{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7A3TBXEYR6EQQJZMC3CBW5VAF","short_pith_number":"pith:Y7A3TBXE","schema_version":"1.0","canonical_sha256":"c7c1b986e4c47c48413960b620dbb50152ae63cd9a812821f9dff6106af3893a","source":{"kind":"arxiv","id":"2606.11745","version":1},"attestation_state":"computed","paper":{"title":"From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoping Yu, Jing Ma, Yuanxi Li","submitted_at":"2026-06-10T07:21:45Z","abstract_excerpt":"Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual inputs and reasoning over intervention effects. Despite recent progress, large vision--language models (VLMs) remain brittle at such tasks, especially for interventional and counterfactual queries over multi-image inputs. Most existing explorations inject causal knowledge via textual prompts, leaving causal mechanisms external to model execution and limiting reliable control during inference. To address this problem, we propose BridgeVLM, which "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.11745","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-10T07:21:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d17b3785e0137a71b2ce20f81ad6cc4253e8f493edda1d7168eb7a3450c815b2","abstract_canon_sha256":"24e97ef12307c34f520d4a4dc576d77175268db823256f4d66fce962c4ddb3d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:10:05.830305Z","signature_b64":"uZ9pGCp9XPCGJ09BGr3MiXqSRUhhJ2ipe3sFIWpSpcNEYv5BnWbiO0nOYhU0ADk0dhunksrqNik4zRoIW1ENAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c1b986e4c47c48413960b620dbb50152ae63cd9a812821f9dff6106af3893a","last_reissued_at":"2026-06-11T01:10:05.829478Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:10:05.829478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoping Yu, Jing Ma, Yuanxi Li","submitted_at":"2026-06-10T07:21:45Z","abstract_excerpt":"Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual inputs and reasoning over intervention effects. Despite recent progress, large vision--language models (VLMs) remain brittle at such tasks, especially for interventional and counterfactual queries over multi-image inputs. Most existing explorations inject causal knowledge via textual prompts, leaving causal mechanisms external to model execution and limiting reliable control during inference. To address this problem, we propose BridgeVLM, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11745","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/2606.11745/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.11745","created_at":"2026-06-11T01:10:05.829609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11745v1","created_at":"2026-06-11T01:10:05.829609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11745","created_at":"2026-06-11T01:10:05.829609+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7A3TBXEYR6E","created_at":"2026-06-11T01:10:05.829609+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7A3TBXEYR6EQQJZ","created_at":"2026-06-11T01:10:05.829609+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7A3TBXE","created_at":"2026-06-11T01:10:05.829609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF","json":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF.json","graph_json":"https://pith.science/api/pith-number/Y7A3TBXEYR6EQQJZMC3CBW5VAF/graph.json","events_json":"https://pith.science/api/pith-number/Y7A3TBXEYR6EQQJZMC3CBW5VAF/events.json","paper":"https://pith.science/paper/Y7A3TBXE"},"agent_actions":{"view_html":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF","download_json":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF.json","view_paper":"https://pith.science/paper/Y7A3TBXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11745&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7A3TBXEYR6EQQJZMC3CBW5VAF/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7A3TBXEYR6EQQJZMC3CBW5VAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF/action/storage_attestation","attest_author":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF/action/author_attestation","sign_citation":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF/action/citation_signature","submit_replication":"https://pith.science/pith/Y7A3TBXEYR6EQQJZMC3CBW5VAF/action/replication_record"}},"created_at":"2026-06-11T01:10:05.829609+00:00","updated_at":"2026-06-11T01:10:05.829609+00:00"}