{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ICQDMSFSA7DB7PQ7DAKKSK6ASO","short_pith_number":"pith:ICQDMSFS","schema_version":"1.0","canonical_sha256":"40a03648b207c61fbe1f1814a92bc093bddf3646f564e836923b2f9b6417a3c6","source":{"kind":"arxiv","id":"2506.08553","version":1},"attestation_state":"computed","paper":{"title":"From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agnese Taluzzi, Chiara Plizzari, Davide Gesualdi, Francesca Palermo, Matteo Matteucci, Riccardo Santambrogio, Simone Mentasti","submitted_at":"2025-06-10T08:21:38Z","abstract_excerpt":"This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relationships, and temporally grounded events. In parallel, KnowledgeNet incorporates ConceptNet's external commonsense knowledge to introduce high-level semantic connections between entities, enabling reasoning beyond directly observable visual evidence. Each method demonstrates distinct strengths across the seven categories of the HD-EPIC benchm"},"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":"2506.08553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-10T08:21:38Z","cross_cats_sorted":[],"title_canon_sha256":"7e0b0d91ad828caec4c7948a26f360104df154237f709a976a5a8e859030aa3e","abstract_canon_sha256":"837f8d787d0c917bd2b059f7dd250da4fc5ebf9d6b36a3ca1e60ea477843a9fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:09.611021Z","signature_b64":"jjPl++2fsU5v2PucV6v6k3t2WFvv3PaG5CZmn63yy0iPs6GfBvzqcBJfrSwrzuvqZpXm2ZjHLNBDKvk4x9nTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40a03648b207c61fbe1f1814a92bc093bddf3646f564e836923b2f9b6417a3c6","last_reissued_at":"2026-07-05T11:19:09.610545Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:09.610545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Pixels to Graphs: using Scene and Knowledge Graphs for HD-EPIC VQA Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Agnese Taluzzi, Chiara Plizzari, Davide Gesualdi, Francesca Palermo, Matteo Matteucci, Riccardo Santambrogio, Simone Mentasti","submitted_at":"2025-06-10T08:21:38Z","abstract_excerpt":"This report presents SceneNet and KnowledgeNet, our approaches developed for the HD-EPIC VQA Challenge 2025. SceneNet leverages scene graphs generated with a multi-modal large language model (MLLM) to capture fine-grained object interactions, spatial relationships, and temporally grounded events. In parallel, KnowledgeNet incorporates ConceptNet's external commonsense knowledge to introduce high-level semantic connections between entities, enabling reasoning beyond directly observable visual evidence. Each method demonstrates distinct strengths across the seven categories of the HD-EPIC benchm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08553","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/2506.08553/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":"2506.08553","created_at":"2026-07-05T11:19:09.610599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08553v1","created_at":"2026-07-05T11:19:09.610599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08553","created_at":"2026-07-05T11:19:09.610599+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICQDMSFSA7DB","created_at":"2026-07-05T11:19:09.610599+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICQDMSFSA7DB7PQ7","created_at":"2026-07-05T11:19:09.610599+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICQDMSFS","created_at":"2026-07-05T11:19:09.610599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31187","citing_title":"Learning to Deny: Action Denial in Multimodal Large Language Models","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO","json":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO.json","graph_json":"https://pith.science/api/pith-number/ICQDMSFSA7DB7PQ7DAKKSK6ASO/graph.json","events_json":"https://pith.science/api/pith-number/ICQDMSFSA7DB7PQ7DAKKSK6ASO/events.json","paper":"https://pith.science/paper/ICQDMSFS"},"agent_actions":{"view_html":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO","download_json":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO.json","view_paper":"https://pith.science/paper/ICQDMSFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08553&json=true","fetch_graph":"https://pith.science/api/pith-number/ICQDMSFSA7DB7PQ7DAKKSK6ASO/graph.json","fetch_events":"https://pith.science/api/pith-number/ICQDMSFSA7DB7PQ7DAKKSK6ASO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO/action/storage_attestation","attest_author":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO/action/author_attestation","sign_citation":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO/action/citation_signature","submit_replication":"https://pith.science/pith/ICQDMSFSA7DB7PQ7DAKKSK6ASO/action/replication_record"}},"created_at":"2026-07-05T11:19:09.610599+00:00","updated_at":"2026-07-05T11:19:09.610599+00:00"}