{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EN5RC7WIKPQZSEUGEBTLSC77N4","short_pith_number":"pith:EN5RC7WI","canonical_record":{"source":{"id":"2401.01529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T03:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"90dc071df367dfa0049e8e2b6193e3d8cc5eeac809c0eab248596cbbc6b20f1c","abstract_canon_sha256":"c75ea3ddc2044ca82fcd65aa013d8e226c9afb6a90cb065b849066a7f1e38861"},"schema_version":"1.0"},"canonical_sha256":"237b117ec853e19912862066b90bff6f29d2a8b8ecac16cef8602f2effec5346","source":{"kind":"arxiv","id":"2401.01529","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01529","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01529v1","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01529","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"EN5RC7WIKPQZ","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"EN5RC7WIKPQZSEUG","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"EN5RC7WI","created_at":"2026-07-05T07:29:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EN5RC7WIKPQZSEUGEBTLSC77N4","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T03:51:16Z","cross_cats_sorted":[],"title_canon_sha256":"90dc071df367dfa0049e8e2b6193e3d8cc5eeac809c0eab248596cbbc6b20f1c","abstract_canon_sha256":"c75ea3ddc2044ca82fcd65aa013d8e226c9afb6a90cb065b849066a7f1e38861"},"schema_version":"1.0"},"canonical_sha256":"237b117ec853e19912862066b90bff6f29d2a8b8ecac16cef8602f2effec5346","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:44.650081Z","signature_b64":"TQGRssP9DpAVqrtV96LVBwzlf/LcFIPm8mCrSBOIZx1MDMwSGJ2uH98c1uZouT7rzvTHdRbmAzkZvkXd6jXZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"237b117ec853e19912862066b90bff6f29d2a8b8ecac16cef8602f2effec5346","last_reissued_at":"2026-07-05T07:29:44.649583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:44.649583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01529","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":"2026-07-05T07:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFLLjBiia8jtKNjgWgAqhEsVkE53hSi1WBAlg2rXdjMbzCOUKrOINrG12skybtvPlPDg5bblJoSVygsJyulBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:14:51.930591Z"},"content_sha256":"148b21e20958495b6f151115f646c66bdbfbd5559cf16bd63fe362b7b87f46e1","schema_version":"1.0","event_id":"sha256:148b21e20958495b6f151115f646c66bdbfbd5559cf16bd63fe362b7b87f46e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EN5RC7WIKPQZSEUGEBTLSC77N4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ruiping Wang, Xilin Chen, Ziyi Bai","submitted_at":"2024-01-03T03:51:16Z","abstract_excerpt":"Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging. In contrast, humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. One simple way is to apply an action "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01529","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/2401.01529/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":"2026-07-05T07:29:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzOaNcBzDntYyq+XGDFnB1uq+oe1OL4xlS9KsGhICS2s+GothocDrjPUwQCeJ/rmXLdxO6slf5BX/GMjY/8oAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:14:51.931090Z"},"content_sha256":"08d44c3655bed84c935c567dae321854f96fd8eba4ccdbccdf0d14e2bdface01","schema_version":"1.0","event_id":"sha256:08d44c3655bed84c935c567dae321854f96fd8eba4ccdbccdf0d14e2bdface01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EN5RC7WIKPQZSEUGEBTLSC77N4/bundle.json","state_url":"https://pith.science/pith/EN5RC7WIKPQZSEUGEBTLSC77N4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EN5RC7WIKPQZSEUGEBTLSC77N4/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":"2026-08-12T07:14:51Z","links":{"resolver":"https://pith.science/pith/EN5RC7WIKPQZSEUGEBTLSC77N4","bundle":"https://pith.science/pith/EN5RC7WIKPQZSEUGEBTLSC77N4/bundle.json","state":"https://pith.science/pith/EN5RC7WIKPQZSEUGEBTLSC77N4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EN5RC7WIKPQZSEUGEBTLSC77N4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EN5RC7WIKPQZSEUGEBTLSC77N4","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":"c75ea3ddc2044ca82fcd65aa013d8e226c9afb6a90cb065b849066a7f1e38861","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T03:51:16Z","title_canon_sha256":"90dc071df367dfa0049e8e2b6193e3d8cc5eeac809c0eab248596cbbc6b20f1c"},"schema_version":"1.0","source":{"id":"2401.01529","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01529","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01529v1","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01529","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"pith_short_12","alias_value":"EN5RC7WIKPQZ","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"pith_short_16","alias_value":"EN5RC7WIKPQZSEUG","created_at":"2026-07-05T07:29:44Z"},{"alias_kind":"pith_short_8","alias_value":"EN5RC7WI","created_at":"2026-07-05T07:29:44Z"}],"graph_snapshots":[{"event_id":"sha256:08d44c3655bed84c935c567dae321854f96fd8eba4ccdbccdf0d14e2bdface01","target":"graph","created_at":"2026-07-05T07:29:44Z","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/2401.01529/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging. In contrast, humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. One simple way is to apply an action ","authors_text":"Ruiping Wang, Xilin Chen, Ziyi Bai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T03:51:16Z","title":"Glance and Focus: Memory Prompting for Multi-Event Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01529","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":"sha256:148b21e20958495b6f151115f646c66bdbfbd5559cf16bd63fe362b7b87f46e1","target":"record","created_at":"2026-07-05T07:29:44Z","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":"c75ea3ddc2044ca82fcd65aa013d8e226c9afb6a90cb065b849066a7f1e38861","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-01-03T03:51:16Z","title_canon_sha256":"90dc071df367dfa0049e8e2b6193e3d8cc5eeac809c0eab248596cbbc6b20f1c"},"schema_version":"1.0","source":{"id":"2401.01529","kind":"arxiv","version":1}},"canonical_sha256":"237b117ec853e19912862066b90bff6f29d2a8b8ecac16cef8602f2effec5346","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"237b117ec853e19912862066b90bff6f29d2a8b8ecac16cef8602f2effec5346","first_computed_at":"2026-07-05T07:29:44.649583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:44.649583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TQGRssP9DpAVqrtV96LVBwzlf/LcFIPm8mCrSBOIZx1MDMwSGJ2uH98c1uZouT7rzvTHdRbmAzkZvkXd6jXZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:44.650081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01529","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:148b21e20958495b6f151115f646c66bdbfbd5559cf16bd63fe362b7b87f46e1","sha256:08d44c3655bed84c935c567dae321854f96fd8eba4ccdbccdf0d14e2bdface01"],"state_sha256":"0966fe29d83ed031fefd2550826ee2a4546b1390670ea4c9796f3cd1782bbc27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gCNFtjs7nJVSo6vvbSbw8uHvIuKCT/HaLC0T7MJQtjDwxg3QtOjetlO5fdWP5Lb7X4//1ZSBBXVZkAHQWiLICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:14:51.935796Z","bundle_sha256":"8e5dc44c4d0c9ce2c7cafe8dba386f60f417d2f90172c291cb668cd6f7dc2135"}}