{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SBEKSNTKLQB2CB2LXKM25F4KKG","short_pith_number":"pith:SBEKSNTK","canonical_record":{"source":{"id":"2607.11436","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T11:44:23Z","cross_cats_sorted":[],"title_canon_sha256":"35bc24a8b62e94b815ee4d48461015afcca4fe1650ffb95a03939fce441dd8da","abstract_canon_sha256":"1869ef15a5eab11cf237c597eba4c00118b7cf67dfb8094aead8dcbb778ada92"},"schema_version":"1.0"},"canonical_sha256":"9048a9366a5c03a1074bba99ae978a51bb6e0f944cb4af7ac1a241a8c8810593","source":{"kind":"arxiv","id":"2607.11436","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11436","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11436v1","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11436","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"SBEKSNTKLQB2","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"SBEKSNTKLQB2CB2L","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"SBEKSNTK","created_at":"2026-07-14T02:22:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SBEKSNTKLQB2CB2LXKM25F4KKG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.11436","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T11:44:23Z","cross_cats_sorted":[],"title_canon_sha256":"35bc24a8b62e94b815ee4d48461015afcca4fe1650ffb95a03939fce441dd8da","abstract_canon_sha256":"1869ef15a5eab11cf237c597eba4c00118b7cf67dfb8094aead8dcbb778ada92"},"schema_version":"1.0"},"canonical_sha256":"9048a9366a5c03a1074bba99ae978a51bb6e0f944cb4af7ac1a241a8c8810593","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:02.704784Z","signature_b64":"LgYyikmDkmhz2S3eOmZBBIhHmURmXCyng0RFB+GtUy3YOqhCTVk36tvvcxNm+z1LD7B4KRTzAr98t60fOo6eBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9048a9366a5c03a1074bba99ae978a51bb6e0f944cb4af7ac1a241a8c8810593","last_reissued_at":"2026-07-14T02:22:02.703881Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:02.703881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.11436","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":"2026-07-14T02:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"th6gouZ8kZtgzLIOxgY7UjExq6GRhXNX/PlqYvP/Q5r6zB8R8Z9DAOQXp/z+4Xsqzr72+V09WazzNYRqhHm+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:23:39.618920Z"},"content_sha256":"9b3ffae71e51516279465273ee7e4c3f9a7363e736b57f1a30ed87a3fca0ed73","schema_version":"1.0","event_id":"sha256:9b3ffae71e51516279465273ee7e4c3f9a7363e736b57f1a30ed87a3fca0ed73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SBEKSNTKLQB2CB2LXKM25F4KKG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Heng Tao Shen, Hongye Fang, Jingkuan Song, Sirui Da, Wencheng Ye, Xing Xu, Yi Bin, Yujuan Ding, Yun Zhang, Zheng Wang","submitted_at":"2026-07-13T11:44:23Z","abstract_excerpt":"Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning. To understand this fragility, we examine the internal dynamics of VLMs through a mechanistic lens and uncover a stable three-stage redistribution of multimodal attention focus across depth: an early question-conditioned organization, a critical middle visual-dominant relay, and a late return to answer formation. We operationalize the middle phase as the Visual Relay Window (VRW), and show that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11436","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/2607.11436/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":"2026-07-14T02:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CPbadCuiI+M0UwFteZeIB0g6/UoUmnDuzYIbyhkxs3y6Qsw8JK1s09ulipCZQNP0fLBbeUd5jRyyZUPOukv3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:23:39.619367Z"},"content_sha256":"a6f3f82cca21e5fc577630a5dbfd79724b2cc03a3608bd33a32720fbe480f661","schema_version":"1.0","event_id":"sha256:a6f3f82cca21e5fc577630a5dbfd79724b2cc03a3608bd33a32720fbe480f661"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SBEKSNTKLQB2CB2LXKM25F4KKG/bundle.json","state_url":"https://pith.science/pith/SBEKSNTKLQB2CB2LXKM25F4KKG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SBEKSNTKLQB2CB2LXKM25F4KKG/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