{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OJYTNIZ7AQ6XLLFDPXNFIS7UDA","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":"f8efbe28c031fd5b72760113f5f840c56b006e2e4e2debedde2ca7a076c353e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T06:08:12Z","title_canon_sha256":"f0c5b40d9efbef27615cda6cd7b5c46a047825f1ce39132d1e0bb40650e5d3cb"},"schema_version":"1.0","source":{"id":"2407.00603","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00603","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00603v2","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00603","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"OJYTNIZ7AQ6X","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"OJYTNIZ7AQ6XLLFD","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"OJYTNIZ7","created_at":"2026-07-05T09:49:07Z"}],"graph_snapshots":[{"event_id":"sha256:f3b89758552d66f36b1cb9854d7f8a97a8d56a14d65645920bcb380cf8bebbc5","target":"graph","created_at":"2026-07-05T09:49:07Z","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/2407.00603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes our champion solution to the LOVEU Challenge @ CVPR'24, Track 1 (Long Video VQA). Processing long sequences of visual tokens is computationally expensive and memory-intensive, making long video question-answering a challenging task. The key is to compress visual tokens effectively, reducing memory footprint and decoding latency, while preserving the essential information for accurate question-answering. We adopt a hierarchical memory mechanism named STAR Memory, proposed in Flash-VStream, that is capable of processing long videos with limited GPU memory (VRAM). We further ","authors_text":"Haoji Zhang, Jiashi Feng, Jifeng Dai, Xiaojie Jin, Yansong Tang, Yiqin Wang, Yong Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T06:08:12Z","title":"Hierarchical Memory for Long Video QA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00603","kind":"arxiv","version":2},"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":"sha256:98f8c94c9e82eb73b38cc83ea5fd0c94a8930b2304a9756b416cf0fd46dba092","target":"record","created_at":"2026-07-05T09:49:07Z","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":"f8efbe28c031fd5b72760113f5f840c56b006e2e4e2debedde2ca7a076c353e5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T06:08:12Z","title_canon_sha256":"f0c5b40d9efbef27615cda6cd7b5c46a047825f1ce39132d1e0bb40650e5d3cb"},"schema_version":"1.0","source":{"id":"2407.00603","kind":"arxiv","version":2}},"canonical_sha256":"727136a33f043d75aca37dda544bf41831b9b1ede750d236044751b29b224dc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"727136a33f043d75aca37dda544bf41831b9b1ede750d236044751b29b224dc9","first_computed_at":"2026-07-05T09:49:07.285336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:07.285336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J7LkDYhE5oNaSjrytfyFw/dO1RZzRYAGTgjLG01ehRe39jRt1KggrQvPc4kJVPtBk5gxhviw0VY0Q90taCF/AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:07.285886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00603","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98f8c94c9e82eb73b38cc83ea5fd0c94a8930b2304a9756b416cf0fd46dba092","sha256:f3b89758552d66f36b1cb9854d7f8a97a8d56a14d65645920bcb380cf8bebbc5"],"state_sha256":"07b350c6fe9109d9eb6b9824bfaeec0b51d59e095f0d004025b3acac62569cdf"}