{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FGCQSQRDYGUVE6UEJP67XJKQY7","short_pith_number":"pith:FGCQSQRD","canonical_record":{"source":{"id":"2606.23354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T13:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"0bfd12ace4674e9bc62db1e7f12761d417769692fccf5645c2e070c71a56e415","abstract_canon_sha256":"e29a806144f66ef26bc1cc287ce13ab297364e8dcbc29c571aa1ff33ed7f746a"},"schema_version":"1.0"},"canonical_sha256":"2985094223c1a9527a844bfdfba550c7f3282508d357d790a15a09eb195d5bc0","source":{"kind":"arxiv","id":"2606.23354","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23354","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23354v1","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23354","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"FGCQSQRDYGUV","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"FGCQSQRDYGUVE6UE","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"FGCQSQRD","created_at":"2026-06-23T03:14:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FGCQSQRDYGUVE6UEJP67XJKQY7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.23354","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T13:54:48Z","cross_cats_sorted":[],"title_canon_sha256":"0bfd12ace4674e9bc62db1e7f12761d417769692fccf5645c2e070c71a56e415","abstract_canon_sha256":"e29a806144f66ef26bc1cc287ce13ab297364e8dcbc29c571aa1ff33ed7f746a"},"schema_version":"1.0"},"canonical_sha256":"2985094223c1a9527a844bfdfba550c7f3282508d357d790a15a09eb195d5bc0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:17.606752Z","signature_b64":"B4gFfwUnQjqKSP9jr9UId/6xpn6B36Ho8W9chR6fdDxrGwACDrfCa8IwgT/LGNRT2qJcMSxorN3AfP5X5OF1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2985094223c1a9527a844bfdfba550c7f3282508d357d790a15a09eb195d5bc0","last_reissued_at":"2026-06-23T03:14:17.606350Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:17.606350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.23354","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":"2026-06-23T03:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2vW34kidztIo51HKDQCztSfxwB++9EYyTYiF5De0f4F5Rj4wUfsvsSWpVlhD6NgY5fOxFXzvVFDyQr5CdlYwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T08:41:11.395058Z"},"content_sha256":"b377541ea9da8e9bc755fa0ac0ca160ab168c4d0735b67820cf47b6dc253cf9d","schema_version":"1.0","event_id":"sha256:b377541ea9da8e9bc755fa0ac0ca160ab168c4d0735b67820cf47b6dc253cf9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FGCQSQRDYGUVE6UEJP67XJKQY7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Faithful Grounded Visual Reasoning via Learned Proxy-Tokens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aboubacar Tuo, Angelique Loesch, Mohamed Chaouch, Tom Hodemon","submitted_at":"2026-06-22T13:54:48Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in Visual Question Answering (VQA), yet their \"black-box\" nature hinders deployment in critical domains. Grounded Visual Reasoning (GVR) approaches attempt to improve interpretability by explicitly couple textual rationales with visual grounding information, which are typically textual coordinates. This mechanism lacks a learnable semantic link to the visual features, often resulting in a semantic-spatial gap where the model hallucinates coordinates that do not correspond to image evidences. In this work, we introduce Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23354","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/2606.23354/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":"2026-06-23T03:14:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yj8jlLwbLSE+XZeB06f+07y7UyoAYID0r3qb+zu2aob/rF0VdwNGdEYgbInNU9jAjEA0gVUt81jmGcObzy4lDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T08:41:11.395455Z"},"content_sha256":"86c8688c266192ccb09d57ffd9c9459565114bf5e32df91f9ef0d4709ecebb42","schema_version":"1.0","event_id":"sha256:86c8688c266192ccb09d57ffd9c9459565114bf5e32df91f9ef0d4709ecebb42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FGCQSQRDYGUVE6UEJP67XJKQY7/bundle.json","state_url":"https://pith.science/pith/FGCQSQRDYGUVE6UEJP67XJKQY7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