{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:565CJGELNG3CBJKZO7UH3ZEEMI","short_pith_number":"pith:565CJGEL","canonical_record":{"source":{"id":"2508.03009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T02:28:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7266f8819e35830d544f0909ee3e03d057d937d5181a6297efafa742d4ddf91","abstract_canon_sha256":"ac031836f90928413684593f088585861259d699b3052220b4612231dcee98c7"},"schema_version":"1.0"},"canonical_sha256":"efba24988b69b620a55977e87de484621dcff217ba3f79f83304a263b965021a","source":{"kind":"arxiv","id":"2508.03009","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03009","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03009v1","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03009","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"565CJGELNG3C","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"565CJGELNG3CBJKZ","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"565CJGEL","created_at":"2026-07-05T11:48:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:565CJGELNG3CBJKZO7UH3ZEEMI","target":"record","payload":{"canonical_record":{"source":{"id":"2508.03009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T02:28:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c7266f8819e35830d544f0909ee3e03d057d937d5181a6297efafa742d4ddf91","abstract_canon_sha256":"ac031836f90928413684593f088585861259d699b3052220b4612231dcee98c7"},"schema_version":"1.0"},"canonical_sha256":"efba24988b69b620a55977e87de484621dcff217ba3f79f83304a263b965021a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:34.780580Z","signature_b64":"lDCehUJazCjisTteO7s1Q3T2T3GEhBAeXCbZ5uQMe03wR5Rzd2zShuP0Rw2JSS/Mo+a5MJqRNll751/stDZHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efba24988b69b620a55977e87de484621dcff217ba3f79f83304a263b965021a","last_reissued_at":"2026-07-05T11:48:34.780052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:34.780052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.03009","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":"2026-07-05T11:48:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6GNA/t+MEZKQaaptoC7SN8MzVQ6u90zXXOTU6CIS6UIzY4Um9d5ptE7raPcB4fJeWxCrV7HZSNEBhH/9ffkDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:53:24.429640Z"},"content_sha256":"67a0effc939385b3640c1c2e5bd6065e246df3ba4ac79965c69d9c29408350c9","schema_version":"1.0","event_id":"sha256:67a0effc939385b3640c1c2e5bd6065e246df3ba4ac79965c69d9c29408350c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:565CJGELNG3CBJKZO7UH3ZEEMI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Long Video Question Answering with Scene-Localized Frame Grouping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fei Ma, Fei Yu, Hongbo Jin, Hongbo Xu, Lin Liu, Wenhao Zhang, Xuyi Yang, Yongwei Nie","submitted_at":"2025-08-05T02:28:58Z","abstract_excerpt":"Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video frames and their associated information. Efficiently extracting relevant information becomes a challenging task. Existing frameworks and evaluation tasks focus on identifying specific frames containing core objects from a large number of irrelevant frames, which does not align with the practical needs of real-world applications. To address this issue, we propose a new scenario under the video question-answering task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03009","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/2508.03009/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":"2026-07-05T11:48:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xojd0awFIK/4JYKutA/WWF3kLjBWrp6Fo//94MaRTPK7gItO0zWzNWJGVeleB2N92Yg4/8twPY3pkxUWJ80jCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:53:24.430593Z"},"content_sha256":"18951bbe35cdf49605e1734aeba84232de03822dd363c1c4c9c692e913cbff82","schema_version":"1.0","event_id":"sha256:18951bbe35cdf49605e1734aeba84232de03822dd363c1c4c9c692e913cbff82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/565CJGELNG3CBJKZO7UH3ZEEMI/bundle.json","state_url":"https://pith.science/pith/565CJGELNG3CBJKZO7UH3ZEEMI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/565CJGELNG3CBJKZO7UH3ZEEMI/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":"2026-08-06T07:53:24Z","links":{"resolver":"https://pith.science/pith/565CJGELNG3CBJKZO7UH3ZEEMI","bundle":"https://pith.science/pith/565CJGELNG3CBJKZO7UH3ZEEMI/bundle.json","state":"https://pith.science/pith/565CJGELNG3CBJKZO7UH3ZEEMI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/565CJGELNG3CBJKZO7UH3ZEEMI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:565CJGELNG3CBJKZO7UH3ZEEMI","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":"ac031836f90928413684593f088585861259d699b3052220b4612231dcee98c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T02:28:58Z","title_canon_sha256":"c7266f8819e35830d544f0909ee3e03d057d937d5181a6297efafa742d4ddf91"},"schema_version":"1.0","source":{"id":"2508.03009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.03009","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"arxiv_version","alias_value":"2508.03009v1","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.03009","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_12","alias_value":"565CJGELNG3C","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_16","alias_value":"565CJGELNG3CBJKZ","created_at":"2026-07-05T11:48:34Z"},{"alias_kind":"pith_short_8","alias_value":"565CJGEL","created_at":"2026-07-05T11:48:34Z"}],"graph_snapshots":[{"event_id":"sha256:18951bbe35cdf49605e1734aeba84232de03822dd363c1c4c9c692e913cbff82","target":"graph","created_at":"2026-07-05T11:48:34Z","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/2508.03009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current Multimodal Large Language Models (MLLMs) often perform poorly in long video understanding, primarily due to resource limitations that prevent them from processing all video frames and their associated information. Efficiently extracting relevant information becomes a challenging task. Existing frameworks and evaluation tasks focus on identifying specific frames containing core objects from a large number of irrelevant frames, which does not align with the practical needs of real-world applications. To address this issue, we propose a new scenario under the video question-answering task","authors_text":"Fei Ma, Fei Yu, Hongbo Jin, Hongbo Xu, Lin Liu, Wenhao Zhang, Xuyi Yang, Yongwei Nie","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T02:28:58Z","title":"Enhancing Long Video Question Answering with Scene-Localized Frame Grouping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.03009","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":"sha256:67a0effc939385b3640c1c2e5bd6065e246df3ba4ac79965c69d9c29408350c9","target":"record","created_at":"2026-07-05T11:48:34Z","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":"ac031836f90928413684593f088585861259d699b3052220b4612231dcee98c7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-05T02:28:58Z","title_canon_sha256":"c7266f8819e35830d544f0909ee3e03d057d937d5181a6297efafa742d4ddf91"},"schema_version":"1.0","source":{"id":"2508.03009","kind":"arxiv","version":1}},"canonical_sha256":"efba24988b69b620a55977e87de484621dcff217ba3f79f83304a263b965021a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efba24988b69b620a55977e87de484621dcff217ba3f79f83304a263b965021a","first_computed_at":"2026-07-05T11:48:34.780052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:48:34.780052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lDCehUJazCjisTteO7s1Q3T2T3GEhBAeXCbZ5uQMe03wR5Rzd2zShuP0Rw2JSS/Mo+a5MJqRNll751/stDZHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:48:34.780580Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.03009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67a0effc939385b3640c1c2e5bd6065e246df3ba4ac79965c69d9c29408350c9","sha256:18951bbe35cdf49605e1734aeba84232de03822dd363c1c4c9c692e913cbff82"],"state_sha256":"caaadcfa96450dd0db48ced93c354eab45d295b282636bd8fa0ee7c7367f20c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BxAZowHVAnd5bEtTUYEklcScafZe0ThzyfrRow02p0gtmjo/o8r125TQtpRrxEzJfaVZjvfNpeVYpEqosaZqCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:53:24.438124Z","bundle_sha256":"078ab6d820c83c8bd4de515f89f38ac67f45576f9949787f9d16daed3ef38491"}}