{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AHSW27JQIUIYFV3UBZJ5QUYKTP","short_pith_number":"pith:AHSW27JQ","canonical_record":{"source":{"id":"2606.30288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T13:30:17Z","cross_cats_sorted":[],"title_canon_sha256":"77ccb252f8ce9cc6fb9f5de0057ca3bfd373e07eca44c737c2b84f6056215fed","abstract_canon_sha256":"d1f4560e98a7d4dc8a4c7f386e8af66c50221053620d85b56438f8341329c43d"},"schema_version":"1.0"},"canonical_sha256":"01e56d7d30451182d7740e53d8530a9bea78e3ad73c479a4ce0f3a59333dba1f","source":{"kind":"arxiv","id":"2606.30288","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30288","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30288v1","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30288","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"AHSW27JQIUIY","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"AHSW27JQIUIYFV3U","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"AHSW27JQ","created_at":"2026-06-30T02:17:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AHSW27JQIUIYFV3UBZJ5QUYKTP","target":"record","payload":{"canonical_record":{"source":{"id":"2606.30288","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T13:30:17Z","cross_cats_sorted":[],"title_canon_sha256":"77ccb252f8ce9cc6fb9f5de0057ca3bfd373e07eca44c737c2b84f6056215fed","abstract_canon_sha256":"d1f4560e98a7d4dc8a4c7f386e8af66c50221053620d85b56438f8341329c43d"},"schema_version":"1.0"},"canonical_sha256":"01e56d7d30451182d7740e53d8530a9bea78e3ad73c479a4ce0f3a59333dba1f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:57.516482Z","signature_b64":"AhTb/Hs3vAqigLF+8kuioSG+NLJS25PD92gJBJfIodl1pxdGi0duQPFLXilkLdZPccYfq0VGNQAie9xK68IkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e56d7d30451182d7740e53d8530a9bea78e3ad73c479a4ce0f3a59333dba1f","last_reissued_at":"2026-06-30T02:17:57.515999Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:57.515999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.30288","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":"2026-06-30T02:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7XpQtAbnC4PWrC6KrxTA/QRM9JBAODkNhdTkdR3rirOeXcbReBaSOq4t6rvIYF7Ar9NO4WEJvnEgFig5ILzmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:04:52.033216Z"},"content_sha256":"c76ecb2e386ad6f05f890ce611ea5143405af348cc9742be74920ff0e19b13fc","schema_version":"1.0","event_id":"sha256:c76ecb2e386ad6f05f890ce611ea5143405af348cc9742be74920ff0e19b13fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AHSW27JQIUIYFV3UBZJ5QUYKTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mohamed Elhoseiny, Xiaoqian Shen","submitted_at":"2026-06-29T13:30:17Z","abstract_excerpt":"Large Vision Language Models (LVLMs) have achieved remarkable success on vision-language tasks, yet fine-grained perception over high-resolution images and long-context videos remains challenging. As the number of visual tokens increases, the visual attention sink phenomenon becomes increasingly severe, causing irrelevant tokens to absorb a disproportionate amount of attention mass. Recent approaches attempt to mitigate this issue by explicitly predicting bounding boxes or temporal spans and re-encoding the cropped visual regions. Such methods depend on unreliable numeric localization in the d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30288","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/2606.30288/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":"2026-06-30T02:17:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/oXo7puISKYhfE359AN3ZZaqeu6AmNSWIMNQ1Xh+qpLvuMnymYXFm3CFyYa9zIuwOSETj+LsO9I46KeRKaMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T18:04:52.033611Z"},"content_sha256":"eaf2499847df3c60ac41b363994e719959ae5079f3c878065a274ff3c9c55ffe","schema_version":"1.0","event_id":"sha256:eaf2499847df3c60ac41b363994e719959ae5079f3c878065a274ff3c9c55ffe"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP/bundle.json","state_url":"https://pith.science/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP/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":"2026-06-30T18:04:52Z","links":{"resolver":"https://pith.science/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP","bundle":"https://pith.science/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP/bundle.json","state":"https://pith.science/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHSW27JQIUIYFV3UBZJ5QUYKTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AHSW27JQIUIYFV3UBZJ5QUYKTP","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":"d1f4560e98a7d4dc8a4c7f386e8af66c50221053620d85b56438f8341329c43d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T13:30:17Z","title_canon_sha256":"77ccb252f8ce9cc6fb9f5de0057ca3bfd373e07eca44c737c2b84f6056215fed"},"schema_version":"1.0","source":{"id":"2606.30288","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30288","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30288v1","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30288","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"pith_short_12","alias_value":"AHSW27JQIUIY","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"pith_short_16","alias_value":"AHSW27JQIUIYFV3U","created_at":"2026-06-30T02:17:57Z"},{"alias_kind":"pith_short_8","alias_value":"AHSW27JQ","created_at":"2026-06-30T02:17:57Z"}],"graph_snapshots":[{"event_id":"sha256:eaf2499847df3c60ac41b363994e719959ae5079f3c878065a274ff3c9c55ffe","target":"graph","created_at":"2026-06-30T02:17:57Z","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/2606.30288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision Language Models (LVLMs) have achieved remarkable success on vision-language tasks, yet fine-grained perception over high-resolution images and long-context videos remains challenging. As the number of visual tokens increases, the visual attention sink phenomenon becomes increasingly severe, causing irrelevant tokens to absorb a disproportionate amount of attention mass. Recent approaches attempt to mitigate this issue by explicitly predicting bounding boxes or temporal spans and re-encoding the cropped visual regions. Such methods depend on unreliable numeric localization in the d","authors_text":"Mohamed Elhoseiny, Xiaoqian Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T13:30:17Z","title":"VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30288","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:c76ecb2e386ad6f05f890ce611ea5143405af348cc9742be74920ff0e19b13fc","target":"record","created_at":"2026-06-30T02:17:57Z","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":"d1f4560e98a7d4dc8a4c7f386e8af66c50221053620d85b56438f8341329c43d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-29T13:30:17Z","title_canon_sha256":"77ccb252f8ce9cc6fb9f5de0057ca3bfd373e07eca44c737c2b84f6056215fed"},"schema_version":"1.0","source":{"id":"2606.30288","kind":"arxiv","version":1}},"canonical_sha256":"01e56d7d30451182d7740e53d8530a9bea78e3ad73c479a4ce0f3a59333dba1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01e56d7d30451182d7740e53d8530a9bea78e3ad73c479a4ce0f3a59333dba1f","first_computed_at":"2026-06-30T02:17:57.515999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:57.515999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AhTb/Hs3vAqigLF+8kuioSG+NLJS25PD92gJBJfIodl1pxdGi0duQPFLXilkLdZPccYfq0VGNQAie9xK68IkAw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:57.516482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30288","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c76ecb2e386ad6f05f890ce611ea5143405af348cc9742be74920ff0e19b13fc","sha256:eaf2499847df3c60ac41b363994e719959ae5079f3c878065a274ff3c9c55ffe"],"state_sha256":"0e0c25bc1144b8381942e32b7f16ceab12c133e2f1077380bb340a733a6f86e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WZ6lcvbNeZbgxqb2XRtrsH8H313iZ6FuXf9gik1HaTOSTyn+refLp4p8Qly/ikrQfQrMDPjgVm0skF4EBG19Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T18:04:52.035633Z","bundle_sha256":"e918e19bc87c1cf4573cea9428918da344a237988d10ce7f6879b07e30842803"}}