{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3FWXPW5GTJIZVIADYZG33LHTFQ","short_pith_number":"pith:3FWXPW5G","schema_version":"1.0","canonical_sha256":"d96d77dba69a519aa003c64dbdacf32c370ed5bb92aa3391e067973ed7f8bb5b","source":{"kind":"arxiv","id":"2311.06553","version":1},"attestation_state":"computed","paper":{"title":"Visual Commonsense based Heterogeneous Graph Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiangyu Zhu, Xi Zhang, Zhaoxiang Zhang, Zhen Lei, Zongzhao Li","submitted_at":"2023-11-11T12:01:18Z","abstract_excerpt":"How to select relevant key objects and reason about the complex relationships cross vision and linguistic domain are two key issues in many multi-modality applications such as visual question answering (VQA). In this work, we incorporate the visual commonsense information and propose a heterogeneous graph contrastive learning method to better finish the visual reasoning task. Our method is designed as a plug-and-play way, so that it can be quickly and easily combined with a wide range of representative methods. Specifically, our model contains two key components: the Commonsense-based Contrast"},"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":"2311.06553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T12:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"8a0ff9fbb0c3101ea89970d53ca5b25c9f93c0c86b776b2281f882cdf8ebaad4","abstract_canon_sha256":"147d50e0c87726b1bcb160fff1a733db84d9293ded7de58d38e7d31fa1590349"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:41.898255Z","signature_b64":"TDWXfQCgETmssUJ39xQHMwcut5klNGfEPwLvPdzll/Xh5Ilx5BbYUAM25g3sIW9HiedKNFvikMymkHQSbwzKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d96d77dba69a519aa003c64dbdacf32c370ed5bb92aa3391e067973ed7f8bb5b","last_reissued_at":"2026-07-05T07:11:41.897805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:41.897805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Commonsense based Heterogeneous Graph Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiangyu Zhu, Xi Zhang, Zhaoxiang Zhang, Zhen Lei, Zongzhao Li","submitted_at":"2023-11-11T12:01:18Z","abstract_excerpt":"How to select relevant key objects and reason about the complex relationships cross vision and linguistic domain are two key issues in many multi-modality applications such as visual question answering (VQA). In this work, we incorporate the visual commonsense information and propose a heterogeneous graph contrastive learning method to better finish the visual reasoning task. Our method is designed as a plug-and-play way, so that it can be quickly and easily combined with a wide range of representative methods. Specifically, our model contains two key components: the Commonsense-based Contrast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06553","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/2311.06553/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":"2311.06553","created_at":"2026-07-05T07:11:41.897862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06553v1","created_at":"2026-07-05T07:11:41.897862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06553","created_at":"2026-07-05T07:11:41.897862+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FWXPW5GTJIZ","created_at":"2026-07-05T07:11:41.897862+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FWXPW5GTJIZVIAD","created_at":"2026-07-05T07:11:41.897862+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FWXPW5G","created_at":"2026-07-05T07:11:41.897862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00711","citing_title":"VIKSER: Visual Knowledge-Driven Self-Reinforcing Reasoning Framework","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ","json":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ.json","graph_json":"https://pith.science/api/pith-number/3FWXPW5GTJIZVIADYZG33LHTFQ/graph.json","events_json":"https://pith.science/api/pith-number/3FWXPW5GTJIZVIADYZG33LHTFQ/events.json","paper":"https://pith.science/paper/3FWXPW5G"},"agent_actions":{"view_html":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ","download_json":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ.json","view_paper":"https://pith.science/paper/3FWXPW5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06553&json=true","fetch_graph":"https://pith.science/api/pith-number/3FWXPW5GTJIZVIADYZG33LHTFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3FWXPW5GTJIZVIADYZG33LHTFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/action/storage_attestation","attest_author":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/action/author_attestation","sign_citation":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/action/citation_signature","submit_replication":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/action/replication_record"}},"created_at":"2026-07-05T07:11:41.897862+00:00","updated_at":"2026-07-05T07:11:41.897862+00:00"}