{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FECFVZXIQVUHPH6CHZ6NMKHQON","short_pith_number":"pith:FECFVZXI","schema_version":"1.0","canonical_sha256":"29045ae6e88568779fc23e7cd628f0737d1898d263f1d9b300275ac714a65135","source":{"kind":"arxiv","id":"2605.26680","version":1},"attestation_state":"computed","paper":{"title":"DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanghao Zhang, Haobing Tang, Hao Jiang, Jinlong Liu, Le Zhang, Longxiang Zhang, Mushui Liu, Peng Zhang, Pipei Huang, Wanggui He, Weilong Dai, Yan Xia, Zhenhao Peng","submitted_at":"2026-05-26T08:16:16Z","abstract_excerpt":"Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps remain in existing thinking-with-video systems. (i) Sampling density is not a learnable decision: existing methods may let the model decide where to look, but the per-window frame rate is largely fixed. As a result, fine-grained evidence is often recovered through repeated retrieval calls, which increases inference context length and training difficulty. (ii) R"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T08:16:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85fb986f439cc280acadc1a60a1b6af066a8857fcd394f28e0b503ff31286763","abstract_canon_sha256":"7e78c517610e837333a1539d2cd6502b54904374d08aad140716f491ae639218"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:05.706373Z","signature_b64":"kDb6WL4QfKmMW2Jt8Kq5dYjIKSdAn46ZjF4upOjc3RN5U2XyoXIVqk6PCJPBuRYaMLkgKflkjgW8G34J4QqAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29045ae6e88568779fc23e7cd628f0737d1898d263f1d9b300275ac714a65135","last_reissued_at":"2026-05-27T01:06:05.705613Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:05.705613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanghao Zhang, Haobing Tang, Hao Jiang, Jinlong Liu, Le Zhang, Longxiang Zhang, Mushui Liu, Peng Zhang, Pipei Huang, Wanggui He, Weilong Dai, Yan Xia, Zhenhao Peng","submitted_at":"2026-05-26T08:16:16Z","abstract_excerpt":"Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video segments during inference. However, two structural gaps remain in existing thinking-with-video systems. (i) Sampling density is not a learnable decision: existing methods may let the model decide where to look, but the per-window frame rate is largely fixed. As a result, fine-grained evidence is often recovered through repeated retrieval calls, which increases inference context length and training difficulty. (ii) R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26680","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/2605.26680/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26680","created_at":"2026-05-27T01:06:05.705730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26680v1","created_at":"2026-05-27T01:06:05.705730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26680","created_at":"2026-05-27T01:06:05.705730+00:00"},{"alias_kind":"pith_short_12","alias_value":"FECFVZXIQVUH","created_at":"2026-05-27T01:06:05.705730+00:00"},{"alias_kind":"pith_short_16","alias_value":"FECFVZXIQVUHPH6C","created_at":"2026-05-27T01:06:05.705730+00:00"},{"alias_kind":"pith_short_8","alias_value":"FECFVZXI","created_at":"2026-05-27T01:06:05.705730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON","json":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON.json","graph_json":"https://pith.science/api/pith-number/FECFVZXIQVUHPH6CHZ6NMKHQON/graph.json","events_json":"https://pith.science/api/pith-number/FECFVZXIQVUHPH6CHZ6NMKHQON/events.json","paper":"https://pith.science/paper/FECFVZXI"},"agent_actions":{"view_html":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON","download_json":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON.json","view_paper":"https://pith.science/paper/FECFVZXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26680&json=true","fetch_graph":"https://pith.science/api/pith-number/FECFVZXIQVUHPH6CHZ6NMKHQON/graph.json","fetch_events":"https://pith.science/api/pith-number/FECFVZXIQVUHPH6CHZ6NMKHQON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON/action/storage_attestation","attest_author":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON/action/author_attestation","sign_citation":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON/action/citation_signature","submit_replication":"https://pith.science/pith/FECFVZXIQVUHPH6CHZ6NMKHQON/action/replication_record"}},"created_at":"2026-05-27T01:06:05.705730+00:00","updated_at":"2026-05-27T01:06:05.705730+00:00"}