{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5FLTEO3ZX4KZ5IDM4VRL3MEW56","short_pith_number":"pith:5FLTEO3Z","canonical_record":{"source":{"id":"2502.17425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:56:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3a70a66e0cce735e36919810f5ce6afd2f3dba9121c5b0582cdc1125fe1da0b","abstract_canon_sha256":"809b237c450bbd36856d4c751c35844716aee8fdb7b7cc618c360c8c4dce6b85"},"schema_version":"1.0"},"canonical_sha256":"e957323b79bf159ea06ce562bdb096efa3b5d197bc75499261c2172bdffe0b31","source":{"kind":"arxiv","id":"2502.17425","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17425","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17425v1","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17425","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"5FLTEO3ZX4KZ","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"5FLTEO3ZX4KZ5IDM","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"5FLTEO3Z","created_at":"2026-07-05T10:19:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5FLTEO3ZX4KZ5IDM4VRL3MEW56","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:56:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e3a70a66e0cce735e36919810f5ce6afd2f3dba9121c5b0582cdc1125fe1da0b","abstract_canon_sha256":"809b237c450bbd36856d4c751c35844716aee8fdb7b7cc618c360c8c4dce6b85"},"schema_version":"1.0"},"canonical_sha256":"e957323b79bf159ea06ce562bdb096efa3b5d197bc75499261c2172bdffe0b31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:10.015957Z","signature_b64":"45KJNpRM2Pyra4vUP9CMF7HedxY22quWTvUObgN96Ynfc4ZEreTD5K69ZaG65rj4bRxX8tYJD36iFdF8eKLOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e957323b79bf159ea06ce562bdb096efa3b5d197bc75499261c2172bdffe0b31","last_reissued_at":"2026-07-05T10:19:10.015486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:10.015486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17425","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":"2026-07-05T10:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XE/8wU4PKnUjV2XTyULwJC52dsRVHYbYe/MBogrmI6DnGF02uHm8paymdXGXnYGImGOdNjhO7UziCSrSZVIDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:03:59.469730Z"},"content_sha256":"993bd63c00bd3ed8badfbbd74d321df2e697de4356b0e8e245b715b9994299e0","schema_version":"1.0","event_id":"sha256:993bd63c00bd3ed8badfbbd74d321df2e697de4356b0e8e245b715b9994299e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5FLTEO3ZX4KZ5IDM4VRL3MEW56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Introducing Visual Perception Token into Multimodal Large Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Runpeng Yu, Xinchao Wang, Xinyin Ma","submitted_at":"2025-02-24T18:56:12Z","abstract_excerpt":"To utilize visual information, Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder. The completeness and accuracy of visual perception significantly influence the precision of spatial reasoning, fine-grained understanding, and other tasks. However, MLLM still lacks the autonomous capability to control its own visual perception processes, for example, selectively reviewing specific regions of an image or focusing on information related to specific object categories. In this work, we propose the concept of Visual Perception Token, aiming to empower MLLM "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17425","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/2502.17425/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":"2026-07-05T10:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xJE06C7qvJqkUUxKp9mwN7gocnPSbvEgHJLt0oUd94iEvUKNKDQoHJWlLt+BqKYhZAT4bszvz3ehi01aryX2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:03:59.470268Z"},"content_sha256":"91a0a6fb363a22146b09be42e18ed9b0e1513e38a73342a42f67ee867c94453c","schema_version":"1.0","event_id":"sha256:91a0a6fb363a22146b09be42e18ed9b0e1513e38a73342a42f67ee867c94453c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56/bundle.json","state_url":"https://pith.science/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56/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":"2026-08-06T03:03:59Z","links":{"resolver":"https://pith.science/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56","bundle":"https://pith.science/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56/bundle.json","state":"https://pith.science/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FLTEO3ZX4KZ5IDM4VRL3MEW56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5FLTEO3ZX4KZ5IDM4VRL3MEW56","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":"809b237c450bbd36856d4c751c35844716aee8fdb7b7cc618c360c8c4dce6b85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:56:12Z","title_canon_sha256":"e3a70a66e0cce735e36919810f5ce6afd2f3dba9121c5b0582cdc1125fe1da0b"},"schema_version":"1.0","source":{"id":"2502.17425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17425","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17425v1","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17425","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"5FLTEO3ZX4KZ","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"5FLTEO3ZX4KZ5IDM","created_at":"2026-07-05T10:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"5FLTEO3Z","created_at":"2026-07-05T10:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:91a0a6fb363a22146b09be42e18ed9b0e1513e38a73342a42f67ee867c94453c","target":"graph","created_at":"2026-07-05T10:19:10Z","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/2502.17425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To utilize visual information, Multimodal Large Language Model (MLLM) relies on the perception process of its vision encoder. The completeness and accuracy of visual perception significantly influence the precision of spatial reasoning, fine-grained understanding, and other tasks. However, MLLM still lacks the autonomous capability to control its own visual perception processes, for example, selectively reviewing specific regions of an image or focusing on information related to specific object categories. In this work, we propose the concept of Visual Perception Token, aiming to empower MLLM ","authors_text":"Runpeng Yu, Xinchao Wang, Xinyin Ma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:56:12Z","title":"Introducing Visual Perception Token into Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17425","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":"sha256:993bd63c00bd3ed8badfbbd74d321df2e697de4356b0e8e245b715b9994299e0","target":"record","created_at":"2026-07-05T10:19:10Z","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":"809b237c450bbd36856d4c751c35844716aee8fdb7b7cc618c360c8c4dce6b85","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-24T18:56:12Z","title_canon_sha256":"e3a70a66e0cce735e36919810f5ce6afd2f3dba9121c5b0582cdc1125fe1da0b"},"schema_version":"1.0","source":{"id":"2502.17425","kind":"arxiv","version":1}},"canonical_sha256":"e957323b79bf159ea06ce562bdb096efa3b5d197bc75499261c2172bdffe0b31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e957323b79bf159ea06ce562bdb096efa3b5d197bc75499261c2172bdffe0b31","first_computed_at":"2026-07-05T10:19:10.015486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:10.015486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"45KJNpRM2Pyra4vUP9CMF7HedxY22quWTvUObgN96Ynfc4ZEreTD5K69ZaG65rj4bRxX8tYJD36iFdF8eKLOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:10.015957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:993bd63c00bd3ed8badfbbd74d321df2e697de4356b0e8e245b715b9994299e0","sha256:91a0a6fb363a22146b09be42e18ed9b0e1513e38a73342a42f67ee867c94453c"],"state_sha256":"6513448e19c710a251bbac3fcac35b2d68fb16097cbd1f42d3314961800a4d0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"evzDR2xOFvtPBK9udiuUk2jS5S6rl74YfHj8Xv306UoIYsw8YVibNYJpVovGRqyw41ML8YZvA9dPCYx3npqnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:03:59.474138Z","bundle_sha256":"1cb451d8a8f8dd69f9e551a4babed49f2180c82e3c76d8a70d834a12cff0364b"}}