{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SQY7Y5BVNEZGYWDZ6APPTWJTSO","short_pith_number":"pith:SQY7Y5BV","schema_version":"1.0","canonical_sha256":"9431fc743569326c5879f01ef9d93393bbe387c8cc56f07000d5cdfbfc010ecd","source":{"kind":"arxiv","id":"2505.09118","version":1},"attestation_state":"computed","paper":{"title":"Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changmeng Zheng, Dayong Liang, Qing Li, Xiao-Yong Wei, Yi Cai, Zhiyuan Wen","submitted_at":"2025-05-14T04:04:23Z","abstract_excerpt":"Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes. This paper addresses two key challenges: (1) conventional detection-to-construction methods produce unfocused, contextually irrelevant relationship sets, and (2) existing approaches fail to form persistent memories for generalizing interaction reasoning to new scenes. We propose Interaction-augmented Scene Graph Reasoning (ISGR), a framework that enhances VLMs' interactional reasoning through three complementary components. Fi"},"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":"2505.09118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T04:04:23Z","cross_cats_sorted":[],"title_canon_sha256":"ad2184289fdae28ad7c44d92fdba0a913128e68732a8ef59a29d8cdb8ace69f3","abstract_canon_sha256":"ac2b4bec5824da27e52cec12e67b16139609454824f284aed9602d47f7aa3343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:50.635017Z","signature_b64":"X1RatDt/I7OR0O4jNDoi2xEGKdwe+KjmoqvGrl+gIfzd7xIeJ3BCTiKkHEgVDqjbIFk7Ta8+4tlNo9ytXlaADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9431fc743569326c5879f01ef9d93393bbe387c8cc56f07000d5cdfbfc010ecd","last_reissued_at":"2026-07-05T11:02:50.634450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:50.634450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changmeng Zheng, Dayong Liang, Qing Li, Xiao-Yong Wei, Yi Cai, Zhiyuan Wen","submitted_at":"2025-05-14T04:04:23Z","abstract_excerpt":"Traditional scene graphs primarily focus on spatial relationships, limiting vision-language models' (VLMs) ability to reason about complex interactions in visual scenes. This paper addresses two key challenges: (1) conventional detection-to-construction methods produce unfocused, contextually irrelevant relationship sets, and (2) existing approaches fail to form persistent memories for generalizing interaction reasoning to new scenes. We propose Interaction-augmented Scene Graph Reasoning (ISGR), a framework that enhances VLMs' interactional reasoning through three complementary components. Fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09118","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/2505.09118/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":"2505.09118","created_at":"2026-07-05T11:02:50.634523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09118v1","created_at":"2026-07-05T11:02:50.634523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09118","created_at":"2026-07-05T11:02:50.634523+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQY7Y5BVNEZG","created_at":"2026-07-05T11:02:50.634523+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQY7Y5BVNEZGYWDZ","created_at":"2026-07-05T11:02:50.634523+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQY7Y5BV","created_at":"2026-07-05T11:02:50.634523+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29425","citing_title":"Mixture of Debaters: Learn to Debate at Architectural Level in Multi-Agent Reasoning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO","json":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO.json","graph_json":"https://pith.science/api/pith-number/SQY7Y5BVNEZGYWDZ6APPTWJTSO/graph.json","events_json":"https://pith.science/api/pith-number/SQY7Y5BVNEZGYWDZ6APPTWJTSO/events.json","paper":"https://pith.science/paper/SQY7Y5BV"},"agent_actions":{"view_html":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO","download_json":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO.json","view_paper":"https://pith.science/paper/SQY7Y5BV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09118&json=true","fetch_graph":"https://pith.science/api/pith-number/SQY7Y5BVNEZGYWDZ6APPTWJTSO/graph.json","fetch_events":"https://pith.science/api/pith-number/SQY7Y5BVNEZGYWDZ6APPTWJTSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/action/storage_attestation","attest_author":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/action/author_attestation","sign_citation":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/action/citation_signature","submit_replication":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/action/replication_record"}},"created_at":"2026-07-05T11:02:50.634523+00:00","updated_at":"2026-07-05T11:02:50.634523+00:00"}