FGCQSQRDYGUVE6UEJP67XJKQY7/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":"2026-07-04T08:41:11Z","links":{"resolver":"https://pith.science/pith/FGCQSQRDYGUVE6UEJP67XJKQY7","bundle":"https://pith.science/pith/FGCQSQRDYGUVE6UEJP67XJKQY7/bundle.json","state":"https://pith.science/pith/FGCQSQRDYGUVE6UEJP67XJKQY7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FGCQSQRDYGUVE6UEJP67XJKQY7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FGCQSQRDYGUVE6UEJP67XJKQY7","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":"e29a806144f66ef26bc1cc287ce13ab297364e8dcbc29c571aa1ff33ed7f746a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T13:54:48Z","title_canon_sha256":"0bfd12ace4674e9bc62db1e7f12761d417769692fccf5645c2e070c71a56e415"},"schema_version":"1.0","source":{"id":"2606.23354","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.23354","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"arxiv_version","alias_value":"2606.23354v1","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23354","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"pith_short_12","alias_value":"FGCQSQRDYGUV","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"pith_short_16","alias_value":"FGCQSQRDYGUVE6UE","created_at":"2026-06-23T03:14:17Z"},{"alias_kind":"pith_short_8","alias_value":"FGCQSQRD","created_at":"2026-06-23T03:14:17Z"}],"graph_snapshots":[{"event_id":"sha256:86c8688c266192ccb09d57ffd9c9459565114bf5e32df91f9ef0d4709ecebb42","target":"graph","created_at":"2026-06-23T03:14:17Z","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/2606.23354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have achieved remarkable success in Visual Question Answering (VQA), yet their \"black-box\" nature hinders deployment in critical domains. Grounded Visual Reasoning (GVR) approaches attempt to improve interpretability by explicitly couple textual rationales with visual grounding information, which are typically textual coordinates. This mechanism lacks a learnable semantic link to the visual features, often resulting in a semantic-spatial gap where the model hallucinates coordinates that do not correspond to image evidences. In this work, we introduce Co","authors_text":"Aboubacar Tuo, Angelique Loesch, Mohamed Chaouch, Tom Hodemon","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T13:54:48Z","title":"Faithful Grounded Visual Reasoning via Learned Proxy-Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23354","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:b377541ea9da8e9bc755fa0ac0ca160ab168c4d0735b67820cf47b6dc253cf9d","target":"record","created_at":"2026-06-23T03:14:17Z","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":"e29a806144f66ef26bc1cc287ce13ab297364e8dcbc29c571aa1ff33ed7f746a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T13:54:48Z","title_canon_sha256":"0bfd12ace4674e9bc62db1e7f12761d417769692fccf5645c2e070c71a56e415"},"schema_version":"1.0","source":{"id":"2606.23354","kind":"arxiv","version":1}},"canonical_sha256":"2985094223c1a9527a844bfdfba550c7f3282508d357d790a15a09eb195d5bc0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2985094223c1a9527a844bfdfba550c7f3282508d357d790a15a09eb195d5bc0","first_computed_at":"2026-06-23T03:14:17.606350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:17.606350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4gFfwUnQjqKSP9jr9UId/6xpn6B36Ho8W9chR6fdDxrGwACDrfCa8IwgT/LGNRT2qJcMSxorN3AfP5X5OF1BA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:17.606752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.23354","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b377541ea9da8e9bc755fa0ac0ca160ab168c4d0735b67820cf47b6dc253cf9d","sha256:86c8688c266192ccb09d57ffd9c9459565114bf5e32df91f9ef0d4709ecebb42"],"state_sha256":"be78c9090e107234fbbaf11d4e61d5d110310976868abb5235018951b81ea402"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QeOHgIhPvQeH5ixpBXgwN0tqvo9BuKpDv6xEnf8QC81wpevNfhdYgwssSMW3BNFGqDWh4cf6pCdBDh5c74PbDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T08:41:11.397420Z","bundle_sha256":"df02cd4e688701d657800170a59dca6fa25ca69742a7ab19466b3f99f59ecd86"}}