{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JDXPPQZJUVVUTSYIQRGOPWHBCA","short_pith_number":"pith:JDXPPQZJ","canonical_record":{"source":{"id":"2412.19304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:53:14Z","cross_cats_sorted":[],"title_canon_sha256":"d47972af7df4285227b8568bac43317afb93f95ba403b6ca0835eb26f3244adb","abstract_canon_sha256":"6d9069b3175e5f72ee91b70efed9840154d34b5a0b12b12bb695d735e4eda5ba"},"schema_version":"1.0"},"canonical_sha256":"48eef7c329a56b49cb08844ce7d8e110203aad47c8e10037f8e5cea5a8479621","source":{"kind":"arxiv","id":"2412.19304","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19304","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19304v1","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19304","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"JDXPPQZJUVVU","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"JDXPPQZJUVVUTSYI","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"JDXPPQZJ","created_at":"2026-07-05T09:54:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JDXPPQZJUVVUTSYIQRGOPWHBCA","target":"record","payload":{"canonical_record":{"source":{"id":"2412.19304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:53:14Z","cross_cats_sorted":[],"title_canon_sha256":"d47972af7df4285227b8568bac43317afb93f95ba403b6ca0835eb26f3244adb","abstract_canon_sha256":"6d9069b3175e5f72ee91b70efed9840154d34b5a0b12b12bb695d735e4eda5ba"},"schema_version":"1.0"},"canonical_sha256":"48eef7c329a56b49cb08844ce7d8e110203aad47c8e10037f8e5cea5a8479621","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:33.723138Z","signature_b64":"JlJFoWmmjw2tZZaPeUvIDLKUnFLW8ZRS0PaWGzsfArx+hRBLp9z6U9W9lu+brgMTU0auaIVvx0TsCMGqFY7DCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48eef7c329a56b49cb08844ce7d8e110203aad47c8e10037f8e5cea5a8479621","last_reissued_at":"2026-07-05T09:54:33.722660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:33.722660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.19304","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":"2026-07-05T09:54:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b57T9apPJK8qa+M2qYnHAEAa6+Mus3LzRwvcyg9bdO/w/4KxZg+Z8iIKOSPCkp3vizD5IgX4m5iYirP9xQXSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:27:56.010277Z"},"content_sha256":"6fe71626c651568e374fa1006aeb93e42827b129b17ebf5abd0a840533cd786f","schema_version":"1.0","event_id":"sha256:6fe71626c651568e374fa1006aeb93e42827b129b17ebf5abd0a840533cd786f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JDXPPQZJUVVUTSYIQRGOPWHBCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gengyuan Zhang, Lorenzo Baraldi, Rajat Koner, Rita Cucchiara, Roberto Amoroso, Volker Tresp","submitted_at":"2024-12-26T17:53:14Z","abstract_excerpt":"Video Question Answering (Video QA) is a challenging video understanding task that requires models to comprehend entire videos, identify the most relevant information based on contextual cues from a given question, and reason accurately to provide answers. Recent advancements in Multimodal Large Language Models (MLLMs) have transformed video QA by leveraging their exceptional commonsense reasoning capabilities. This progress is largely driven by the effective alignment between visual data and the language space of MLLMs. However, for video QA, an additional space-time alignment poses a conside"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19304","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/2412.19304/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":"2026-07-05T09:54:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxytJY/XwKCSEEMP/4lyT0TFkIu2SBEZdtTZTh6Gb/7TbHymCvhxfC8KzvuxwpRKebybspzkMmmuXtuBqbd/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:27:56.010896Z"},"content_sha256":"674db38e786c08315f1f6c84b3e604a5b4a82b40572ce49119cf32af508ec3aa","schema_version":"1.0","event_id":"sha256:674db38e786c08315f1f6c84b3e604a5b4a82b40572ce49119cf32af508ec3aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA/bundle.json","state_url":"https://pith.science/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA/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":"2026-08-04T17:27:56Z","links":{"resolver":"https://pith.science/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA","bundle":"https://pith.science/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA/bundle.json","state":"https://pith.science/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JDXPPQZJUVVUTSYIQRGOPWHBCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JDXPPQZJUVVUTSYIQRGOPWHBCA","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":"6d9069b3175e5f72ee91b70efed9840154d34b5a0b12b12bb695d735e4eda5ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:53:14Z","title_canon_sha256":"d47972af7df4285227b8568bac43317afb93f95ba403b6ca0835eb26f3244adb"},"schema_version":"1.0","source":{"id":"2412.19304","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.19304","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.19304v1","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19304","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_12","alias_value":"JDXPPQZJUVVU","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_16","alias_value":"JDXPPQZJUVVUTSYI","created_at":"2026-07-05T09:54:33Z"},{"alias_kind":"pith_short_8","alias_value":"JDXPPQZJ","created_at":"2026-07-05T09:54:33Z"}],"graph_snapshots":[{"event_id":"sha256:674db38e786c08315f1f6c84b3e604a5b4a82b40572ce49119cf32af508ec3aa","target":"graph","created_at":"2026-07-05T09:54:33Z","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/2412.19304/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Question Answering (Video QA) is a challenging video understanding task that requires models to comprehend entire videos, identify the most relevant information based on contextual cues from a given question, and reason accurately to provide answers. Recent advancements in Multimodal Large Language Models (MLLMs) have transformed video QA by leveraging their exceptional commonsense reasoning capabilities. This progress is largely driven by the effective alignment between visual data and the language space of MLLMs. However, for video QA, an additional space-time alignment poses a conside","authors_text":"Gengyuan Zhang, Lorenzo Baraldi, Rajat Koner, Rita Cucchiara, Roberto Amoroso, Volker Tresp","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:53:14Z","title":"Perceive, Query & Reason: Enhancing Video QA with Question-Guided Temporal Queries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19304","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":"sha256:6fe71626c651568e374fa1006aeb93e42827b129b17ebf5abd0a840533cd786f","target":"record","created_at":"2026-07-05T09:54:33Z","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":"6d9069b3175e5f72ee91b70efed9840154d34b5a0b12b12bb695d735e4eda5ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T17:53:14Z","title_canon_sha256":"d47972af7df4285227b8568bac43317afb93f95ba403b6ca0835eb26f3244adb"},"schema_version":"1.0","source":{"id":"2412.19304","kind":"arxiv","version":1}},"canonical_sha256":"48eef7c329a56b49cb08844ce7d8e110203aad47c8e10037f8e5cea5a8479621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48eef7c329a56b49cb08844ce7d8e110203aad47c8e10037f8e5cea5a8479621","first_computed_at":"2026-07-05T09:54:33.722660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:33.722660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JlJFoWmmjw2tZZaPeUvIDLKUnFLW8ZRS0PaWGzsfArx+hRBLp9z6U9W9lu+brgMTU0auaIVvx0TsCMGqFY7DCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:33.723138Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.19304","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fe71626c651568e374fa1006aeb93e42827b129b17ebf5abd0a840533cd786f","sha256:674db38e786c08315f1f6c84b3e604a5b4a82b40572ce49119cf32af508ec3aa"],"state_sha256":"762f32ddfd4cec915de07da245de10ea59558007fa1913d9c49eb66872f413f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5HaKfOXg5UcnNUo3sU/xQFrHDmNPCxDLmn00gLW/sq2I453U9YsI+sqo8qPiyKR9gdawyuaW55aE+0QAnrQBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:27:56.016700Z","bundle_sha256":"0c7a0bb5ed9e048237c54df8a09baddb307165c0c897681bea5f25d042a90d51"}}