{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:C5VS42FPCBOHJGCUV6SJ33MOFP","short_pith_number":"pith:C5VS42FP","canonical_record":{"source":{"id":"2506.23825","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"15077eaf6dd854a3bf042534c461f3bc9aaf86cbaba3eff2034002f53f72d0ee","abstract_canon_sha256":"7190bacdf89f3dd685a49cfe4ddcff52eb10f16247fd4d57ee9e67ea18f282e1"},"schema_version":"1.0"},"canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","source":{"kind":"arxiv","id":"2506.23825","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23825","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23825v2","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23825","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"C5VS42FPCBOH","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"C5VS42FPCBOHJGCU","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"C5VS42FP","created_at":"2026-07-05T11:42:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:C5VS42FPCBOHJGCUV6SJ33MOFP","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23825","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:17:49Z","cross_cats_sorted":[],"title_canon_sha256":"15077eaf6dd854a3bf042534c461f3bc9aaf86cbaba3eff2034002f53f72d0ee","abstract_canon_sha256":"7190bacdf89f3dd685a49cfe4ddcff52eb10f16247fd4d57ee9e67ea18f282e1"},"schema_version":"1.0"},"canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:31.309613Z","signature_b64":"rWJIFwTYfbMVh0LTEYPVR0HKg8M1FDnuB9msmFW3jEdEfufyR0hmwnMj1MBG4aJd6Q+PCMgXnorWPhMSadU8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","last_reissued_at":"2026-07-05T11:42:31.309047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:31.309047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23825","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Z+sTBGW3dMcISXE98b1eeN2cGM9UtrdcvLrStWTZy3AmCrYaXLXQoMxjIiKvSdWtFyZs4xpsAPFKriVmZtoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:10:06.805874Z"},"content_sha256":"85196b6a9c8aca3d0f07a6ec007d2d644d9c0c753d1f1cdb993ed53c828c6663","schema_version":"1.0","event_id":"sha256:85196b6a9c8aca3d0f07a6ec007d2d644d9c0c753d1f1cdb993ed53c828c6663"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:C5VS42FPCBOHJGCUV6SJ33MOFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoji Zhang, Jiashi Feng, Xiaojie Jin, Yansong Tang, Yiqin Wang, Yong Liu","submitted_at":"2025-06-30T13:17:49Z","abstract_excerpt":"Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23825","kind":"arxiv","version":2},"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/2506.23825/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":"2026-07-05T11:42:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rCcQXHbWve56jNcoZFGMCSTcRkI1YWW0a6sUXzuBVw3kwdqTOahY36h9VhuTts+IOPFDCxgoEXz3EJhwnlmpDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T11:10:06.806396Z"},"content_sha256":"dab32e98733b8580e9210e1ba6fd0bc4ed30f5424007c810da42c84ba3b853e0","schema_version":"1.0","event_id":"sha256:dab32e98733b8580e9210e1ba6fd0bc4ed30f5424007c810da42c84ba3b853e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/bundle.json","state_url":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/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":"2026-08-03T11:10:06Z","links":{"resolver":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP","bundle":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/bundle.json","state":"https://pith.science/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5VS42FPCBOHJGCUV6SJ33MOFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C5VS42FPCBOHJGCUV6SJ33MOFP","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":"7190bacdf89f3dd685a49cfe4ddcff52eb10f16247fd4d57ee9e67ea18f282e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:17:49Z","title_canon_sha256":"15077eaf6dd854a3bf042534c461f3bc9aaf86cbaba3eff2034002f53f72d0ee"},"schema_version":"1.0","source":{"id":"2506.23825","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23825","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23825v2","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23825","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"pith_short_12","alias_value":"C5VS42FPCBOH","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"pith_short_16","alias_value":"C5VS42FPCBOHJGCU","created_at":"2026-07-05T11:42:31Z"},{"alias_kind":"pith_short_8","alias_value":"C5VS42FP","created_at":"2026-07-05T11:42:31Z"}],"graph_snapshots":[{"event_id":"sha256:dab32e98733b8580e9210e1ba6fd0bc4ed30f5424007c810da42c84ba3b853e0","target":"graph","created_at":"2026-07-05T11:42:31Z","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/2506.23825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short video understanding. However, the understanding of long videos is still challenging, as their long-context nature results in significant computational and memory overhead. Most existing work treats long videos in the same way as short videos, which is inefficient for real-world applications and hard to generalize to even longer videos. To address these issues, we propose Flash-VStream, an efficient video language model","authors_text":"Haoji Zhang, Jiashi Feng, 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":"2025-06-30T13:17:49Z","title":"Flash-VStream: Efficient Real-Time Understanding for Long Video Streams"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23825","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":"sha256:85196b6a9c8aca3d0f07a6ec007d2d644d9c0c753d1f1cdb993ed53c828c6663","target":"record","created_at":"2026-07-05T11:42:31Z","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":"7190bacdf89f3dd685a49cfe4ddcff52eb10f16247fd4d57ee9e67ea18f282e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:17:49Z","title_canon_sha256":"15077eaf6dd854a3bf042534c461f3bc9aaf86cbaba3eff2034002f53f72d0ee"},"schema_version":"1.0","source":{"id":"2506.23825","kind":"arxiv","version":2}},"canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"176b2e68af105c749854afa49ded8e2be0cf3e1859f67b9863aac32f4df8eb7e","first_computed_at":"2026-07-05T11:42:31.309047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:31.309047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWJIFwTYfbMVh0LTEYPVR0HKg8M1FDnuB9msmFW3jEdEfufyR0hmwnMj1MBG4aJd6Q+PCMgXnorWPhMSadU8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:31.309613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23825","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85196b6a9c8aca3d0f07a6ec007d2d644d9c0c753d1f1cdb993ed53c828c6663","sha256:dab32e98733b8580e9210e1ba6fd0bc4ed30f5424007c810da42c84ba3b853e0"],"state_sha256":"c248ac1bebf4425d2cf60098701b92967a58fb43d00de2274b0a4c09d4a885a8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6iN2vac3SbzM31vypLGG1GtWcdXoKE45KUkfieiDeNjZAQF3SPCvxAzMxog3EHvbT1qwPvhI9S2yI97Aet3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T11:10:06.810796Z","bundle_sha256":"997a9b5d291fba2dc4549b848a2a018456030bd56f56dbd1e7afb675b7472680"}}