{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C2EGESCAI6L7QY3G5PBXTA4IVY","short_pith_number":"pith:C2EGESCA","canonical_record":{"source":{"id":"2411.14228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T15:37:52Z","cross_cats_sorted":[],"title_canon_sha256":"ac27116020bbc6799248e599d415968b091ec451902437987779f00e90b581f9","abstract_canon_sha256":"381edb0ef50c4ba506e02691cc0bb645ccc3271601bc1b58e78a45224a7739a5"},"schema_version":"1.0"},"canonical_sha256":"16886248404797f86366ebc3798388ae12acb84d5347aed26710cde9a5f5d240","source":{"kind":"arxiv","id":"2411.14228","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14228","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14228v1","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14228","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"C2EGESCAI6L7","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"C2EGESCAI6L7QY3G","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"C2EGESCA","created_at":"2026-07-05T09:38:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C2EGESCAI6L7QY3G5PBXTA4IVY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T15:37:52Z","cross_cats_sorted":[],"title_canon_sha256":"ac27116020bbc6799248e599d415968b091ec451902437987779f00e90b581f9","abstract_canon_sha256":"381edb0ef50c4ba506e02691cc0bb645ccc3271601bc1b58e78a45224a7739a5"},"schema_version":"1.0"},"canonical_sha256":"16886248404797f86366ebc3798388ae12acb84d5347aed26710cde9a5f5d240","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:43.737537Z","signature_b64":"HrCdWdDNNcYZ4u5SzTbGjo7vuCRv2DuJ1VX4rBMipmNX1kByakIIVaZ5mzOExft8Bx+7/2DHe7WOma/XGtY6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16886248404797f86366ebc3798388ae12acb84d5347aed26710cde9a5f5d240","last_reissued_at":"2026-07-05T09:38:43.737009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:43.737009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14228","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":"2026-07-05T09:38:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RWkMju4yESzivdF3i2Ysk05KEqsdHAA1jq+4xRsxNGz8Fo7qCWgCDWdNs+vzLXP7BxRDcvuvP87WFKTACxV6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:32:31.589714Z"},"content_sha256":"1069fa91a5bda181aff694e8129295785b34d2c1ad234bd0c548cc97ac6f5302","schema_version":"1.0","event_id":"sha256:1069fa91a5bda181aff694e8129295785b34d2c1ad234bd0c548cc97ac6f5302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C2EGESCAI6L7QY3G5PBXTA4IVY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Chi Xie, Sheng Guo, Shuang Liang, Yuke Zhu","submitted_at":"2024-11-21T15:37:52Z","abstract_excerpt":"Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in the number of visual tokens input into LLMs, resulting in significant computational costs. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We argue that removing visual redundancy can simultaneously improve both efficiency and performance. We build a coarse-to-fine visual token comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14228","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/2411.14228/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":"2026-07-05T09:38:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hd3nh87xiMLGpGV0fYJPJ9c2Nl1ut2zzQCSugSH0BR7vgJ05wCBsUcHoe/92lEYl0mPkYq/4Y4CPMUQfC+DqDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:32:31.590241Z"},"content_sha256":"e44cf8f6b67fd8b5399a07a241082efa8eb270c6f5fde38a5332e4be994425c2","schema_version":"1.0","event_id":"sha256:e44cf8f6b67fd8b5399a07a241082efa8eb270c6f5fde38a5332e4be994425c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2EGESCAI6L7QY3G5PBXTA4IVY/bundle.json","state_url":"https://pith.science/pith/C2EGESCAI6L7QY3G5PBXTA4IVY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2EGESCAI6L7QY3G5PBXTA4IVY/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":"2026-08-09T06:32:31Z","links":{"resolver":"https://pith.science/pith/C2EGESCAI6L7QY3G5PBXTA4IVY","bundle":"https://pith.science/pith/C2EGESCAI6L7QY3G5PBXTA4IVY/bundle.json","state":"https://pith.science/pith/C2EGESCAI6L7QY3G5PBXTA4IVY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2EGESCAI6L7QY3G5PBXTA4IVY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C2EGESCAI6L7QY3G5PBXTA4IVY","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":"381edb0ef50c4ba506e02691cc0bb645ccc3271601bc1b58e78a45224a7739a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T15:37:52Z","title_canon_sha256":"ac27116020bbc6799248e599d415968b091ec451902437987779f00e90b581f9"},"schema_version":"1.0","source":{"id":"2411.14228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14228","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14228v1","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14228","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_12","alias_value":"C2EGESCAI6L7","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_16","alias_value":"C2EGESCAI6L7QY3G","created_at":"2026-07-05T09:38:43Z"},{"alias_kind":"pith_short_8","alias_value":"C2EGESCA","created_at":"2026-07-05T09:38:43Z"}],"graph_snapshots":[{"event_id":"sha256:e44cf8f6b67fd8b5399a07a241082efa8eb270c6f5fde38a5332e4be994425c2","target":"graph","created_at":"2026-07-05T09:38:43Z","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/2411.14228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in the number of visual tokens input into LLMs, resulting in significant computational costs. Current work develop visual token compression methods to achieve efficiency improvements, often at the expense of performance. We argue that removing visual redundancy can simultaneously improve both efficiency and performance. We build a coarse-to-fine visual token comp","authors_text":"Bo Zheng, Chi Xie, Sheng Guo, Shuang Liang, Yuke Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T15:37:52Z","title":"FocusLLaVA: A Coarse-to-Fine Approach for Efficient and Effective Visual Token Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14228","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":"sha256:1069fa91a5bda181aff694e8129295785b34d2c1ad234bd0c548cc97ac6f5302","target":"record","created_at":"2026-07-05T09:38:43Z","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":"381edb0ef50c4ba506e02691cc0bb645ccc3271601bc1b58e78a45224a7739a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T15:37:52Z","title_canon_sha256":"ac27116020bbc6799248e599d415968b091ec451902437987779f00e90b581f9"},"schema_version":"1.0","source":{"id":"2411.14228","kind":"arxiv","version":1}},"canonical_sha256":"16886248404797f86366ebc3798388ae12acb84d5347aed26710cde9a5f5d240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16886248404797f86366ebc3798388ae12acb84d5347aed26710cde9a5f5d240","first_computed_at":"2026-07-05T09:38:43.737009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:43.737009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HrCdWdDNNcYZ4u5SzTbGjo7vuCRv2DuJ1VX4rBMipmNX1kByakIIVaZ5mzOExft8Bx+7/2DHe7WOma/XGtY6Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:43.737537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1069fa91a5bda181aff694e8129295785b34d2c1ad234bd0c548cc97ac6f5302","sha256:e44cf8f6b67fd8b5399a07a241082efa8eb270c6f5fde38a5332e4be994425c2"],"state_sha256":"42be9b7ffa97a8b2dee442396fc60281661f678c1f9d37cb75fcfa3c62e89fb9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jz8MePQgP6a5jrW65l0Sunf5AAn8PxzbWBgthcKXGzOdcHFIdcIvW1mtYHTEKmP7sqoQUHmkhEdtYvWEiGjvDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:32:31.594577Z","bundle_sha256":"77ee5a0e9a2fd970d5901b7aaae5f21fc7c01c87f42b71b67ef9be244b44f3c5"}}