{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:62Q6NPCO65FREOVT4CWT76S6T4","short_pith_number":"pith:62Q6NPCO","canonical_record":{"source":{"id":"2607.19857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T07:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df7dbb7f859ebb4b5ef931e50d28a89f52ecd3b62d8a51e2dd1ac716d31a438a","abstract_canon_sha256":"84b078737756cbb18ef8258be8d37a551d159d38daf2e737881b9b12384dc544"},"schema_version":"1.0"},"canonical_sha256":"f6a1e6bc4ef74b123ab3e0ad3ffa5e9f33f07582994620dc3808932d9c295957","source":{"kind":"arxiv","id":"2607.19857","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19857","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19857v1","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19857","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"pith_short_12","alias_value":"62Q6NPCO65FR","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"pith_short_16","alias_value":"62Q6NPCO65FREOVT","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"pith_short_8","alias_value":"62Q6NPCO","created_at":"2026-07-23T01:24:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:62Q6NPCO65FREOVT4CWT76S6T4","target":"record","payload":{"canonical_record":{"source":{"id":"2607.19857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T07:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df7dbb7f859ebb4b5ef931e50d28a89f52ecd3b62d8a51e2dd1ac716d31a438a","abstract_canon_sha256":"84b078737756cbb18ef8258be8d37a551d159d38daf2e737881b9b12384dc544"},"schema_version":"1.0"},"canonical_sha256":"f6a1e6bc4ef74b123ab3e0ad3ffa5e9f33f07582994620dc3808932d9c295957","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:24:04.134206Z","signature_b64":"zxnhgimuPD+ry2MORwPHNLkedN2XYn/oGtD1tk4SqsBll9J1PzG4l8W+VmhK19z2nybRHah/z/GSklP0gg5FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6a1e6bc4ef74b123ab3e0ad3ffa5e9f33f07582994620dc3808932d9c295957","last_reissued_at":"2026-07-23T01:24:04.133370Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:24:04.133370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.19857","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":"2026-07-23T01:24:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1d0M2KqnupJI0/jfetrOBrnwgfF7+uNsueOqzI4BYj8bLwnyPpksLRFDRgq3j/JBlX0pJvOq99FH/wn4Ri5PAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:34:02.781884Z"},"content_sha256":"f5aaa4f5eccd41d56485a1746935e1297fe77e644d5967f4b01875315424b11a","schema_version":"1.0","event_id":"sha256:f5aaa4f5eccd41d56485a1746935e1297fe77e644d5967f4b01875315424b11a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:62Q6NPCO65FREOVT4CWT76S6T4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Han, Henghui Ding, Kaiyong Zhao, Penglei Sun, Runwei Guan, Xiang Li, Xiaowen Chu, Yang Yang, Yaoxian Song, Yehua Huang, Zhuoli Tao","submitted_at":"2026-07-22T07:45:50Z","abstract_excerpt":"Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployment, the UAV must respond while it flies, so such perception runs in an online streaming manner, where frames arrive sequentially and the model responds to each one without access to future frames. However, applying current Multimodal Large Language Models (MLLMs) to this setting raises two challenges. First, targets viewed from the air are often tiny, yet the visual compression in existing MLLMs treats all regions equally and discards their fine-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19857","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/2607.19857/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":"2026-07-23T01:24:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZrPU59H+7x91ZsyW8OAqe6oZVRyZqw57ap64Sg38qQF0QQI+MZZ122M6RW3XS9BIpQ5DYtAGxvZ9SY7Q/MvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T23:34:02.782429Z"},"content_sha256":"5519c80239ef68684609f7a5e892a86495e59b39cde8758ba50df10f3e81bfa1","schema_version":"1.0","event_id":"sha256:5519c80239ef68684609f7a5e892a86495e59b39cde8758ba50df10f3e81bfa1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62Q6NPCO65FREOVT4CWT76S6T4/bundle.json","state_url":"https://pith.science/pith/62Q6NPCO65FREOVT4CWT76S6T4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62Q6NPCO65FREOVT4CWT76S6T4/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":"2026-08-08T23:34:02Z","links":{"resolver":"https://pith.science/pith/62Q6NPCO65FREOVT4CWT76S6T4","bundle":"https://pith.science/pith/62Q6NPCO65FREOVT4CWT76S6T4/bundle.json","state":"https://pith.science/pith/62Q6NPCO65FREOVT4CWT76S6T4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62Q6NPCO65FREOVT4CWT76S6T4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:62Q6NPCO65FREOVT4CWT76S6T4","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":"84b078737756cbb18ef8258be8d37a551d159d38daf2e737881b9b12384dc544","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T07:45:50Z","title_canon_sha256":"df7dbb7f859ebb4b5ef931e50d28a89f52ecd3b62d8a51e2dd1ac716d31a438a"},"schema_version":"1.0","source":{"id":"2607.19857","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.19857","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.19857v1","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19857","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"pith_short_12","alias_value":"62Q6NPCO65FR","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"pith_short_16","alias_value":"62Q6NPCO65FREOVT","created_at":"2026-07-23T01:24:04Z"},{"alias_kind":"pith_short_8","alias_value":"62Q6NPCO","created_at":"2026-07-23T01:24:04Z"}],"graph_snapshots":[{"event_id":"sha256:5519c80239ef68684609f7a5e892a86495e59b39cde8758ba50df10f3e81bfa1","target":"graph","created_at":"2026-07-23T01:24:04Z","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/2607.19857/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-guided aerial perception aims to understand user-specified tiny targets in complex unmanned aerial vehicle (UAV) scenes. In real UAV deployment, the UAV must respond while it flies, so such perception runs in an online streaming manner, where frames arrive sequentially and the model responds to each one without access to future frames. However, applying current Multimodal Large Language Models (MLLMs) to this setting raises two challenges. First, targets viewed from the air are often tiny, yet the visual compression in existing MLLMs treats all regions equally and discards their fine-","authors_text":"Bo Han, Henghui Ding, Kaiyong Zhao, Penglei Sun, Runwei Guan, Xiang Li, Xiaowen Chu, Yang Yang, Yaoxian Song, Yehua Huang, Zhuoli Tao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T07:45:50Z","title":"Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Streaming Aerial Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19857","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:f5aaa4f5eccd41d56485a1746935e1297fe77e644d5967f4b01875315424b11a","target":"record","created_at":"2026-07-23T01:24:04Z","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":"84b078737756cbb18ef8258be8d37a551d159d38daf2e737881b9b12384dc544","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T07:45:50Z","title_canon_sha256":"df7dbb7f859ebb4b5ef931e50d28a89f52ecd3b62d8a51e2dd1ac716d31a438a"},"schema_version":"1.0","source":{"id":"2607.19857","kind":"arxiv","version":1}},"canonical_sha256":"f6a1e6bc4ef74b123ab3e0ad3ffa5e9f33f07582994620dc3808932d9c295957","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6a1e6bc4ef74b123ab3e0ad3ffa5e9f33f07582994620dc3808932d9c295957","first_computed_at":"2026-07-23T01:24:04.133370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-23T01:24:04.133370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zxnhgimuPD+ry2MORwPHNLkedN2XYn/oGtD1tk4SqsBll9J1PzG4l8W+VmhK19z2nybRHah/z/GSklP0gg5FBg==","signature_status":"signed_v1","signed_at":"2026-07-23T01:24:04.134206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.19857","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5aaa4f5eccd41d56485a1746935e1297fe77e644d5967f4b01875315424b11a","sha256:5519c80239ef68684609f7a5e892a86495e59b39cde8758ba50df10f3e81bfa1"],"state_sha256":"30bbd5b73f806727d409f7efe4e6eecc2f025746a4365c90505ee84b5590a857"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPPFe+mdAQSg05jCvpQHBdvH5DNUBN6D6AuFP90tNKu9m/wOAgZ6Sik6k5RqsYyHpMhAGAa3dhHapWo4WwsmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T23:34:02.787739Z","bundle_sha256":"146e439588219067efcf3599dc9cdd50e4ed3b3d077dfdf4a1f29fbe540de9a6"}}