{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AFH5LHCVFT5UG63OAEDO4ZYWDU","short_pith_number":"pith:AFH5LHCV","canonical_record":{"source":{"id":"2606.09131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:28:14Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"613de62861b4733df430d8e614b8f02eb0532bf4f7ab6620368b65848ac10072","abstract_canon_sha256":"e801c91ae6c8071dfb87bed05a73e1518847ee50e2903958f34bec3dc00155b8"},"schema_version":"1.0"},"canonical_sha256":"014fd59c552cfb437b6e0106ee67161d16d7aa9f1a77dc36bbb6d53f63e99cc7","source":{"kind":"arxiv","id":"2606.09131","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09131","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09131v1","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09131","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"AFH5LHCVFT5U","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"AFH5LHCVFT5UG63O","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"AFH5LHCV","created_at":"2026-06-09T02:08:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AFH5LHCVFT5UG63OAEDO4ZYWDU","target":"record","payload":{"canonical_record":{"source":{"id":"2606.09131","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:28:14Z","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"613de62861b4733df430d8e614b8f02eb0532bf4f7ab6620368b65848ac10072","abstract_canon_sha256":"e801c91ae6c8071dfb87bed05a73e1518847ee50e2903958f34bec3dc00155b8"},"schema_version":"1.0"},"canonical_sha256":"014fd59c552cfb437b6e0106ee67161d16d7aa9f1a77dc36bbb6d53f63e99cc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:01.028878Z","signature_b64":"ldOaHng1WR+ChpTesuZjGOvfIafR9hkJcEuAfm3vto3NKQgfMoy9uCcT3EhSbEJ+VmrLIf25w8c6DYpiLA6UCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"014fd59c552cfb437b6e0106ee67161d16d7aa9f1a77dc36bbb6d53f63e99cc7","last_reissued_at":"2026-06-09T02:08:01.028022Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:01.028022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.09131","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":"2026-06-09T02:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cS2r/k6bydEaeruxMJIFqJtD9KOKW42/MRKDzQ02hpdpFhIa824Z6P3HcF/fuZiHZFPzrvOXgjIgrPBun6WyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T21:03:51.550002Z"},"content_sha256":"f6c2ab4c55cca733942085415491c258a9191684ef224657098a575f1803a6c4","schema_version":"1.0","event_id":"sha256:f6c2ab4c55cca733942085415491c258a9191684ef224657098a575f1803a6c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AFH5LHCVFT5UG63OAEDO4ZYWDU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Jinyang Wu, Siyuan Liu","submitted_at":"2026-06-08T07:28:14Z","abstract_excerpt":"Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the same computation uniformly to image and language tokens. This design overlooks a key modality asymmetry: image and text tokens differ substantially in information density, redundancy, and required reasoning depth. Through a layer-wise analysis of LLaVA-1.5, we observe that vision tokens tend to saturate in the middle layers. Specifically, text-to-image attention decreases from 0.68 at layer 0 to 0.07 by layer 4, and stabilizes near 0.04 after lay"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09131","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/2606.09131/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":"2026-06-09T02:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Afo2Z2c+tYasacC1sXqJUEaRGkjzz+f1f5kif1+UkxV1bkLIOBcDTrK/eBUGZfBt65BA3lfx9NzkNqi0RCwCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T21:03:51.550816Z"},"content_sha256":"a7aed69440b60064de59f4cea26477bf4bbe984cd37d341ea1df4b504b58cc53","schema_version":"1.0","event_id":"sha256:a7aed69440b60064de59f4cea26477bf4bbe984cd37d341ea1df4b504b58cc53"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU/bundle.json","state_url":"https://pith.science/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU/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":"2026-06-09T21:03:51Z","links":{"resolver":"https://pith.science/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU","bundle":"https://pith.science/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU/bundle.json","state":"https://pith.science/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AFH5LHCVFT5UG63OAEDO4ZYWDU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AFH5LHCVFT5UG63OAEDO4ZYWDU","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":"e801c91ae6c8071dfb87bed05a73e1518847ee50e2903958f34bec3dc00155b8","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:28:14Z","title_canon_sha256":"613de62861b4733df430d8e614b8f02eb0532bf4f7ab6620368b65848ac10072"},"schema_version":"1.0","source":{"id":"2606.09131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09131","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09131v1","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09131","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"AFH5LHCVFT5U","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"AFH5LHCVFT5UG63O","created_at":"2026-06-09T02:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"AFH5LHCV","created_at":"2026-06-09T02:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:a7aed69440b60064de59f4cea26477bf4bbe984cd37d341ea1df4b504b58cc53","target":"graph","created_at":"2026-06-09T02:08:01Z","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/2606.09131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the same computation uniformly to image and language tokens. This design overlooks a key modality asymmetry: image and text tokens differ substantially in information density, redundancy, and required reasoning depth. Through a layer-wise analysis of LLaVA-1.5, we observe that vision tokens tend to saturate in the middle layers. Specifically, text-to-image attention decreases from 0.68 at layer 0 to 0.07 by layer 4, and stabilizes near 0.04 after lay","authors_text":"Jinyang Wu, Siyuan Liu","cross_cats":["cs.CL","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:28:14Z","title":"Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09131","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:f6c2ab4c55cca733942085415491c258a9191684ef224657098a575f1803a6c4","target":"record","created_at":"2026-06-09T02:08:01Z","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":"e801c91ae6c8071dfb87bed05a73e1518847ee50e2903958f34bec3dc00155b8","cross_cats_sorted":["cs.CL","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-08T07:28:14Z","title_canon_sha256":"613de62861b4733df430d8e614b8f02eb0532bf4f7ab6620368b65848ac10072"},"schema_version":"1.0","source":{"id":"2606.09131","kind":"arxiv","version":1}},"canonical_sha256":"014fd59c552cfb437b6e0106ee67161d16d7aa9f1a77dc36bbb6d53f63e99cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"014fd59c552cfb437b6e0106ee67161d16d7aa9f1a77dc36bbb6d53f63e99cc7","first_computed_at":"2026-06-09T02:08:01.028022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:08:01.028022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldOaHng1WR+ChpTesuZjGOvfIafR9hkJcEuAfm3vto3NKQgfMoy9uCcT3EhSbEJ+VmrLIf25w8c6DYpiLA6UCQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:08:01.028878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6c2ab4c55cca733942085415491c258a9191684ef224657098a575f1803a6c4","sha256:a7aed69440b60064de59f4cea26477bf4bbe984cd37d341ea1df4b504b58cc53"],"state_sha256":"1f73aa0560d5d1a741618910c6359832e67b65bb0fe236982b22f89acf922c24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HhxdcoMwxjGGhiVb3dO9ofcUgqry10s4aueFVwQbCGzV8BFJo+rzqs7gGZg+mEuGZZJtLSoV5B5efOtY7acSCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T21:03:51.554648Z","bundle_sha256":"5777840a99d0751e465d2083f6e0ce54c027ba3a48c13f3706cbaa86d67a6142"}}