{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WUMMBWJRE6ZRFRT7L6RQSGE7KG","short_pith_number":"pith:WUMMBWJR","canonical_record":{"source":{"id":"2506.22139","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T11:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"b1ac7835809bad633fe33c7cb9c0d09f357c4ee2c63d4599740babca4fbd0c8f","abstract_canon_sha256":"d97803d793f4fb739dd8cfb49ce34838650cb302307e28377e1aa6ff5c986f43"},"schema_version":"1.0"},"canonical_sha256":"b518c0d93127b312c67f5fa309189f519b7e99d121182957cf8d5acd88d9de8c","source":{"kind":"arxiv","id":"2506.22139","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22139","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22139v3","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22139","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"WUMMBWJRE6ZR","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"WUMMBWJRE6ZRFRT7","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"WUMMBWJR","created_at":"2026-07-05T11:40:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WUMMBWJRE6ZRFRT7L6RQSGE7KG","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22139","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T11:30:51Z","cross_cats_sorted":[],"title_canon_sha256":"b1ac7835809bad633fe33c7cb9c0d09f357c4ee2c63d4599740babca4fbd0c8f","abstract_canon_sha256":"d97803d793f4fb739dd8cfb49ce34838650cb302307e28377e1aa6ff5c986f43"},"schema_version":"1.0"},"canonical_sha256":"b518c0d93127b312c67f5fa309189f519b7e99d121182957cf8d5acd88d9de8c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:55.554090Z","signature_b64":"o4JFEZ4RNiMaEEW4NYjRraM9sVDmMr6jj44mC4re+ev9j+9YS7uMb1wAO8TBC07+6uPRutn9pjPHvhKhcXLrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b518c0d93127b312c67f5fa309189f519b7e99d121182957cf8d5acd88d9de8c","last_reissued_at":"2026-07-05T11:40:55.553569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:55.553569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22139","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iPtDk8DG7xSsPfeMJhm/T/YlTuNXTZ+T8yEPjnuIpZdNlhnTT/sQ0GPzBznboBX8RvwQ+wvzm5Lsdv0KjSpEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:10:09.890760Z"},"content_sha256":"d2e890b672392f854cc45d83600a97de54efc6af184638a027a22e91e9ee8c5a","schema_version":"1.0","event_id":"sha256:d2e890b672392f854cc45d83600a97de54efc6af184638a027a22e91e9ee8c5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WUMMBWJRE6ZRFRT7L6RQSGE7KG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahui Yang, Jian Luan, Jianqin Yin, Shaojie Zhang, Zhenbo Luo","submitted_at":"2025-06-27T11:30:51Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal complexity. Existing Video-LLMs using uniform frame sampling often struggle to capture the query-related crucial spatiotemporal clues of videos effectively. In this paper, we introduce Q-Frame, a novel approach for adaptive frame selection and multi-resolution scaling tailored to the video's content and the specific query. Q-Frame employs a training-free, plug-and-p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22139","kind":"arxiv","version":3},"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/2506.22139/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":"2026-07-05T11:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ib66wD/Sh/E99i6RRxHr23nEZpZR/GxQyVyR4cjd3QvZ2jGfUFwa08hR5sZbOsbn5Qtbdbz/gAxedemWszPpDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:10:09.891300Z"},"content_sha256":"69194f682b0f0a833c675141f1fc33dbd99f439686fc99a96028298aa643945a","schema_version":"1.0","event_id":"sha256:69194f682b0f0a833c675141f1fc33dbd99f439686fc99a96028298aa643945a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG/bundle.json","state_url":"https://pith.science/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG/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":"2026-08-07T08:10:09Z","links":{"resolver":"https://pith.science/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG","bundle":"https://pith.science/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG/bundle.json","state":"https://pith.science/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WUMMBWJRE6ZRFRT7L6RQSGE7KG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WUMMBWJRE6ZRFRT7L6RQSGE7KG","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":"d97803d793f4fb739dd8cfb49ce34838650cb302307e28377e1aa6ff5c986f43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T11:30:51Z","title_canon_sha256":"b1ac7835809bad633fe33c7cb9c0d09f357c4ee2c63d4599740babca4fbd0c8f"},"schema_version":"1.0","source":{"id":"2506.22139","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22139","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22139v3","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22139","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"WUMMBWJRE6ZR","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"WUMMBWJRE6ZRFRT7","created_at":"2026-07-05T11:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"WUMMBWJR","created_at":"2026-07-05T11:40:55Z"}],"graph_snapshots":[{"event_id":"sha256:69194f682b0f0a833c675141f1fc33dbd99f439686fc99a96028298aa643945a","target":"graph","created_at":"2026-07-05T11:40:55Z","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/2506.22139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal complexity. Existing Video-LLMs using uniform frame sampling often struggle to capture the query-related crucial spatiotemporal clues of videos effectively. In this paper, we introduce Q-Frame, a novel approach for adaptive frame selection and multi-resolution scaling tailored to the video's content and the specific query. Q-Frame employs a training-free, plug-and-p","authors_text":"Jiahui Yang, Jian Luan, Jianqin Yin, Shaojie Zhang, Zhenbo Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T11:30:51Z","title":"Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22139","kind":"arxiv","version":3},"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:d2e890b672392f854cc45d83600a97de54efc6af184638a027a22e91e9ee8c5a","target":"record","created_at":"2026-07-05T11:40:55Z","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":"d97803d793f4fb739dd8cfb49ce34838650cb302307e28377e1aa6ff5c986f43","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-27T11:30:51Z","title_canon_sha256":"b1ac7835809bad633fe33c7cb9c0d09f357c4ee2c63d4599740babca4fbd0c8f"},"schema_version":"1.0","source":{"id":"2506.22139","kind":"arxiv","version":3}},"canonical_sha256":"b518c0d93127b312c67f5fa309189f519b7e99d121182957cf8d5acd88d9de8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b518c0d93127b312c67f5fa309189f519b7e99d121182957cf8d5acd88d9de8c","first_computed_at":"2026-07-05T11:40:55.553569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:55.553569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o4JFEZ4RNiMaEEW4NYjRraM9sVDmMr6jj44mC4re+ev9j+9YS7uMb1wAO8TBC07+6uPRutn9pjPHvhKhcXLrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:55.554090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22139","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2e890b672392f854cc45d83600a97de54efc6af184638a027a22e91e9ee8c5a","sha256:69194f682b0f0a833c675141f1fc33dbd99f439686fc99a96028298aa643945a"],"state_sha256":"f6ee4c0756ec2c3a98fcf039f8460924ebe37b425f1dc6704acd27e462d53e5e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7R+1rM53+b6cuQwZPQf0YsuuRdP6TfPUBYBmLm+94i+fKRjk0IGLmwMuYVHpeDputUlfWIHFlgJO1CPccRJbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:10:09.894823Z","bundle_sha256":"1228873b873ce3a825adf14f19e3477a84620b9c2c37c7b8c241a262891336d1"}}