{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VPRXSAHJS67JVL6LODPAEFJKHC","short_pith_number":"pith:VPRXSAHJ","canonical_record":{"source":{"id":"2607.28463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:23:10Z","cross_cats_sorted":[],"title_canon_sha256":"83f2559c126ffdd06a66d5ee75feb4994951f6a98f5ddde0333e40645ce6cd7b","abstract_canon_sha256":"0fc3c44bf2388a2b047e5d17cdb6e7b1896be5962154a612764374e451956537"},"schema_version":"1.0"},"canonical_sha256":"abe37900e997be9aafcb70de02152a388a9e1169264857448c5bf4e5886df9bc","source":{"kind":"arxiv","id":"2607.28463","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28463","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28463v1","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28463","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"pith_short_12","alias_value":"VPRXSAHJS67J","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"pith_short_16","alias_value":"VPRXSAHJS67JVL6L","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"pith_short_8","alias_value":"VPRXSAHJ","created_at":"2026-07-31T01:37:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VPRXSAHJS67JVL6LODPAEFJKHC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.28463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:23:10Z","cross_cats_sorted":[],"title_canon_sha256":"83f2559c126ffdd06a66d5ee75feb4994951f6a98f5ddde0333e40645ce6cd7b","abstract_canon_sha256":"0fc3c44bf2388a2b047e5d17cdb6e7b1896be5962154a612764374e451956537"},"schema_version":"1.0"},"canonical_sha256":"abe37900e997be9aafcb70de02152a388a9e1169264857448c5bf4e5886df9bc","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abe37900e997be9aafcb70de02152a388a9e1169264857448c5bf4e5886df9bc","last_reissued_at":"2026-07-31T01:37:46.949297Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:37:46.949297Z"},"source_kind":"arxiv","source_id":"2607.28463","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":"2026-07-31T01:37:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4XPiOoTUEqaUK+h8Ns1DpbcBjFKYMasVdjGSqCh9gonqTpYIUnyzy/FDV2M/TKquLBd/t7O7vKJFslmjjsYtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:56:18.514339Z"},"content_sha256":"330d3e43bec26bf151a0a3948543d4a1520aee5fc0c58e2067c4a7e15f717a7e","schema_version":"1.0","event_id":"sha256:330d3e43bec26bf151a0a3948543d4a1520aee5fc0c58e2067c4a7e15f717a7e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VPRXSAHJS67JVL6LODPAEFJKHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Duo Peng, Guoqing Wang, Haiyue Zhang, Heng Tao Shen, Xun Jiang, Yang Yang, Yi Bin, Zeyu Ma","submitted_at":"2026-07-30T16:23:10Z","abstract_excerpt":"Large vision-language models (LVLMs) have achieved significant progress in video understanding, yet understanding long videos remains challenging due to the large number of visual tokens and limited context windows. Visual sampling provides a practical solution by selecting an informative subset of frames. However, existing methods typically either rely on relevance-aware sampling, leading to redundant frame selection and insufficient temporal coverage, or adopt a fixed sampling strategy regardless of query type. In this paper, we propose VisualRouter, a training-free and plug-and-play framewo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28463","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/2607.28463/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":"2026-07-31T01:37:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mcpL22l33v+GhyTQHnUpUitLTfBdlujkdgaDKCxbr44z4Z9x9gbG8/Sx0d+/Hc/5O7j38wS4zZUlvDRCTHtmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:56:18.514875Z"},"content_sha256":"ffcba4ceb651c473bf60313cffd7164ed0f69847ad8abd4142dfafd807a08e98","schema_version":"1.0","event_id":"sha256:ffcba4ceb651c473bf60313cffd7164ed0f69847ad8abd4142dfafd807a08e98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VPRXSAHJS67JVL6LODPAEFJKHC/bundle.json","state_url":"https://pith.science/pith/VPRXSAHJS67JVL6LODPAEFJKHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VPRXSAHJS67JVL6LODPAEFJKHC/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":"2026-08-04T22:56:18Z","links":{"resolver":"https://pith.science/pith/VPRXSAHJS67JVL6LODPAEFJKHC","bundle":"https://pith.science/pith/VPRXSAHJS67JVL6LODPAEFJKHC/bundle.json","state":"https://pith.science/pith/VPRXSAHJS67JVL6LODPAEFJKHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VPRXSAHJS67JVL6LODPAEFJKHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VPRXSAHJS67JVL6LODPAEFJKHC","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":"0fc3c44bf2388a2b047e5d17cdb6e7b1896be5962154a612764374e451956537","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:23:10Z","title_canon_sha256":"83f2559c126ffdd06a66d5ee75feb4994951f6a98f5ddde0333e40645ce6cd7b"},"schema_version":"1.0","source":{"id":"2607.28463","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28463","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28463v1","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28463","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"pith_short_12","alias_value":"VPRXSAHJS67J","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"pith_short_16","alias_value":"VPRXSAHJS67JVL6L","created_at":"2026-07-31T01:37:46Z"},{"alias_kind":"pith_short_8","alias_value":"VPRXSAHJ","created_at":"2026-07-31T01:37:46Z"}],"graph_snapshots":[{"event_id":"sha256:ffcba4ceb651c473bf60313cffd7164ed0f69847ad8abd4142dfafd807a08e98","target":"graph","created_at":"2026-07-31T01:37:46Z","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/2607.28463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models (LVLMs) have achieved significant progress in video understanding, yet understanding long videos remains challenging due to the large number of visual tokens and limited context windows. Visual sampling provides a practical solution by selecting an informative subset of frames. However, existing methods typically either rely on relevance-aware sampling, leading to redundant frame selection and insufficient temporal coverage, or adopt a fixed sampling strategy regardless of query type. In this paper, we propose VisualRouter, a training-free and plug-and-play framewo","authors_text":"Duo Peng, Guoqing Wang, Haiyue Zhang, Heng Tao Shen, Xun Jiang, Yang Yang, Yi Bin, Zeyu Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:23:10Z","title":"VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28463","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":"sha256:330d3e43bec26bf151a0a3948543d4a1520aee5fc0c58e2067c4a7e15f717a7e","target":"record","created_at":"2026-07-31T01:37:46Z","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":"0fc3c44bf2388a2b047e5d17cdb6e7b1896be5962154a612764374e451956537","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-30T16:23:10Z","title_canon_sha256":"83f2559c126ffdd06a66d5ee75feb4994951f6a98f5ddde0333e40645ce6cd7b"},"schema_version":"1.0","source":{"id":"2607.28463","kind":"arxiv","version":1}},"canonical_sha256":"abe37900e997be9aafcb70de02152a388a9e1169264857448c5bf4e5886df9bc","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abe37900e997be9aafcb70de02152a388a9e1169264857448c5bf4e5886df9bc","first_computed_at":"2026-07-31T01:37:46.949297Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:37:46.949297Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28463","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:330d3e43bec26bf151a0a3948543d4a1520aee5fc0c58e2067c4a7e15f717a7e","sha256:ffcba4ceb651c473bf60313cffd7164ed0f69847ad8abd4142dfafd807a08e98"],"state_sha256":"16617abc92ed808979e0a2535c36e7898f3b7b67e41142ab4e4e6fcd15e25881"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ctiTcyIl75/XnaFHy7Dyt5N2RR+a8G/iXA+eFeJYtNQ9SyrBg64lYlIApYtT4HBQVMKUoIh56AzvS89mhYvICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:56:18.520683Z","bundle_sha256":"b52c82f6ec08bcf59ca07f92540c3e2b0922b0c89303038e7c55a4620c0ad9d9"}}