{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KHUIB7STW3WDHE4D7XYHESBIXA","short_pith_number":"pith:KHUIB7ST","canonical_record":{"source":{"id":"2404.17176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T06:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"dad6ee1189a484b7a74bfd235050aaebda475bd790da777a0822338ecce49347","abstract_canon_sha256":"c3d84e86618499d919d221601c38fc37bbe4c57805ce870ac712b75fcae64346"},"schema_version":"1.0"},"canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","source":{"kind":"arxiv","id":"2404.17176","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17176","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17176v1","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17176","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"KHUIB7STW3WD","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"KHUIB7STW3WDHE4D","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"KHUIB7ST","created_at":"2026-07-05T08:12:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KHUIB7STW3WDHE4D7XYHESBIXA","target":"record","payload":{"canonical_record":{"source":{"id":"2404.17176","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T06:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"dad6ee1189a484b7a74bfd235050aaebda475bd790da777a0822338ecce49347","abstract_canon_sha256":"c3d84e86618499d919d221601c38fc37bbe4c57805ce870ac712b75fcae64346"},"schema_version":"1.0"},"canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:34.007640Z","signature_b64":"hYZ58rlpZDtgOE1GeNmzUJ2vgecPLxMMAdg9cMuA8kMEU9oB8C73Y058PKNAFB8+zmcZ9/8gt9cNWl4UxLRiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","last_reissued_at":"2026-07-05T08:12:34.007131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:34.007131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.17176","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":"2026-07-05T08:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YvmNRxMtZkP5h0XQ9FHzy65faUrQZZjAaI7/9IpkDAv8z8au7tfhIwsRiFQMbvzNB4Wtx1VEj0LiQJqKD1gxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:04:44.614606Z"},"content_sha256":"f063e612afb4af9c4e8283107005e876940aecc7f7c7a0af8cb276e4c4193780","schema_version":"1.0","event_id":"sha256:f063e612afb4af9c4e8283107005e876940aecc7f7c7a0af8cb276e4c4193780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KHUIB7STW3WDHE4D7XYHESBIXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Enxin Song, Gaoang Wang, Jenq-Neng Hwang, Tian Ye, Wenhao Chai, Xi Li","submitted_at":"2024-04-26T06:17:04Z","abstract_excerpt":"Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17176","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/2404.17176/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":"2026-07-05T08:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0me05AHo2mtDFYJxUVqhJoDpkZOIJaVQrTxqcd/JTrG5GOOLsr3OBuudH6ZOhY8tXkJRbaj4ndwhaHm5O5/9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:04:44.615326Z"},"content_sha256":"832d81005077e3de899001566b892d88d43c80def10aeeff14923c9c558cdd8f","schema_version":"1.0","event_id":"sha256:832d81005077e3de899001566b892d88d43c80def10aeeff14923c9c558cdd8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/bundle.json","state_url":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KHUIB7STW3WDHE4D7XYHESBIXA/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":"2026-08-07T01:04:44Z","links":{"resolver":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA","bundle":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/bundle.json","state":"https://pith.science/pith/KHUIB7STW3WDHE4D7XYHESBIXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KHUIB7STW3WDHE4D7XYHESBIXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KHUIB7STW3WDHE4D7XYHESBIXA","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":"c3d84e86618499d919d221601c38fc37bbe4c57805ce870ac712b75fcae64346","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T06:17:04Z","title_canon_sha256":"dad6ee1189a484b7a74bfd235050aaebda475bd790da777a0822338ecce49347"},"schema_version":"1.0","source":{"id":"2404.17176","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17176","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17176v1","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17176","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"KHUIB7STW3WD","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"KHUIB7STW3WDHE4D","created_at":"2026-07-05T08:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"KHUIB7ST","created_at":"2026-07-05T08:12:34Z"}],"graph_snapshots":[{"event_id":"sha256:832d81005077e3de899001566b892d88d43c80def10aeeff14923c9c558cdd8f","target":"graph","created_at":"2026-07-05T08:12:34Z","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/2404.17176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, integrating video foundation models and large language models to build a video understanding system can overcome the limitations of specific pre-defined vision tasks. Yet, existing methods either employ complex spatial-temporal modules or rely heavily on additional perception models to extract temporal features for video understanding, and they only perform well on short videos. For long videos, the computational complexity and memory costs associated with long-term temporal connections are significantly increased, posing additional challenges.Taking advantage of the Atkinson-Shiffri","authors_text":"Enxin Song, Gaoang Wang, Jenq-Neng Hwang, Tian Ye, Wenhao Chai, Xi Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T06:17:04Z","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17176","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:f063e612afb4af9c4e8283107005e876940aecc7f7c7a0af8cb276e4c4193780","target":"record","created_at":"2026-07-05T08:12:34Z","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":"c3d84e86618499d919d221601c38fc37bbe4c57805ce870ac712b75fcae64346","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-04-26T06:17:04Z","title_canon_sha256":"dad6ee1189a484b7a74bfd235050aaebda475bd790da777a0822338ecce49347"},"schema_version":"1.0","source":{"id":"2404.17176","kind":"arxiv","version":1}},"canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51e880fe53b6ec339383fdf0724828b815306c93b56c660e00a57e0f4c45acd4","first_computed_at":"2026-07-05T08:12:34.007131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:34.007131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hYZ58rlpZDtgOE1GeNmzUJ2vgecPLxMMAdg9cMuA8kMEU9oB8C73Y058PKNAFB8+zmcZ9/8gt9cNWl4UxLRiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:34.007640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17176","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f063e612afb4af9c4e8283107005e876940aecc7f7c7a0af8cb276e4c4193780","sha256:832d81005077e3de899001566b892d88d43c80def10aeeff14923c9c558cdd8f"],"state_sha256":"37b25062942e1161a678b7878e376bed17c7874ee15e96ef61ea10c616912ff5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pckps422z6PzKhSQCpZKg5i42ulfnq9CioJQxPCvzYXf/0vEJ1F/KelCeeciNnJV0jkdEnJQs8Zs6cpiGbPxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:04:44.620443Z","bundle_sha256":"66ca0dff4d65e864ab2a9e75a050239c99cd92373404b9f11e5c78d22faa0dd0"}}