{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PF5HXGXMMTHSIOUC6SFWFSF3AG","short_pith_number":"pith:PF5HXGXM","canonical_record":{"source":{"id":"2412.16117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:01:58Z","cross_cats_sorted":[],"title_canon_sha256":"0c6b50853edfe8c2fdadfefcd6e6ccea0d130da1d93e963d59ebedd27f6f57a9","abstract_canon_sha256":"b8599910403b03884b7b68f19b1d7e0c8367e7d7f94695ddf1e9d858deb715a0"},"schema_version":"1.0"},"canonical_sha256":"797a7b9aec64cf243a82f48b62c8bb019d92c0a8a97ed35f8fa5d3cc94e67e28","source":{"kind":"arxiv","id":"2412.16117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16117","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16117v1","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16117","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"PF5HXGXMMTHS","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"PF5HXGXMMTHSIOUC","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"PF5HXGXM","created_at":"2026-07-05T09:52:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PF5HXGXMMTHSIOUC6SFWFSF3AG","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:01:58Z","cross_cats_sorted":[],"title_canon_sha256":"0c6b50853edfe8c2fdadfefcd6e6ccea0d130da1d93e963d59ebedd27f6f57a9","abstract_canon_sha256":"b8599910403b03884b7b68f19b1d7e0c8367e7d7f94695ddf1e9d858deb715a0"},"schema_version":"1.0"},"canonical_sha256":"797a7b9aec64cf243a82f48b62c8bb019d92c0a8a97ed35f8fa5d3cc94e67e28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:35.242180Z","signature_b64":"DOfbWwPhin3n0M0xC85aY/n5TkOMq5aKdehANJtQ8sxHSQ15DyuDggYNxp+9/f5dJ1Tf960b1DjhE8ukPrXSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"797a7b9aec64cf243a82f48b62c8bb019d92c0a8a97ed35f8fa5d3cc94e67e28","last_reissued_at":"2026-07-05T09:52:35.241719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:35.241719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16117","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":"2026-07-05T09:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QXrvPYkyq+70dOtI4GAib3ojz9H+Xqs5/7IWM62t0zLMiCva7WvXYHTt+5tl20cJgO+xWOe3MlEuDnrTaGlPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:57:28.903879Z"},"content_sha256":"a87e5aa99665b96e03e00f726916cfa704ac072737cf1c3eb1dcd2e694a5d217","schema_version":"1.0","event_id":"sha256:a87e5aa99665b96e03e00f726916cfa704ac072737cf1c3eb1dcd2e694a5d217"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PF5HXGXMMTHSIOUC6SFWFSF3AG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PruneVid: Visual Token Pruning for Efficient Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Zhou, Kai Han, Xiaohu Huang","submitted_at":"2024-12-20T18:01:58Z","abstract_excerpt":"In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended capabilities in comprehending visual modalities. However, the substantial redundancy in video data presents significant computational challenges for LLMs. To address this issue, we introduce a training-free method that 1) minimizes video redundancy by merging spatial-temporal tokens, and 2) leverages LLMs' reasoning capabilities to selectively prune visual fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16117","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/2412.16117/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":"2026-07-05T09:52:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfzZ9vjt+44cpV5ZqVvoTnYctj5xuQjOQe+R/k270OD5AT87P51dwryVIHyhfnYtbfMbW9biLj4UgFe9BBplAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:57:28.904439Z"},"content_sha256":"e72b4758cfb6462c5cb757ad6e93d8990166a663819ae6ba5c4f9f33611d7306","schema_version":"1.0","event_id":"sha256:e72b4758cfb6462c5cb757ad6e93d8990166a663819ae6ba5c4f9f33611d7306"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG/bundle.json","state_url":"https://pith.science/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG/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":"2026-08-05T10:57:28Z","links":{"resolver":"https://pith.science/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG","bundle":"https://pith.science/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG/bundle.json","state":"https://pith.science/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PF5HXGXMMTHSIOUC6SFWFSF3AG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PF5HXGXMMTHSIOUC6SFWFSF3AG","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":"b8599910403b03884b7b68f19b1d7e0c8367e7d7f94695ddf1e9d858deb715a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:01:58Z","title_canon_sha256":"0c6b50853edfe8c2fdadfefcd6e6ccea0d130da1d93e963d59ebedd27f6f57a9"},"schema_version":"1.0","source":{"id":"2412.16117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16117","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16117v1","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16117","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"pith_short_12","alias_value":"PF5HXGXMMTHS","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"pith_short_16","alias_value":"PF5HXGXMMTHSIOUC","created_at":"2026-07-05T09:52:35Z"},{"alias_kind":"pith_short_8","alias_value":"PF5HXGXM","created_at":"2026-07-05T09:52:35Z"}],"graph_snapshots":[{"event_id":"sha256:e72b4758cfb6462c5cb757ad6e93d8990166a663819ae6ba5c4f9f33611d7306","target":"graph","created_at":"2026-07-05T09:52:35Z","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/2412.16117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown promising performance in video tasks due to their extended capabilities in comprehending visual modalities. However, the substantial redundancy in video data presents significant computational challenges for LLMs. To address this issue, we introduce a training-free method that 1) minimizes video redundancy by merging spatial-temporal tokens, and 2) leverages LLMs' reasoning capabilities to selectively prune visual fea","authors_text":"Hao Zhou, Kai Han, Xiaohu Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:01:58Z","title":"PruneVid: Visual Token Pruning for Efficient Video Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16117","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:a87e5aa99665b96e03e00f726916cfa704ac072737cf1c3eb1dcd2e694a5d217","target":"record","created_at":"2026-07-05T09:52:35Z","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":"b8599910403b03884b7b68f19b1d7e0c8367e7d7f94695ddf1e9d858deb715a0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:01:58Z","title_canon_sha256":"0c6b50853edfe8c2fdadfefcd6e6ccea0d130da1d93e963d59ebedd27f6f57a9"},"schema_version":"1.0","source":{"id":"2412.16117","kind":"arxiv","version":1}},"canonical_sha256":"797a7b9aec64cf243a82f48b62c8bb019d92c0a8a97ed35f8fa5d3cc94e67e28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"797a7b9aec64cf243a82f48b62c8bb019d92c0a8a97ed35f8fa5d3cc94e67e28","first_computed_at":"2026-07-05T09:52:35.241719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:35.241719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOfbWwPhin3n0M0xC85aY/n5TkOMq5aKdehANJtQ8sxHSQ15DyuDggYNxp+9/f5dJ1Tf960b1DjhE8ukPrXSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:35.242180Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a87e5aa99665b96e03e00f726916cfa704ac072737cf1c3eb1dcd2e694a5d217","sha256:e72b4758cfb6462c5cb757ad6e93d8990166a663819ae6ba5c4f9f33611d7306"],"state_sha256":"d1d179400f807ba5d6fa59755d2a752399a48181f7de7ecc6e077f23c768e517"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRcLofpFzgHBnZQ9wryFjnnV4S4EwyhuNnpk9AJNE53vOkGXvXbxnEHc/q2cRxgbGJT12nXRvjufP4U7H2UpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:57:28.908976Z","bundle_sha256":"25c80bbad7bc8b385cb1875a00d02560678c5bbbb593e968fdd5013bbf749510"}}