{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PLVTTP34VMXY46BDQSRLOSWVGD","short_pith_number":"pith:PLVTTP34","schema_version":"1.0","canonical_sha256":"7aeb39bf7cab2f8e782384a2b74ad530d71e57d7ae49ad6addfecd280fe0564c","source":{"kind":"arxiv","id":"2506.05787","version":2},"attestation_state":"computed","paper":{"title":"EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Giovanni Maria Farinella, Ivan Rodin, Kyle Min, Sharath Nittur Sridhar, Subarna Tripathi, Tz-Ying Wu","submitted_at":"2025-06-06T06:33:16Z","abstract_excerpt":"We introduce EASG-Bench, a question-answering benchmark for egocentric videos where the question-answering pairs are created from spatio-temporally grounded dynamic scene graphs capturing intricate relationships among actors, actions, and objects. We propose a systematic evaluation framework and evaluate several language-only and video large language models (video-LLMs) on this benchmark. We observe a performance gap in language-only and video-LLMs, especially on questions focusing on temporal ordering, thus identifying a research gap in the area of long-context video understanding. To promote"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.05787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T06:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"79b14cdcf88ab54ff9a2ab693d12ffacd0f1bd19c4bce1748219de7041cfb595","abstract_canon_sha256":"edc751ddb9d31b7ad6606a6ba50d9543921e53fc81cfd8b7319ba405e704eba2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:26.581109Z","signature_b64":"/W481X2eOto7Wi4ZfVVSEOcEXA+Sw4DLK9xWN7c0ufUI4KmGDcd6vYkkToQTtz7GmKwOgU/EkbSmBnGmCA9IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aeb39bf7cab2f8e782384a2b74ad530d71e57d7ae49ad6addfecd280fe0564c","last_reissued_at":"2026-07-05T11:48:26.580322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:26.580322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EASG-Bench: Video Q&A Benchmark with Egocentric Action Scene Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonino Furnari, Giovanni Maria Farinella, Ivan Rodin, Kyle Min, Sharath Nittur Sridhar, Subarna Tripathi, Tz-Ying Wu","submitted_at":"2025-06-06T06:33:16Z","abstract_excerpt":"We introduce EASG-Bench, a question-answering benchmark for egocentric videos where the question-answering pairs are created from spatio-temporally grounded dynamic scene graphs capturing intricate relationships among actors, actions, and objects. We propose a systematic evaluation framework and evaluate several language-only and video large language models (video-LLMs) on this benchmark. We observe a performance gap in language-only and video-LLMs, especially on questions focusing on temporal ordering, thus identifying a research gap in the area of long-context video understanding. To promote"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05787","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/2506.05787/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.05787","created_at":"2026-07-05T11:48:26.580389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05787v2","created_at":"2026-07-05T11:48:26.580389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05787","created_at":"2026-07-05T11:48:26.580389+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLVTTP34VMXY","created_at":"2026-07-05T11:48:26.580389+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLVTTP34VMXY46BD","created_at":"2026-07-05T11:48:26.580389+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLVTTP34","created_at":"2026-07-05T11:48:26.580389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.14122","citing_title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD","json":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD.json","graph_json":"https://pith.science/api/pith-number/PLVTTP34VMXY46BDQSRLOSWVGD/graph.json","events_json":"https://pith.science/api/pith-number/PLVTTP34VMXY46BDQSRLOSWVGD/events.json","paper":"https://pith.science/paper/PLVTTP34"},"agent_actions":{"view_html":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD","download_json":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD.json","view_paper":"https://pith.science/paper/PLVTTP34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05787&json=true","fetch_graph":"https://pith.science/api/pith-number/PLVTTP34VMXY46BDQSRLOSWVGD/graph.json","fetch_events":"https://pith.science/api/pith-number/PLVTTP34VMXY46BDQSRLOSWVGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD/action/storage_attestation","attest_author":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD/action/author_attestation","sign_citation":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD/action/citation_signature","submit_replication":"https://pith.science/pith/PLVTTP34VMXY46BDQSRLOSWVGD/action/replication_record"}},"created_at":"2026-07-05T11:48:26.580389+00:00","updated_at":"2026-07-05T11:48:26.580389+00:00"}