{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XMX5WBD52DCW2K3RO6FY6Q5TEB","short_pith_number":"pith:XMX5WBD5","canonical_record":{"source":{"id":"2407.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T16:11:15Z","cross_cats_sorted":[],"title_canon_sha256":"ded96a4b7154128c8234cd18ce843db199c38aba569557137599debfe568d809","abstract_canon_sha256":"b590f8dad78d60b8a4b48791d58f193ba4e4bdce2b94b4ac241c52f7b183332d"},"schema_version":"1.0"},"canonical_sha256":"bb2fdb047dd0c56d2b71778b8f43b320640b0db839f0653d1c03ddfa7f5cb839","source":{"kind":"arxiv","id":"2407.14439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14439","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14439v1","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14439","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"XMX5WBD52DCW","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"XMX5WBD52DCW2K3R","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"XMX5WBD5","created_at":"2026-07-05T08:46:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XMX5WBD52DCW2K3RO6FY6Q5TEB","target":"record","payload":{"canonical_record":{"source":{"id":"2407.14439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T16:11:15Z","cross_cats_sorted":[],"title_canon_sha256":"ded96a4b7154128c8234cd18ce843db199c38aba569557137599debfe568d809","abstract_canon_sha256":"b590f8dad78d60b8a4b48791d58f193ba4e4bdce2b94b4ac241c52f7b183332d"},"schema_version":"1.0"},"canonical_sha256":"bb2fdb047dd0c56d2b71778b8f43b320640b0db839f0653d1c03ddfa7f5cb839","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:12.745136Z","signature_b64":"cbwoOmiBbxJ+KCDYlJUJ6EldRX+f4P1a3hHFjLe6GSTtOXezM41bjhwl0TejGxg39gFgE2UxOXQdtDuwPg/3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb2fdb047dd0c56d2b71778b8f43b320640b0db839f0653d1c03ddfa7f5cb839","last_reissued_at":"2026-07-05T08:46:12.744666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:12.744666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.14439","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":"2026-07-05T08:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6sboUV+gZszcC8R4Imqd18Pv/rQpotIPWieE6DuTVmi6rXniTdHkWKdgT/2HiIIyWqylEyFPFTZqkXs3H4sBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:34:15.952627Z"},"content_sha256":"314d07eee4f7ec2123c69894a856da6324951515b15b3bc2c689475dadb44b58","schema_version":"1.0","event_id":"sha256:314d07eee4f7ec2123c69894a856da6324951515b15b3bc2c689475dadb44b58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XMX5WBD52DCW2K3RO6FY6Q5TEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gongwei Chen, Liqiang Nie, Renshan Zhang, Rui Shao, Weili Guan, Yibo Lyu","submitted_at":"2024-07-19T16:11:15Z","abstract_excerpt":"Cropping high-resolution document images into multiple sub-images is the most widely used approach for current Multimodal Large Language Models (MLLMs) to do document understanding. Most of current document understanding methods preserve all tokens within sub-images and treat them equally. This neglects their different informativeness and leads to a significant increase in the number of image tokens. To perform a more adaptive and efficient document understanding, we propose Token-level Correlation-guided Compression, a parameter-free and plug-and-play methodology to optimize token processing."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14439","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/2407.14439/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":"2026-07-05T08:46:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M9BoGC7oPdNr9OCwMkAn4b4rmLiwHCLNZjVHt9V3pW0j3Z/UmX1+r7+DZ0+6f8BS7b6I0e9XoPGpjG9EWECsAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T21:34:15.953204Z"},"content_sha256":"3a13622c712e604797bb2ba49a57bca15cb2ca6db598a5480952772fe8ae4ac6","schema_version":"1.0","event_id":"sha256:3a13622c712e604797bb2ba49a57bca15cb2ca6db598a5480952772fe8ae4ac6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB/bundle.json","state_url":"https://pith.science/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB/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":"2026-08-08T21:34:15Z","links":{"resolver":"https://pith.science/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB","bundle":"https://pith.science/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB/bundle.json","state":"https://pith.science/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMX5WBD52DCW2K3RO6FY6Q5TEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XMX5WBD52DCW2K3RO6FY6Q5TEB","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":"b590f8dad78d60b8a4b48791d58f193ba4e4bdce2b94b4ac241c52f7b183332d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T16:11:15Z","title_canon_sha256":"ded96a4b7154128c8234cd18ce843db199c38aba569557137599debfe568d809"},"schema_version":"1.0","source":{"id":"2407.14439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.14439","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.14439v1","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14439","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"pith_short_12","alias_value":"XMX5WBD52DCW","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"pith_short_16","alias_value":"XMX5WBD52DCW2K3R","created_at":"2026-07-05T08:46:12Z"},{"alias_kind":"pith_short_8","alias_value":"XMX5WBD5","created_at":"2026-07-05T08:46:12Z"}],"graph_snapshots":[{"event_id":"sha256:3a13622c712e604797bb2ba49a57bca15cb2ca6db598a5480952772fe8ae4ac6","target":"graph","created_at":"2026-07-05T08:46:12Z","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/2407.14439/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cropping high-resolution document images into multiple sub-images is the most widely used approach for current Multimodal Large Language Models (MLLMs) to do document understanding. Most of current document understanding methods preserve all tokens within sub-images and treat them equally. This neglects their different informativeness and leads to a significant increase in the number of image tokens. To perform a more adaptive and efficient document understanding, we propose Token-level Correlation-guided Compression, a parameter-free and plug-and-play methodology to optimize token processing.","authors_text":"Gongwei Chen, Liqiang Nie, Renshan Zhang, Rui Shao, Weili Guan, Yibo Lyu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T16:11:15Z","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14439","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":"sha256:314d07eee4f7ec2123c69894a856da6324951515b15b3bc2c689475dadb44b58","target":"record","created_at":"2026-07-05T08:46:12Z","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":"b590f8dad78d60b8a4b48791d58f193ba4e4bdce2b94b4ac241c52f7b183332d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T16:11:15Z","title_canon_sha256":"ded96a4b7154128c8234cd18ce843db199c38aba569557137599debfe568d809"},"schema_version":"1.0","source":{"id":"2407.14439","kind":"arxiv","version":1}},"canonical_sha256":"bb2fdb047dd0c56d2b71778b8f43b320640b0db839f0653d1c03ddfa7f5cb839","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb2fdb047dd0c56d2b71778b8f43b320640b0db839f0653d1c03ddfa7f5cb839","first_computed_at":"2026-07-05T08:46:12.744666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:12.744666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cbwoOmiBbxJ+KCDYlJUJ6EldRX+f4P1a3hHFjLe6GSTtOXezM41bjhwl0TejGxg39gFgE2UxOXQdtDuwPg/3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:12.745136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.14439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:314d07eee4f7ec2123c69894a856da6324951515b15b3bc2c689475dadb44b58","sha256:3a13622c712e604797bb2ba49a57bca15cb2ca6db598a5480952772fe8ae4ac6"],"state_sha256":"610d45556a34e89cd12d40f67200817508c04877f0a0e49cb8b74b4e6604233c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MJhBfAQ06QUeowXBX3/zii6HC0fcmvbTh5PWgIyaqr3YAysp138REKwKfMvddoATsXbvxY3eDRg92DXsWoykBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T21:34:15.957842Z","bundle_sha256":"31b0730a9ee109fc62181b87f5e201d455f8a37c9e08c220fa234759ac41cb3e"}}