{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQY7Y5BVNEZGYWDZ6APPTWJTSO","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":"ac2b4bec5824da27e52cec12e67b16139609454824f284aed9602d47f7aa3343","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T04:04:23Z","title_canon_sha256":"ad2184289fdae28ad7c44d92fdba0a913128e68732a8ef59a29d8cdb8ace69f3"},"schema_version":"1.0","source":{"id":"2505.09118","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09118","created_at":"2026-07-05T11:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09118v1","created_at":"2026-07-05T11:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09118","created_at":"2026-07-05T11:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"SQY7Y5BVNEZG","created_at":"2026-07-05T11:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"SQY7Y5BVNEZGYWDZ","created_at":"2026-07-05T11:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"SQY7Y5BV","created_at":"2026-07-05T11:02:50Z"}],"graph_snapshots":[{"event_id":"sha256:3c6ccfd9c52f39ad45f841b696a6e7bf2dd1a08cc201f6db5e32d2c262b7de16","target":"graph","created_at":"2026-07-05T11:02:50Z","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/2505.09118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changmeng Zheng, Dayong Liang, Qing Li, Xiao-Yong Wei, Yi Cai, Zhiyuan Wen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T04:04:23Z","title":"Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09118","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":"sha256:55bb2df20b577bf62f8b00d8f87130bf803214d0572fa83897a1b3b2f71fc1f0","target":"record","created_at":"2026-07-05T11:02:50Z","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":"ac2b4bec5824da27e52cec12e67b16139609454824f284aed9602d47f7aa3343","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T04:04:23Z","title_canon_sha256":"ad2184289fdae28ad7c44d92fdba0a913128e68732a8ef59a29d8cdb8ace69f3"},"schema_version":"1.0","source":{"id":"2505.09118","kind":"arxiv","version":1}},"canonical_sha256":"9431fc743569326c5879f01ef9d93393bbe387c8cc56f07000d5cdfbfc010ecd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9431fc743569326c5879f01ef9d93393bbe387c8cc56f07000d5cdfbfc010ecd","first_computed_at":"2026-07-05T11:02:50.634450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:50.634450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X1RatDt/I7OR0O4jNDoi2xEGKdwe+KjmoqvGrl+gIfzd7xIeJ3BCTiKkHEgVDqjbIFk7Ta8+4tlNo9ytXlaADg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:50.635017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09118","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55bb2df20b577bf62f8b00d8f87130bf803214d0572fa83897a1b3b2f71fc1f0","sha256:3c6ccfd9c52f39ad45f841b696a6e7bf2dd1a08cc201f6db5e32d2c262b7de16"],"state_sha256":"4d9d08f136349717db16eb9165329b48c0e46a821cdb6a977b4cf5d7c8a3d5d9"}