{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BGBALTQVLD45ZPYP36QGEBLD2H","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":"3982ca9593735814a747f2afef4662a11db89cb984c7a46910a7d279c8b70052","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T10:40:25Z","title_canon_sha256":"a7458ba6fac8363b2df4777cc98f90dd74de7c4e31aab086d76ac3428d097334"},"schema_version":"1.0","source":{"id":"2308.09455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.09455","created_at":"2026-07-05T06:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2308.09455v1","created_at":"2026-07-05T06:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09455","created_at":"2026-07-05T06:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"BGBALTQVLD45","created_at":"2026-07-05T06:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"BGBALTQVLD45ZPYP","created_at":"2026-07-05T06:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"BGBALTQV","created_at":"2026-07-05T06:42:32Z"}],"graph_snapshots":[{"event_id":"sha256:7dab8cb3d087f0c503380f28e830afbc489655e0b4ebb356f2b05db5b8af010c","target":"graph","created_at":"2026-07-05T06:42:32Z","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/2308.09455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success of self-supervised learning, multimodal foundation models have rapidly adapted a wide range of downstream tasks driven by vision and language (VL) pretraining. State-of-the-art methods achieve impressive performance by pre-training on large-scale datasets. However, bridging the semantic gap between the two modalities remains a nonnegligible challenge for VL tasks. In this work, we propose an efficient computation framework for multimodal alignment by introducing a novel visual semantic module to further improve the performance of the VL tasks. Specifically, we propose a flexib","authors_text":"Haoran Wang, Siyu Zhang, Weijian Liang, Yaoru Sun, Yeming Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T10:40:25Z","title":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09455","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":"sha256:0a31097f9cadcdadd5fc27792b1782af80d889f2d9257bd9b4e59b0e4c7741e7","target":"record","created_at":"2026-07-05T06:42:32Z","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":"3982ca9593735814a747f2afef4662a11db89cb984c7a46910a7d279c8b70052","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T10:40:25Z","title_canon_sha256":"a7458ba6fac8363b2df4777cc98f90dd74de7c4e31aab086d76ac3428d097334"},"schema_version":"1.0","source":{"id":"2308.09455","kind":"arxiv","version":1}},"canonical_sha256":"098205ce1558f9dcbf0fdfa0620563d1e01c7bfb73ce8fe705d409024852460e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"098205ce1558f9dcbf0fdfa0620563d1e01c7bfb73ce8fe705d409024852460e","first_computed_at":"2026-07-05T06:42:32.859375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:32.859375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sfp1GiKUz1fxdMMSNiODJHI5hCCJmqXuGiv1jVsEoFLWM4BDcmH26GxjuvM1fs2ZU5GWpm1IVvQHKh90rgUqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:32.859975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.09455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a31097f9cadcdadd5fc27792b1782af80d889f2d9257bd9b4e59b0e4c7741e7","sha256:7dab8cb3d087f0c503380f28e830afbc489655e0b4ebb356f2b05db5b8af010c"],"state_sha256":"909b51fd6295374186afedbf2391b22ac45187a3ebe3bd98578d17b420c1c4a2"}