{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BGBALTQVLD45ZPYP36QGEBLD2H","short_pith_number":"pith:BGBALTQV","schema_version":"1.0","canonical_sha256":"098205ce1558f9dcbf0fdfa0620563d1e01c7bfb73ce8fe705d409024852460e","source":{"kind":"arxiv","id":"2308.09455","version":1},"attestation_state":"computed","paper":{"title":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haoran Wang, Siyu Zhang, Weijian Liang, Yaoru Sun, Yeming Chen","submitted_at":"2023-08-18T10:40:25Z","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"},"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":"2308.09455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-08-18T10:40:25Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a7458ba6fac8363b2df4777cc98f90dd74de7c4e31aab086d76ac3428d097334","abstract_canon_sha256":"3982ca9593735814a747f2afef4662a11db89cb984c7a46910a7d279c8b70052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:32.859975Z","signature_b64":"sfp1GiKUz1fxdMMSNiODJHI5hCCJmqXuGiv1jVsEoFLWM4BDcmH26GxjuvM1fs2ZU5GWpm1IVvQHKh90rgUqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"098205ce1558f9dcbf0fdfa0620563d1e01c7bfb73ce8fe705d409024852460e","last_reissued_at":"2026-07-05T06:42:32.859375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:32.859375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Artificial-Spiking Hierarchical Networks for Vision-Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Haoran Wang, Siyu Zhang, Weijian Liang, Yaoru Sun, Yeming Chen","submitted_at":"2023-08-18T10:40:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09455","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/2308.09455/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":"2308.09455","created_at":"2026-07-05T06:42:32.859448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09455v1","created_at":"2026-07-05T06:42:32.859448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09455","created_at":"2026-07-05T06:42:32.859448+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGBALTQVLD45","created_at":"2026-07-05T06:42:32.859448+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGBALTQVLD45ZPYP","created_at":"2026-07-05T06:42:32.859448+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGBALTQV","created_at":"2026-07-05T06:42:32.859448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H","json":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H.json","graph_json":"https://pith.science/api/pith-number/BGBALTQVLD45ZPYP36QGEBLD2H/graph.json","events_json":"https://pith.science/api/pith-number/BGBALTQVLD45ZPYP36QGEBLD2H/events.json","paper":"https://pith.science/paper/BGBALTQV"},"agent_actions":{"view_html":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H","download_json":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H.json","view_paper":"https://pith.science/paper/BGBALTQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09455&json=true","fetch_graph":"https://pith.science/api/pith-number/BGBALTQVLD45ZPYP36QGEBLD2H/graph.json","fetch_events":"https://pith.science/api/pith-number/BGBALTQVLD45ZPYP36QGEBLD2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H/action/storage_attestation","attest_author":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H/action/author_attestation","sign_citation":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H/action/citation_signature","submit_replication":"https://pith.science/pith/BGBALTQVLD45ZPYP36QGEBLD2H/action/replication_record"}},"created_at":"2026-07-05T06:42:32.859448+00:00","updated_at":"2026-07-05T06:42:32.859448+00:00"}