{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MMGBJHTE43YRU3BPDY53R6DOYV","short_pith_number":"pith:MMGBJHTE","canonical_record":{"source":{"id":"2404.05726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"e92ab81c5284655c5a7ab73181b4842edc91310e895ce76dbe68f23fbdbe2d8a","abstract_canon_sha256":"897e88f023ddc83ea62ffeb4acc5a4537d393e3ae603bfecfe3c056b663dc163"},"schema_version":"1.0"},"canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","source":{"kind":"arxiv","id":"2404.05726","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05726","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05726v2","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05726","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"pith_short_12","alias_value":"MMGBJHTE43YR","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"pith_short_16","alias_value":"MMGBJHTE43YRU3BP","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"pith_short_8","alias_value":"MMGBJHTE","created_at":"2026-07-05T08:11:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MMGBJHTE43YRU3BPDY53R6DOYV","target":"record","payload":{"canonical_record":{"source":{"id":"2404.05726","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"e92ab81c5284655c5a7ab73181b4842edc91310e895ce76dbe68f23fbdbe2d8a","abstract_canon_sha256":"897e88f023ddc83ea62ffeb4acc5a4537d393e3ae603bfecfe3c056b663dc163"},"schema_version":"1.0"},"canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:43.735393Z","signature_b64":"AV88nssG8xV6FdUPTYBnvvVyJovA8kIkORhAVHo4mg8RglYvGpkSDXQZwFFrst/Bu2PQv8WgUku7VwKvferNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","last_reissued_at":"2026-07-05T08:11:43.734894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:43.734894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.05726","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":"2026-07-05T08:11:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5wxfnWb8t+xdfGJdONM5hQ87hYdnUmiv3rUPjzRNu1ZRi18ix8W+2YbOTJgOvw2SwMdRd0QWcezxiogmBbf/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:00:34.322897Z"},"content_sha256":"f00a66f2a44fe576b0bb240ebdc4e441f3447bda84ce66cec98388dee05bac57","schema_version":"1.0","event_id":"sha256:f00a66f2a44fe576b0bb240ebdc4e441f3447bda84ce66cec98388dee05bac57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MMGBJHTE43YRU3BPDY53R6DOYV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ashish Shah, Bo He, Hengduo Li, Menglin Jia, Ser-Nam Lim, Xuefei Cao, Young Kyun Jang","submitted_at":"2024-04-08T17:59:24Z","abstract_excerpt":"With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05726","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/2404.05726/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":"2026-07-05T08:11:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"urgXH2I+S40q5UfZ+pfBNaSFKnrVzPESc91d3gTde2Whka4Wbfs5uJvfDWiwrAqZ4h9abQ9zlNFAv1XILFewCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:00:34.323391Z"},"content_sha256":"70730b8fc03f8d2946f3c49d6657e5aa7cf4bf0d91970cfe7fbe0310bb95e8a4","schema_version":"1.0","event_id":"sha256:70730b8fc03f8d2946f3c49d6657e5aa7cf4bf0d91970cfe7fbe0310bb95e8a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/bundle.json","state_url":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MMGBJHTE43YRU3BPDY53R6DOYV/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":"2026-08-05T04:00:34Z","links":{"resolver":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV","bundle":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/bundle.json","state":"https://pith.science/pith/MMGBJHTE43YRU3BPDY53R6DOYV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MMGBJHTE43YRU3BPDY53R6DOYV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MMGBJHTE43YRU3BPDY53R6DOYV","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":"897e88f023ddc83ea62ffeb4acc5a4537d393e3ae603bfecfe3c056b663dc163","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:59:24Z","title_canon_sha256":"e92ab81c5284655c5a7ab73181b4842edc91310e895ce76dbe68f23fbdbe2d8a"},"schema_version":"1.0","source":{"id":"2404.05726","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05726","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05726v2","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05726","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"pith_short_12","alias_value":"MMGBJHTE43YR","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"pith_short_16","alias_value":"MMGBJHTE43YRU3BP","created_at":"2026-07-05T08:11:43Z"},{"alias_kind":"pith_short_8","alias_value":"MMGBJHTE","created_at":"2026-07-05T08:11:43Z"}],"graph_snapshots":[{"event_id":"sha256:70730b8fc03f8d2946f3c49d6657e5aa7cf4bf0d91970cfe7fbe0310bb95e8a4","target":"graph","created_at":"2026-07-05T08:11:43Z","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/2404.05726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success of large language models (LLMs), integrating the vision model into LLMs to build vision-language foundation models has gained much more interest recently. However, existing LLM-based large multimodal models (e.g., Video-LLaMA, VideoChat) can only take in a limited number of frames for short video understanding. In this study, we mainly focus on designing an efficient and effective model for long-term video understanding. Instead of trying to process more frames simultaneously like most existing work, we propose to process videos in an online manner and store past video informa","authors_text":"Abhinav Shrivastava, Ashish Shah, Bo He, Hengduo Li, Menglin Jia, Ser-Nam Lim, Xuefei Cao, Young Kyun Jang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:59:24Z","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05726","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:f00a66f2a44fe576b0bb240ebdc4e441f3447bda84ce66cec98388dee05bac57","target":"record","created_at":"2026-07-05T08:11:43Z","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":"897e88f023ddc83ea62ffeb4acc5a4537d393e3ae603bfecfe3c056b663dc163","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-08T17:59:24Z","title_canon_sha256":"e92ab81c5284655c5a7ab73181b4842edc91310e895ce76dbe68f23fbdbe2d8a"},"schema_version":"1.0","source":{"id":"2404.05726","kind":"arxiv","version":2}},"canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"630c149e64e6f11a6c2f1e3bb8f86ec57b25bfb7365009a4bd99a1f678d46e2f","first_computed_at":"2026-07-05T08:11:43.734894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:11:43.734894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AV88nssG8xV6FdUPTYBnvvVyJovA8kIkORhAVHo4mg8RglYvGpkSDXQZwFFrst/Bu2PQv8WgUku7VwKvferNCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:11:43.735393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05726","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f00a66f2a44fe576b0bb240ebdc4e441f3447bda84ce66cec98388dee05bac57","sha256:70730b8fc03f8d2946f3c49d6657e5aa7cf4bf0d91970cfe7fbe0310bb95e8a4"],"state_sha256":"b9f3efe368971ea9fc00ed4355b06bb53cdc99ba8bb6ba64122c966af88da4a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgx6UPPbCvv+icb2Hu70HRgXdT9jGvxg5gEUNyvpGrdEEMerq3HY2qM+9YZUXF9oBFzbN4bhTzpJjHWsTEdFBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:00:34.326786Z","bundle_sha256":"17bc8ed074abbed6e77c9cc971638b5a537513f234c2ae03a9a2df2fa7da38da"}}