{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VZMLLGAWQUW5Q3CRNEFGPHIF3K","short_pith_number":"pith:VZMLLGAW","canonical_record":{"source":{"id":"2606.01503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T23:59:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0d7963df82b5ed4618e757d9d35dd89f62d1676a6dfd3333afd7d30b9c9a7c18","abstract_canon_sha256":"601af94154317b76d74d0cc04eb134ffbb3e00546a67c90e84d6892edf8ec19e"},"schema_version":"1.0"},"canonical_sha256":"ae58b59816852dd86c51690a679d05daa289299a5e9e34bf7b86732fc9d054cd","source":{"kind":"arxiv","id":"2606.01503","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01503","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01503v1","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01503","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"VZMLLGAWQUW5","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"VZMLLGAWQUW5Q3CR","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"VZMLLGAW","created_at":"2026-06-02T02:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VZMLLGAWQUW5Q3CRNEFGPHIF3K","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01503","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T23:59:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0d7963df82b5ed4618e757d9d35dd89f62d1676a6dfd3333afd7d30b9c9a7c18","abstract_canon_sha256":"601af94154317b76d74d0cc04eb134ffbb3e00546a67c90e84d6892edf8ec19e"},"schema_version":"1.0"},"canonical_sha256":"ae58b59816852dd86c51690a679d05daa289299a5e9e34bf7b86732fc9d054cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:34.947841Z","signature_b64":"BBDN2+yuG0R1aIR7nBVy0zqogTOQBu4Va4bf6ikCIS3cB5c2IEa/3GMUe82K9zsPDj+msDN4evtZCZLOsyvgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae58b59816852dd86c51690a679d05daa289299a5e9e34bf7b86732fc9d054cd","last_reissued_at":"2026-06-02T02:04:34.947412Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:34.947412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01503","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":"2026-06-02T02:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6BXktLGOXy754BXvQYaoFajbZvxNbOUOxB/8VOAehZD/ZnCAi1aqC0Y3dqQWn0AFbES6sGDJ188/gjCiiMfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T19:11:16.617648Z"},"content_sha256":"763256326ab2c246ff6c4592fb4e498b81e167d4a6bdeed9c35f1669d540a261","schema_version":"1.0","event_id":"sha256:763256326ab2c246ff6c4592fb4e498b81e167d4a6bdeed9c35f1669d540a261"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VZMLLGAWQUW5Q3CRNEFGPHIF3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Limits of Token Reduction for Efficient Unified Vision Language Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jingtao Li, Lingjuan Lv, Siyi Chen, Weiming Zhuang","submitted_at":"2026-05-31T23:59:12Z","abstract_excerpt":"Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective. In this work, we study the feasibility and limits of token-reduction-based acceleration for unified VLM training. Through a systematic analysis of layerwise attention allocation, we uncover a fundamental asymmetry: visual understanding exhibits substantial late-layer visual redundancy, whereas visual generation maintains persistent dependence on image token"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01503","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/2606.01503/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":"2026-06-02T02:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VUOlNWsq4PXNwSPYbP2cDY78DiPOcxf40dGlD5AE/d3UaV9dCU4G4lHQBmXP6aOFp7VgU/8mlgdM2pSCegYHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T19:11:16.618420Z"},"content_sha256":"130244907994373959ff31de635836692252ee3a6eb4bd2909ddfc2dd64406d5","schema_version":"1.0","event_id":"sha256:130244907994373959ff31de635836692252ee3a6eb4bd2909ddfc2dd64406d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K/bundle.json","state_url":"https://pith.science/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K/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":"2026-06-07T19:11:16Z","links":{"resolver":"https://pith.science/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K","bundle":"https://pith.science/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K/bundle.json","state":"https://pith.science/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VZMLLGAWQUW5Q3CRNEFGPHIF3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VZMLLGAWQUW5Q3CRNEFGPHIF3K","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":"601af94154317b76d74d0cc04eb134ffbb3e00546a67c90e84d6892edf8ec19e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T23:59:12Z","title_canon_sha256":"0d7963df82b5ed4618e757d9d35dd89f62d1676a6dfd3333afd7d30b9c9a7c18"},"schema_version":"1.0","source":{"id":"2606.01503","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01503","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01503v1","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01503","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"VZMLLGAWQUW5","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"VZMLLGAWQUW5Q3CR","created_at":"2026-06-02T02:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"VZMLLGAW","created_at":"2026-06-02T02:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:130244907994373959ff31de635836692252ee3a6eb4bd2909ddfc2dd64406d5","target":"graph","created_at":"2026-06-02T02:04:34Z","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/2606.01503/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective. In this work, we study the feasibility and limits of token-reduction-based acceleration for unified VLM training. Through a systematic analysis of layerwise attention allocation, we uncover a fundamental asymmetry: visual understanding exhibits substantial late-layer visual redundancy, whereas visual generation maintains persistent dependence on image token","authors_text":"Jingtao Li, Lingjuan Lv, Siyi Chen, Weiming Zhuang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T23:59:12Z","title":"On the Limits of Token Reduction for Efficient Unified Vision Language Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01503","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":"sha256:763256326ab2c246ff6c4592fb4e498b81e167d4a6bdeed9c35f1669d540a261","target":"record","created_at":"2026-06-02T02:04:34Z","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":"601af94154317b76d74d0cc04eb134ffbb3e00546a67c90e84d6892edf8ec19e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T23:59:12Z","title_canon_sha256":"0d7963df82b5ed4618e757d9d35dd89f62d1676a6dfd3333afd7d30b9c9a7c18"},"schema_version":"1.0","source":{"id":"2606.01503","kind":"arxiv","version":1}},"canonical_sha256":"ae58b59816852dd86c51690a679d05daa289299a5e9e34bf7b86732fc9d054cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae58b59816852dd86c51690a679d05daa289299a5e9e34bf7b86732fc9d054cd","first_computed_at":"2026-06-02T02:04:34.947412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:34.947412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBDN2+yuG0R1aIR7nBVy0zqogTOQBu4Va4bf6ikCIS3cB5c2IEa/3GMUe82K9zsPDj+msDN4evtZCZLOsyvgDQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:34.947841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01503","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:763256326ab2c246ff6c4592fb4e498b81e167d4a6bdeed9c35f1669d540a261","sha256:130244907994373959ff31de635836692252ee3a6eb4bd2909ddfc2dd64406d5"],"state_sha256":"39012624ea81fc30d6910a7e23a78b98dde2646021daee7459852e8f7f24f48f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DYoub45Xngd7XQITafYxeqqUpiekIpqdY0jSitSpnGAH1cOcSkSnRjWrqKtxqCEHvwrNlng2vTpXeOXJotoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T19:11:16.622184Z","bundle_sha256":"945ec80def5109f70d55ff11628dd4e11c8e3d864f38bff0c827e2111bacb863"}}