB","created_at":"2026-06-19T16:12:59Z"}],"graph_snapshots":[{"event_id":"sha256:5616a2c147864a61e76e2a2dc015f4940de072d73b2e3170f79ffbc7ac40e78e","target":"graph","created_at":"2026-06-19T16:12:59Z","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/2606.19965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) are increasingly expected to act on visual information, yet the same scene may require different actions under different task contexts. How reliably can a model turn the same visual evidence into the action required by the current context? To answer this question, we introduce \\textsc{ROSE} (\\textbf{R}eference-conditioned \\textbf{O}ddity and \\textbf{S}ymbolic \\textbf{E}xecution), a controlled benchmark that holds the visual scene fixed while varying region constraints and required symbolic outputs. Through coupled counting and coordinate-action tasks, \\","authors_text":"Jie Ren, Keze Wang, Yihao Wang, Zijian He","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T09:05:48Z","title":"ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19965","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":"sha256:894f70ef8b6eb72f812d50304b47ef38edd872df7d6d57f0c83c21dde9067fe2","target":"record","created_at":"2026-06-19T16:12:59Z","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":"49eb4ecf5a30f4e9aa7d6c34209c6b37c81561a17a474bb92a0a6fd5e24aff0d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-18T09:05:48Z","title_canon_sha256":"a3441c6445fc48166882afc7403cd9901168c99a65981c1c065b384a88a5ddd5"},"schema_version":"1.0","source":{"id":"2606.19965","kind":"arxiv","version":1}},"canonical_sha256":"3a1bc9cd613dfccca9e34bded88ac8794a843d0477fcdcc592f5d0c3dea870d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a1bc9cd613dfccca9e34bded88ac8794a843d0477fcdcc592f5d0c3dea870d3","first_computed_at":"2026-06-19T16:12:59.353400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:59.353400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y6vQLjDcxQqYJp7EMtVBmudlrUd0LuAvsabHElDFQ1HkEB0vzD+RnYX6418EPG9D+aiBza2Uf1q2HKDdlCAPCQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:59.353770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19965","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:894f70ef8b6eb72f812d50304b47ef38edd872df7d6d57f0c83c21dde9067fe2","sha256:5616a2c147864a61e76e2a2dc015f4940de072d73b2e3170f79ffbc7ac40e78e"],"state_sha256":"3071e6f844b903bebb1fc023826e8832cf2ca477c9c047913bf35f5a91f65ad4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+c5dOCp/ua5M8vVw5heebAg3ydTZadeGvP8lumyIo/rK6g4AcZgQ9gaTA8fr5WqH3qV8RumHle7bY3CUQcbBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T20:53:00.660930Z","bundle_sha256":"d8e69deeb0a6db61c14b6214b65f76f3e571a3acf417a416718b90269ede88b7"}}