{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2I6XLRR7FDHUCCRRHTMUTVZFM5","short_pith_number":"pith:2I6XLRR7","canonical_record":{"source":{"id":"2409.10197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T11:43:19Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"76c06a23dea201701ecd79fa6243588c6dc4afbe97d41730d4d8cac64a2b1cb6","abstract_canon_sha256":"cbbb3206683e5c03f60f8c0860e9dec0e0160d536ca3e6b5f57af31940ba3f95"},"schema_version":"1.0"},"canonical_sha256":"d23d75c63f28cf410a313cd949d725674e3630a504a6869898aae28c8fb1f282","source":{"kind":"arxiv","id":"2409.10197","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10197","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10197v2","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10197","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"2I6XLRR7FDHU","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"2I6XLRR7FDHUCCRR","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"2I6XLRR7","created_at":"2026-07-05T09:54:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2I6XLRR7FDHUCCRRHTMUTVZFM5","target":"record","payload":{"canonical_record":{"source":{"id":"2409.10197","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T11:43:19Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"76c06a23dea201701ecd79fa6243588c6dc4afbe97d41730d4d8cac64a2b1cb6","abstract_canon_sha256":"cbbb3206683e5c03f60f8c0860e9dec0e0160d536ca3e6b5f57af31940ba3f95"},"schema_version":"1.0"},"canonical_sha256":"d23d75c63f28cf410a313cd949d725674e3630a504a6869898aae28c8fb1f282","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:04.435554Z","signature_b64":"1h4nF4g6Ihjt1fw+PAqSCu6O0T85N32Ye4NAnJYi8xlqI1xmix2Qzq39Z0BobdQzjpm5RX/jadXpHmRxeDQQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23d75c63f28cf410a313cd949d725674e3630a504a6869898aae28c8fb1f282","last_reissued_at":"2026-07-05T09:54:04.435098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:04.435098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.10197","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"otHjEyU2/DeinT54cCCjBV1RxWZ/w9M9aJc763o5fCAhkC6brVMAoDrPD0pO7K6jRAA/pDOZuQ8BUoFpvoEZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:34:20.063817Z"},"content_sha256":"d8699728a13a88479ad650cd0e6b9ae07f5c4f757bc35e08c039c4844831a550","schema_version":"1.0","event_id":"sha256:d8699728a13a88479ad650cd0e6b9ae07f5c4f757bc35e08c039c4844831a550"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2I6XLRR7FDHUCCRRHTMUTVZFM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Qiong Wu, Weihao Ye, Wenhao Lin, Yiyi Zhou","submitted_at":"2024-09-16T11:43:19Z","abstract_excerpt":"Recent progress in Multimodal Large Language Models(MLLMs) often use large image tokens to compensate the visual shortcoming of MLLMs, which not only exhibits obvious redundancy but also greatly exacerbates the already high computation. Token pruning is an effective solution for speeding up MLLMs, but when and how to drop tokens still remains a challenge. In this paper, we propose a novel and training-free approach for the effective visual token pruning of MLLMs, termed FitPrune, which can quickly produce a complete pruning recipe for MLLMs according to a pre-defined budget. Specifically, FitP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10197","kind":"arxiv","version":2},"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/2409.10197/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":"2026-07-05T09:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkZMxa+Ft7Do0paEacCpLyIi23TiXaQrUvq1JI6l66wF1QmB/buDgw8NDqO8GERUVtjGwLLgmV88L37+TujFAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:34:20.064842Z"},"content_sha256":"936d53b4ee41ebd490f971d6b2e6b17330f1a2ce37feff6705f729f4b05262d6","schema_version":"1.0","event_id":"sha256:936d53b4ee41ebd490f971d6b2e6b17330f1a2ce37feff6705f729f4b05262d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5/bundle.json","state_url":"https://pith.science/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5/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":"2026-08-07T18:34:20Z","links":{"resolver":"https://pith.science/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5","bundle":"https://pith.science/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5/bundle.json","state":"https://pith.science/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2I6XLRR7FDHUCCRRHTMUTVZFM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2I6XLRR7FDHUCCRRHTMUTVZFM5","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":"cbbb3206683e5c03f60f8c0860e9dec0e0160d536ca3e6b5f57af31940ba3f95","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T11:43:19Z","title_canon_sha256":"76c06a23dea201701ecd79fa6243588c6dc4afbe97d41730d4d8cac64a2b1cb6"},"schema_version":"1.0","source":{"id":"2409.10197","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10197","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10197v2","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10197","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"2I6XLRR7FDHU","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"2I6XLRR7FDHUCCRR","created_at":"2026-07-05T09:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"2I6XLRR7","created_at":"2026-07-05T09:54:04Z"}],"graph_snapshots":[{"event_id":"sha256:936d53b4ee41ebd490f971d6b2e6b17330f1a2ce37feff6705f729f4b05262d6","target":"graph","created_at":"2026-07-05T09:54:04Z","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/2409.10197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in Multimodal Large Language Models(MLLMs) often use large image tokens to compensate the visual shortcoming of MLLMs, which not only exhibits obvious redundancy but also greatly exacerbates the already high computation. Token pruning is an effective solution for speeding up MLLMs, but when and how to drop tokens still remains a challenge. In this paper, we propose a novel and training-free approach for the effective visual token pruning of MLLMs, termed FitPrune, which can quickly produce a complete pruning recipe for MLLMs according to a pre-defined budget. Specifically, FitP","authors_text":"Qiong Wu, Weihao Ye, Wenhao Lin, Yiyi Zhou","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T11:43:19Z","title":"Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10197","kind":"arxiv","version":2},"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:d8699728a13a88479ad650cd0e6b9ae07f5c4f757bc35e08c039c4844831a550","target":"record","created_at":"2026-07-05T09:54:04Z","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":"cbbb3206683e5c03f60f8c0860e9dec0e0160d536ca3e6b5f57af31940ba3f95","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-09-16T11:43:19Z","title_canon_sha256":"76c06a23dea201701ecd79fa6243588c6dc4afbe97d41730d4d8cac64a2b1cb6"},"schema_version":"1.0","source":{"id":"2409.10197","kind":"arxiv","version":2}},"canonical_sha256":"d23d75c63f28cf410a313cd949d725674e3630a504a6869898aae28c8fb1f282","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d23d75c63f28cf410a313cd949d725674e3630a504a6869898aae28c8fb1f282","first_computed_at":"2026-07-05T09:54:04.435098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:04.435098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1h4nF4g6Ihjt1fw+PAqSCu6O0T85N32Ye4NAnJYi8xlqI1xmix2Qzq39Z0BobdQzjpm5RX/jadXpHmRxeDQQAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:04.435554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10197","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8699728a13a88479ad650cd0e6b9ae07f5c4f757bc35e08c039c4844831a550","sha256:936d53b4ee41ebd490f971d6b2e6b17330f1a2ce37feff6705f729f4b05262d6"],"state_sha256":"7cc34f5495c42bd0f1b1b3bd7a806267c6aca3eeb7b3d2872bf7cf9013476375"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pzR3DbfCzVzaVbuKSEkbzttrf7xsQLFd7lTpDXFP5KJWXFnl3/z5kARewBv4q8cvA4xZqluIW8kDqW1ThQCOCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:34:20.075042Z","bundle_sha256":"9d7158c614218bbb06361bc7777511c7fcaafce8eb7c0be087377634c7b2117d"}}