{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZQBRYX7EUPOVAEOD3DREWOWRKX","short_pith_number":"pith:ZQBRYX7E","canonical_record":{"source":{"id":"2605.22078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T07:16:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a2696476a12360c300a3bcccbb3d52bfabf404c6628e9107f2ff9d539ba10a23","abstract_canon_sha256":"031c64d9aaa17d17220b7886b9568429e849ad3b9271d30535a8c50523ca1b66"},"schema_version":"1.0"},"canonical_sha256":"cc031c5fe4a3dd5011c3d8e24b3ad155f1b6453ca07fe56eaf0eb5c2086dd134","source":{"kind":"arxiv","id":"2605.22078","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22078","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22078v1","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22078","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZQBRYX7EUPOV","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZQBRYX7EUPOVAEOD","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZQBRYX7E","created_at":"2026-05-22T01:04:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZQBRYX7EUPOVAEOD3DREWOWRKX","target":"record","payload":{"canonical_record":{"source":{"id":"2605.22078","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T07:16:45Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a2696476a12360c300a3bcccbb3d52bfabf404c6628e9107f2ff9d539ba10a23","abstract_canon_sha256":"031c64d9aaa17d17220b7886b9568429e849ad3b9271d30535a8c50523ca1b66"},"schema_version":"1.0"},"canonical_sha256":"cc031c5fe4a3dd5011c3d8e24b3ad155f1b6453ca07fe56eaf0eb5c2086dd134","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:24.098925Z","signature_b64":"3RwZCVkiVfQU/MXSWiYg7Nq8+VhUMx+AIc8R3Fn35SXsXe7rrJD4fYkKySUJRlUWBbUjXRR2V0jhFJcBgO+vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc031c5fe4a3dd5011c3d8e24b3ad155f1b6453ca07fe56eaf0eb5c2086dd134","last_reissued_at":"2026-05-22T01:04:24.098044Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:24.098044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.22078","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":"2026-05-22T01:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DReDNnkgTZAV9fms2R4br4Jga2p3lH3PZi/ZjLom+1hYHiEv1MnnYS6CW7APoTsD+o5Z6rhAEGMjOeA6p63RBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T14:24:11.340065Z"},"content_sha256":"aff487167c002ec21cc23bd70938c9bfce48e2f25534dd7381aa3b6d42142a8a","schema_version":"1.0","event_id":"sha256:aff487167c002ec21cc23bd70938c9bfce48e2f25534dd7381aa3b6d42142a8a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZQBRYX7EUPOVAEOD3DREWOWRKX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Bingjun Luo, Hanqi Chen, Tony Wang, Xinpeng Ding","submitted_at":"2026-05-21T07:16:45Z","abstract_excerpt":"Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens while preserving spatiotemporal interactions. Existing methods, such as LLaVA family, utilize simplistic pooling or interpolation techniques that overlook the intricate dynamics of visual tokens. To bridge this gap, we propose ST-GridPool, a novel training-free visual token enhancement method designed specifically for Video LLMs. Our approach integrates Pyramid Temporal Gridding (PTG), which captures multi-grained spat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22078","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/2605.22078/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":"2026-05-22T01:04:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VmheepfVm/rffhBSP9OEZOemfPckCiRdd/8lg5VGtZqAKUVtRIDG9xMN9X/YMM3mMhdQOsnFWNyXWPYK0YgWCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T14:24:11.340835Z"},"content_sha256":"8e413ffb803e3485674489bec4bde35cdaff924c0e06a95a5439a8b854589865","schema_version":"1.0","event_id":"sha256:8e413ffb803e3485674489bec4bde35cdaff924c0e06a95a5439a8b854589865"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX/bundle.json","state_url":"https://pith.science/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX/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":"2026-05-24T14:24:11Z","links":{"resolver":"https://pith.science/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX","bundle":"https://pith.science/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX/bundle.json","state":"https://pith.science/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZQBRYX7EUPOVAEOD3DREWOWRKX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZQBRYX7EUPOVAEOD3DREWOWRKX","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":"031c64d9aaa17d17220b7886b9568429e849ad3b9271d30535a8c50523ca1b66","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T07:16:45Z","title_canon_sha256":"a2696476a12360c300a3bcccbb3d52bfabf404c6628e9107f2ff9d539ba10a23"},"schema_version":"1.0","source":{"id":"2605.22078","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.22078","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.22078v1","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22078","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_12","alias_value":"ZQBRYX7EUPOV","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_16","alias_value":"ZQBRYX7EUPOVAEOD","created_at":"2026-05-22T01:04:24Z"},{"alias_kind":"pith_short_8","alias_value":"ZQBRYX7E","created_at":"2026-05-22T01:04:24Z"}],"graph_snapshots":[{"event_id":"sha256:8e413ffb803e3485674489bec4bde35cdaff924c0e06a95a5439a8b854589865","target":"graph","created_at":"2026-05-22T01:04:24Z","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/2605.22078/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens while preserving spatiotemporal interactions. Existing methods, such as LLaVA family, utilize simplistic pooling or interpolation techniques that overlook the intricate dynamics of visual tokens. To bridge this gap, we propose ST-GridPool, a novel training-free visual token enhancement method designed specifically for Video LLMs. Our approach integrates Pyramid Temporal Gridding (PTG), which captures multi-grained spat","authors_text":"Bingjun Luo, Hanqi Chen, Tony Wang, Xinpeng Ding","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T07:16:45Z","title":"Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22078","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:aff487167c002ec21cc23bd70938c9bfce48e2f25534dd7381aa3b6d42142a8a","target":"record","created_at":"2026-05-22T01:04:24Z","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":"031c64d9aaa17d17220b7886b9568429e849ad3b9271d30535a8c50523ca1b66","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-21T07:16:45Z","title_canon_sha256":"a2696476a12360c300a3bcccbb3d52bfabf404c6628e9107f2ff9d539ba10a23"},"schema_version":"1.0","source":{"id":"2605.22078","kind":"arxiv","version":1}},"canonical_sha256":"cc031c5fe4a3dd5011c3d8e24b3ad155f1b6453ca07fe56eaf0eb5c2086dd134","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc031c5fe4a3dd5011c3d8e24b3ad155f1b6453ca07fe56eaf0eb5c2086dd134","first_computed_at":"2026-05-22T01:04:24.098044Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:24.098044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3RwZCVkiVfQU/MXSWiYg7Nq8+VhUMx+AIc8R3Fn35SXsXe7rrJD4fYkKySUJRlUWBbUjXRR2V0jhFJcBgO+vDA==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:24.098925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.22078","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aff487167c002ec21cc23bd70938c9bfce48e2f25534dd7381aa3b6d42142a8a","sha256:8e413ffb803e3485674489bec4bde35cdaff924c0e06a95a5439a8b854589865"],"state_sha256":"2f6b4a90d3a19a1d3117fb060c445d35da6c25aaef5bc066d3426cabecd0f027"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mYOotqPKBtk1yJXccBRFLiZW50qZaCZO1Pr5Oek1GkoT29kmeJhrtsiKfE5ZfwZ2PfOSbSrUAi7P8tCWe4qzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T14:24:11.344199Z","bundle_sha256":"e4dec09afafc35a47b2ca8bbbabf885c0ae6dbb2adf00fcc22af87aeb6427e04"}}