{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3FWXPW5GTJIZVIADYZG33LHTFQ","short_pith_number":"pith:3FWXPW5G","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"},"canonical_sha256":"d96d77dba69a519aa003c64dbdacf32c370ed5bb92aa3391e067973ed7f8bb5b","source":{"kind":"arxiv","id":"2311.06553","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06553","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06553v1","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06553","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"3FWXPW5GTJIZ","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"3FWXPW5GTJIZVIAD","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"3FWXPW5G","created_at":"2026-07-05T07:11:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3FWXPW5GTJIZVIADYZG33LHTFQ","target":"record","payload":{"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"},"canonical_sha256":"d96d77dba69a519aa003c64dbdacf32c370ed5bb92aa3391e067973ed7f8bb5b","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"},"source_kind":"arxiv","source_id":"2311.06553","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":"2026-07-05T07:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6WH4Q/4D4/jShCYQ5oDnTQcrgd4haLpYQ0h0hj4gXjXcLeO6z++BHWmbawe64KntByAbsAnQzrb8Mb3pCCVhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:45:19.329210Z"},"content_sha256":"d9cea647d6f61c0f4fed5176345389e199d623b05dac17b1c37cda987dd008f6","schema_version":"1.0","event_id":"sha256:d9cea647d6f61c0f4fed5176345389e199d623b05dac17b1c37cda987dd008f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3FWXPW5GTJIZVIADYZG33LHTFQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NyrK7OmdgVsxAaeupNZvOP2lJx8zY2Eqdhgw/60wRvpRBgdFfUnmijy+UWodDmKiY3s3IOVQ65vzLcZmMjDeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T23:45:19.329727Z"},"content_sha256":"9e0e0758ed495ec889922147df65fadcade25b95c7827546a90efca10536317d","schema_version":"1.0","event_id":"sha256:9e0e0758ed495ec889922147df65fadcade25b95c7827546a90efca10536317d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/bundle.json","state_url":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/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":"2026-08-10T23:45:19Z","links":{"resolver":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ","bundle":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/bundle.json","state":"https://pith.science/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FWXPW5GTJIZVIADYZG33LHTFQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3FWXPW5GTJIZVIADYZG33LHTFQ","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":"147d50e0c87726b1bcb160fff1a733db84d9293ded7de58d38e7d31fa1590349","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T12:01:18Z","title_canon_sha256":"8a0ff9fbb0c3101ea89970d53ca5b25c9f93c0c86b776b2281f882cdf8ebaad4"},"schema_version":"1.0","source":{"id":"2311.06553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06553","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06553v1","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06553","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"3FWXPW5GTJIZ","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"3FWXPW5GTJIZVIAD","created_at":"2026-07-05T07:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"3FWXPW5G","created_at":"2026-07-05T07:11:41Z"}],"graph_snapshots":[{"event_id":"sha256:9e0e0758ed495ec889922147df65fadcade25b95c7827546a90efca10536317d","target":"graph","created_at":"2026-07-05T07:11:41Z","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/2311.06553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Xiangyu Zhu, Xi Zhang, Zhaoxiang Zhang, Zhen Lei, Zongzhao Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T12:01:18Z","title":"Visual Commonsense based Heterogeneous Graph Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06553","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:d9cea647d6f61c0f4fed5176345389e199d623b05dac17b1c37cda987dd008f6","target":"record","created_at":"2026-07-05T07:11:41Z","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":"147d50e0c87726b1bcb160fff1a733db84d9293ded7de58d38e7d31fa1590349","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-11T12:01:18Z","title_canon_sha256":"8a0ff9fbb0c3101ea89970d53ca5b25c9f93c0c86b776b2281f882cdf8ebaad4"},"schema_version":"1.0","source":{"id":"2311.06553","kind":"arxiv","version":1}},"canonical_sha256":"d96d77dba69a519aa003c64dbdacf32c370ed5bb92aa3391e067973ed7f8bb5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d96d77dba69a519aa003c64dbdacf32c370ed5bb92aa3391e067973ed7f8bb5b","first_computed_at":"2026-07-05T07:11:41.897805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:41.897805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDWXfQCgETmssUJ39xQHMwcut5klNGfEPwLvPdzll/Xh5Ilx5BbYUAM25g3sIW9HiedKNFvikMymkHQSbwzKBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:41.898255Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9cea647d6f61c0f4fed5176345389e199d623b05dac17b1c37cda987dd008f6","sha256:9e0e0758ed495ec889922147df65fadcade25b95c7827546a90efca10536317d"],"state_sha256":"2de35e4154f36abe7e2f64e9f5ab009a34dc8eb546761d16c00edd4925834b5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQGe0tNIC/ehEnBmwIF6FGlvV9aPY0muQrGbPzkFQwHyi/jjCvJI0DtIYbq3ayoWWuNFZV+mfgFDKoU+jHXADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T23:45:19.342648Z","bundle_sha256":"8080916122e1b2ef7008371b4f0663d05a0c4e32af7edf13fee6a1de8dc1a879"}}