{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:W5XK3MCJCYJVWIB7LZWWBOMYCP","short_pith_number":"pith:W5XK3MCJ","canonical_record":{"source":{"id":"2411.10803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T13:45:33Z","cross_cats_sorted":[],"title_canon_sha256":"6e9c46b4cbbc3f3db2a0a60027f4fe61967ba2aa96114a47049c338383f87975","abstract_canon_sha256":"3b583b2b2d9c1d7d6c2fc63815c23a3aaaf6c2ecc22b967048667168c7ac52c7"},"schema_version":"1.0"},"canonical_sha256":"b76eadb04916135b203f5e6d60b99813f4a20dd99f0c49e9f00344b285392ce8","source":{"kind":"arxiv","id":"2411.10803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10803","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10803v1","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10803","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"W5XK3MCJCYJV","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"W5XK3MCJCYJVWIB7","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"W5XK3MCJ","created_at":"2026-07-05T09:36:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:W5XK3MCJCYJVWIB7LZWWBOMYCP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.10803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T13:45:33Z","cross_cats_sorted":[],"title_canon_sha256":"6e9c46b4cbbc3f3db2a0a60027f4fe61967ba2aa96114a47049c338383f87975","abstract_canon_sha256":"3b583b2b2d9c1d7d6c2fc63815c23a3aaaf6c2ecc22b967048667168c7ac52c7"},"schema_version":"1.0"},"canonical_sha256":"b76eadb04916135b203f5e6d60b99813f4a20dd99f0c49e9f00344b285392ce8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:22.403539Z","signature_b64":"Ut2RiEIKXJ7TUvr3qYGbmjNSuJRKe+5xoSpqVU46ZJjsOjZVbamsKZ8KiDsaDwShETZ2H+GUUprbUGIYymy4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b76eadb04916135b203f5e6d60b99813f4a20dd99f0c49e9f00344b285392ce8","last_reissued_at":"2026-07-05T09:36:22.403019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:22.403019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.10803","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":"2026-07-05T09:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EMZSvYFf0zWtOK0okLgIN1gOxSUPZpUYrXgYB5866A2k+ZGXNhotm5eUjfFc93+l5N9kvvjyglWk8arMgFcUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:36:02.658388Z"},"content_sha256":"0bb6578a7bfbd2ceecfc9979975344ea685baedf95260b51410eb1f22a7cafbf","schema_version":"1.0","event_id":"sha256:0bb6578a7bfbd2ceecfc9979975344ea685baedf95260b51410eb1f22a7cafbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:W5XK3MCJCYJVWIB7LZWWBOMYCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liangtao Shi, Linfeng Zhang, Quanjun Yin, Richang Hong, Ting Liu, Yue Hu","submitted_at":"2024-11-16T13:45:33Z","abstract_excerpt":"The vision tokens in multimodal large language models usually exhibit significant spatial and temporal redundancy and take up most of the input tokens, which harms their inference efficiency. To solve this problem, some recent works were introduced to drop the unimportant tokens during inference where the importance of each token is decided only by the information in either the vision encoding stage or the prefilling stage. In this paper, we propose Multi-stage Token Dropping (MustDrop) to measure the importance of each token from the whole lifecycle, including the vision encoding stage, prefi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10803","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/2411.10803/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":"2026-07-05T09:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q/338jZCf2dxkn4yQYpP0zm2JMmbOuRHzrVKnHqHV7fB5VspSZWNoWcV3RGZIcziZLjtBOWxKC+1hitD+bNLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T17:36:02.658881Z"},"content_sha256":"e7cf7cc2dedf7f2106e71da8d7607cfdddb0d46cfe89280704da704fdb424d39","schema_version":"1.0","event_id":"sha256:e7cf7cc2dedf7f2106e71da8d7607cfdddb0d46cfe89280704da704fdb424d39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP/bundle.json","state_url":"https://pith.science/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP/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":"2026-08-08T17:36:02Z","links":{"resolver":"https://pith.science/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP","bundle":"https://pith.science/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP/bundle.json","state":"https://pith.science/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W5XK3MCJCYJVWIB7LZWWBOMYCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W5XK3MCJCYJVWIB7LZWWBOMYCP","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":"3b583b2b2d9c1d7d6c2fc63815c23a3aaaf6c2ecc22b967048667168c7ac52c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T13:45:33Z","title_canon_sha256":"6e9c46b4cbbc3f3db2a0a60027f4fe61967ba2aa96114a47049c338383f87975"},"schema_version":"1.0","source":{"id":"2411.10803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.10803","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2411.10803v1","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10803","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"W5XK3MCJCYJV","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"W5XK3MCJCYJVWIB7","created_at":"2026-07-05T09:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"W5XK3MCJ","created_at":"2026-07-05T09:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:e7cf7cc2dedf7f2106e71da8d7607cfdddb0d46cfe89280704da704fdb424d39","target":"graph","created_at":"2026-07-05T09:36:22Z","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/2411.10803/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The vision tokens in multimodal large language models usually exhibit significant spatial and temporal redundancy and take up most of the input tokens, which harms their inference efficiency. To solve this problem, some recent works were introduced to drop the unimportant tokens during inference where the importance of each token is decided only by the information in either the vision encoding stage or the prefilling stage. In this paper, we propose Multi-stage Token Dropping (MustDrop) to measure the importance of each token from the whole lifecycle, including the vision encoding stage, prefi","authors_text":"Liangtao Shi, Linfeng Zhang, Quanjun Yin, Richang Hong, Ting Liu, Yue Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T13:45:33Z","title":"Multi-Stage Vision Token Dropping: Towards Efficient Multimodal Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10803","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":"sha256:0bb6578a7bfbd2ceecfc9979975344ea685baedf95260b51410eb1f22a7cafbf","target":"record","created_at":"2026-07-05T09:36:22Z","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":"3b583b2b2d9c1d7d6c2fc63815c23a3aaaf6c2ecc22b967048667168c7ac52c7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-16T13:45:33Z","title_canon_sha256":"6e9c46b4cbbc3f3db2a0a60027f4fe61967ba2aa96114a47049c338383f87975"},"schema_version":"1.0","source":{"id":"2411.10803","kind":"arxiv","version":1}},"canonical_sha256":"b76eadb04916135b203f5e6d60b99813f4a20dd99f0c49e9f00344b285392ce8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b76eadb04916135b203f5e6d60b99813f4a20dd99f0c49e9f00344b285392ce8","first_computed_at":"2026-07-05T09:36:22.403019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:22.403019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ut2RiEIKXJ7TUvr3qYGbmjNSuJRKe+5xoSpqVU46ZJjsOjZVbamsKZ8KiDsaDwShETZ2H+GUUprbUGIYymy4Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:22.403539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.10803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bb6578a7bfbd2ceecfc9979975344ea685baedf95260b51410eb1f22a7cafbf","sha256:e7cf7cc2dedf7f2106e71da8d7607cfdddb0d46cfe89280704da704fdb424d39"],"state_sha256":"8560425a2efbf0fa2cb9a71b760a9c7f9a7d553f9690442df6a7817e6fd1b439"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"epoSxxlz/6DSvmWc4VqI+OjdbbE3Rt5ZU4q8VhlkfOkySzu17sde00AXrRKW1b2UdBguXtlFRC533SaXx/b1Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T17:36:02.662730Z","bundle_sha256":"2ca6a50936981889ca53b0a5cf14b3806e1702f92d226d168a13f20c63ede4fb"}}