{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C63I6HX6STBY6BESHFP64WDARH","short_pith_number":"pith:C63I6HX6","canonical_record":{"source":{"id":"2504.04024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-05T02:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"64a616526519c61e08e98477703035cb472b1f18254a03a65b9ade3647c8c5a6","abstract_canon_sha256":"50f2e1cc73e8ddf8a00c16ba0440ad2b548a71c323c737e0c5b94fd630a18cb5"},"schema_version":"1.0"},"canonical_sha256":"17b68f1efe94c38f0492395fee586089d95b69d2c32612e7f7fe6501f1575f85","source":{"kind":"arxiv","id":"2504.04024","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04024","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04024v1","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04024","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"C63I6HX6STBY","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"C63I6HX6STBY6BES","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"C63I6HX6","created_at":"2026-07-05T10:44:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C63I6HX6STBY6BESHFP64WDARH","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04024","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-05T02:32:58Z","cross_cats_sorted":[],"title_canon_sha256":"64a616526519c61e08e98477703035cb472b1f18254a03a65b9ade3647c8c5a6","abstract_canon_sha256":"50f2e1cc73e8ddf8a00c16ba0440ad2b548a71c323c737e0c5b94fd630a18cb5"},"schema_version":"1.0"},"canonical_sha256":"17b68f1efe94c38f0492395fee586089d95b69d2c32612e7f7fe6501f1575f85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:53.104254Z","signature_b64":"JgpDUoh1TiR+cG0tIlIO77YfRMMqJ1B1j0UW4bhi1XNJexEak6V+BQdlPyVCAQU+CdZ600u0rqYNXZ0STjtcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17b68f1efe94c38f0492395fee586089d95b69d2c32612e7f7fe6501f1575f85","last_reissued_at":"2026-07-05T10:44:53.103765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:53.103765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04024","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":"2026-07-05T10:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tDb+m/vL+QtzjQRlPGeBodN7wNnTch2g02zsV87xMHKamzrosiFPWOKRGS6IsVrTSzHWTk/wpyVexHBuAAdeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:58:26.691497Z"},"content_sha256":"342687d7c41d8d6de140960f7d1efd7fc50d8df2271694e92850089ccea8aa90","schema_version":"1.0","event_id":"sha256:342687d7c41d8d6de140960f7d1efd7fc50d8df2271694e92850089ccea8aa90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C63I6HX6STBY6BESHFP64WDARH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Window Token Concatenation for Efficient Visual Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Botao Ye, Huan Liu, Tianlong Chen, Wentao Bao, Yifan Li, Yu Kong, Zhen Tan","submitted_at":"2025-04-05T02:32:58Z","abstract_excerpt":"To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens. However, directly concatenating these tokens may group diverse tokens into one, and thus obscure some fine details. To address this challenge, we propose fine-tuning the last few layers of the vision encoder to adaptively adjust the visual tokens, encouraging that those within the same window exhibit similar features. To further enhance the performance on f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04024","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/2504.04024/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":"2026-07-05T10:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SiPuH/m5BI/xH4elL3EEjBGl5nJ/bx7vQr09h+CG5vJgUyYVGTHmiGpnXLw19QGZosjO/FW5llL2PsKmYZkhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:58:26.691864Z"},"content_sha256":"c887d867ca3ec002595324035586c73c24ac55a62a1528b52cd5f04fb40dc322","schema_version":"1.0","event_id":"sha256:c887d867ca3ec002595324035586c73c24ac55a62a1528b52cd5f04fb40dc322"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C63I6HX6STBY6BESHFP64WDARH/bundle.json","state_url":"https://pith.science/pith/C63I6HX6STBY6BESHFP64WDARH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C63I6HX6STBY6BESHFP64WDARH/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":"2026-07-07T08:58:26Z","links":{"resolver":"https://pith.science/pith/C63I6HX6STBY6BESHFP64WDARH","bundle":"https://pith.science/pith/C63I6HX6STBY6BESHFP64WDARH/bundle.json","state":"https://pith.science/pith/C63I6HX6STBY6BESHFP64WDARH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C63I6HX6STBY6BESHFP64WDARH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C63I6HX6STBY6BESHFP64WDARH","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":"50f2e1cc73e8ddf8a00c16ba0440ad2b548a71c323c737e0c5b94fd630a18cb5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-05T02:32:58Z","title_canon_sha256":"64a616526519c61e08e98477703035cb472b1f18254a03a65b9ade3647c8c5a6"},"schema_version":"1.0","source":{"id":"2504.04024","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04024","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04024v1","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04024","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"C63I6HX6STBY","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"C63I6HX6STBY6BES","created_at":"2026-07-05T10:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"C63I6HX6","created_at":"2026-07-05T10:44:53Z"}],"graph_snapshots":[{"event_id":"sha256:c887d867ca3ec002595324035586c73c24ac55a62a1528b52cd5f04fb40dc322","target":"graph","created_at":"2026-07-05T10:44:53Z","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/2504.04024/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To effectively reduce the visual tokens in Visual Large Language Models (VLLMs), we propose a novel approach called Window Token Concatenation (WiCo). Specifically, we employ a sliding window to concatenate spatially adjacent visual tokens. However, directly concatenating these tokens may group diverse tokens into one, and thus obscure some fine details. To address this challenge, we propose fine-tuning the last few layers of the vision encoder to adaptively adjust the visual tokens, encouraging that those within the same window exhibit similar features. To further enhance the performance on f","authors_text":"Botao Ye, Huan Liu, Tianlong Chen, Wentao Bao, Yifan Li, Yu Kong, Zhen Tan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-05T02:32:58Z","title":"Window Token Concatenation for Efficient Visual Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04024","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":"sha256:342687d7c41d8d6de140960f7d1efd7fc50d8df2271694e92850089ccea8aa90","target":"record","created_at":"2026-07-05T10:44:53Z","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":"50f2e1cc73e8ddf8a00c16ba0440ad2b548a71c323c737e0c5b94fd630a18cb5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-05T02:32:58Z","title_canon_sha256":"64a616526519c61e08e98477703035cb472b1f18254a03a65b9ade3647c8c5a6"},"schema_version":"1.0","source":{"id":"2504.04024","kind":"arxiv","version":1}},"canonical_sha256":"17b68f1efe94c38f0492395fee586089d95b69d2c32612e7f7fe6501f1575f85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17b68f1efe94c38f0492395fee586089d95b69d2c32612e7f7fe6501f1575f85","first_computed_at":"2026-07-05T10:44:53.103765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:53.103765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JgpDUoh1TiR+cG0tIlIO77YfRMMqJ1B1j0UW4bhi1XNJexEak6V+BQdlPyVCAQU+CdZ600u0rqYNXZ0STjtcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:53.104254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04024","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:342687d7c41d8d6de140960f7d1efd7fc50d8df2271694e92850089ccea8aa90","sha256:c887d867ca3ec002595324035586c73c24ac55a62a1528b52cd5f04fb40dc322"],"state_sha256":"ac7a51673a35ea657ad50c2003d1f1cc61caa0cabc2aa74c370eadcfbfb4484d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/TSJGcqQ0IKw5AIfOYhnq4MFnEh36CbBSOmnVWZu8S98MsYlS4YIvvclxTq3WKSNeshcM411RvZvB7wcrc3TBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:58:26.693711Z","bundle_sha256":"d499968c328860aef98660b8108d93e4f0603219141887aaa5b4bddd5a66cb96"}}