{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SQY7Y5BVNEZGYWDZ6APPTWJTSO","short_pith_number":"pith:SQY7Y5BV","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"},"canonical_sha256":"9431fc743569326c5879f01ef9d93393bbe387c8cc56f07000d5cdfbfc010ecd","source":{"kind":"arxiv","id":"2505.09118","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SQY7Y5BVNEZGYWDZ6APPTWJTSO","target":"record","payload":{"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"},"canonical_sha256":"9431fc743569326c5879f01ef9d93393bbe387c8cc56f07000d5cdfbfc010ecd","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"},"source_kind":"arxiv","source_id":"2505.09118","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":"2026-07-05T11:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4fk4Alq+5/PgkuvmkMlxynyEy/TyUvNGbdWrWdodL32m76JGw7lmP0eEQNTejkA4EzX7p98CBdmpTmNQztyOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:23:04.077120Z"},"content_sha256":"55bb2df20b577bf62f8b00d8f87130bf803214d0572fa83897a1b3b2f71fc1f0","schema_version":"1.0","event_id":"sha256:55bb2df20b577bf62f8b00d8f87130bf803214d0572fa83897a1b3b2f71fc1f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SQY7Y5BVNEZGYWDZ6APPTWJTSO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yeAG0awo6fbg/ZiWCpjTFvdyC/YV3lLSHqrir0ImXJztZWZG8XKS4p+VIDvMhfv25+B7nnp+ML+rqDFARklTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:23:04.077710Z"},"content_sha256":"3c6ccfd9c52f39ad45f841b696a6e7bf2dd1a08cc201f6db5e32d2c262b7de16","schema_version":"1.0","event_id":"sha256:3c6ccfd9c52f39ad45f841b696a6e7bf2dd1a08cc201f6db5e32d2c262b7de16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/bundle.json","state_url":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/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":"2026-08-18T20:23:04Z","links":{"resolver":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO","bundle":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/bundle.json","state":"https://pith.science/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQY7Y5BVNEZGYWDZ6APPTWJTSO/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3+CAgt0i2XiiKBvrIpQIvzPkbGBCd6/kUy7+DhWOmNoL4aBbg11yIqp0Hsf/eYzz0FYjY76KRLLSV5DuXPOAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:23:04.082118Z","bundle_sha256":"4a47cc2cac050428fd56408eb6fe7dfe8480edd2435269607e69e212f883675d"}}