":"2026-08-14T17:23:39Z","links":{"resolver":"https://pith.science/pith/SBEKSNTKLQB2CB2LXKM25F4KKG","bundle":"https://pith.science/pith/SBEKSNTKLQB2CB2LXKM25F4KKG/bundle.json","state":"https://pith.science/pith/SBEKSNTKLQB2CB2LXKM25F4KKG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SBEKSNTKLQB2CB2LXKM25F4KKG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SBEKSNTKLQB2CB2LXKM25F4KKG","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":"1869ef15a5eab11cf237c597eba4c00118b7cf67dfb8094aead8dcbb778ada92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T11:44:23Z","title_canon_sha256":"35bc24a8b62e94b815ee4d48461015afcca4fe1650ffb95a03939fce441dd8da"},"schema_version":"1.0","source":{"id":"2607.11436","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.11436","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.11436v1","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11436","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"SBEKSNTKLQB2","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"SBEKSNTKLQB2CB2L","created_at":"2026-07-14T02:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"SBEKSNTK","created_at":"2026-07-14T02:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:a6f3f82cca21e5fc577630a5dbfd79724b2cc03a3608bd33a32720fbe480f661","target":"graph","created_at":"2026-07-14T02:22:02Z","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/2607.11436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models increasingly succeed on multimodal reasoning benchmarks, yet their visual evidence often becomes unstable once it enters the language stack, weakening evidence-grounded reasoning. To understand this fragility, we examine the internal dynamics of VLMs through a mechanistic lens and uncover a stable three-stage redistribution of multimodal attention focus across depth: an early question-conditioned organization, a critical middle visual-dominant relay, and a late return to answer formation. We operationalize the middle phase as the Visual Relay Window (VRW), and show that ","authors_text":"Heng Tao Shen, Hongye Fang, Jingkuan Song, Sirui Da, Wencheng Ye, Xing Xu, Yi Bin, Yujuan Ding, Yun Zhang, Zheng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T11:44:23Z","title":"The Ebb and Flow of Multimodal Focus: Scheduling Visual Relay Windows for Grounded VLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11436","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":"sha256:9b3ffae71e51516279465273ee7e4c3f9a7363e736b57f1a30ed87a3fca0ed73","target":"record","created_at":"2026-07-14T02:22:02Z","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":"1869ef15a5eab11cf237c597eba4c00118b7cf67dfb8094aead8dcbb778ada92","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-13T11:44:23Z","title_canon_sha256":"35bc24a8b62e94b815ee4d48461015afcca4fe1650ffb95a03939fce441dd8da"},"schema_version":"1.0","source":{"id":"2607.11436","kind":"arxiv","version":1}},"canonical_sha256":"9048a9366a5c03a1074bba99ae978a51bb6e0f944cb4af7ac1a241a8c8810593","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9048a9366a5c03a1074bba99ae978a51bb6e0f944cb4af7ac1a241a8c8810593","first_computed_at":"2026-07-14T02:22:02.703881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T02:22:02.703881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LgYyikmDkmhz2S3eOmZBBIhHmURmXCyng0RFB+GtUy3YOqhCTVk36tvvcxNm+z1LD7B4KRTzAr98t60fOo6eBw==","signature_status":"signed_v1","signed_at":"2026-07-14T02:22:02.704784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.11436","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b3ffae71e51516279465273ee7e4c3f9a7363e736b57f1a30ed87a3fca0ed73","sha256:a6f3f82cca21e5fc577630a5dbfd79724b2cc03a3608bd33a32720fbe480f661"],"state_sha256":"646d38da5399c1b787b6fa935a2e964f5cd7f076a0432f968bea9a7f08bef7ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c8xI0SXMcRYyiC16cxkR9ko48UYzs4TTOnl3pLyib3IgD4g9Q6ODvxsf3PtJ/7fXddk34Yl8lujz3vzFvaaaDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:23:39.622989Z","bundle_sha256":"422173684490787a5d5be1eb582348df49909be4f748f862a6db8a97382b77e4"}}