{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Z7PBSYALJ533IUDVAV75JZMLX7","short_pith_number":"pith:Z7PBSYAL","schema_version":"1.0","canonical_sha256":"cfde19600b4f77b45075057fd4e58bbffe91d811b118fbd1d0657cd12342c0c7","source":{"kind":"arxiv","id":"2501.19069","version":2},"attestation_state":"computed","paper":{"title":"Improving vision-language alignment with graph spiking hybrid Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng cheng, Heming Zheng, Siyu Zhang, Wenzhe Liu, Yeming Chen, Yiming Wu","submitted_at":"2025-01-31T11:55:17Z","abstract_excerpt":"To bridge the semantic gap between vision and language (VL), it is necessary to develop a good alignment strategy, which includes handling semantic diversity, abstract representation of visual information, and generalization ability of models. Recent works use detector-based bounding boxes or patches with regular partitions to represent visual semantics. While current paradigms have made strides, they are still insufficient for fully capturing the nuanced contextual relations among various objects. This paper proposes a comprehensive visual semantic representation module, necessitating the uti"},"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":"2501.19069","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T11:55:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5745924dc8e4d3ae13fced25347745fa2d8bd92d673b73e154b3c13b9c0a4aa","abstract_canon_sha256":"7211fd0cf98e62cabe08d9567dd19db95e2ba4df37552c5f1ab6a834d5b8e7ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:12.634984Z","signature_b64":"ff6W7S2HM2tcxnawBReHd3LIBhd6Qg3zGZw0qDqfPmilSvxMfSyJpcyZ0VcKfj/GHyOQdRxhagZ/gCz+P1CqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfde19600b4f77b45075057fd4e58bbffe91d811b118fbd1d0657cd12342c0c7","last_reissued_at":"2026-07-05T10:22:12.634439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:12.634439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving vision-language alignment with graph spiking hybrid Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng cheng, Heming Zheng, Siyu Zhang, Wenzhe Liu, Yeming Chen, Yiming Wu","submitted_at":"2025-01-31T11:55:17Z","abstract_excerpt":"To bridge the semantic gap between vision and language (VL), it is necessary to develop a good alignment strategy, which includes handling semantic diversity, abstract representation of visual information, and generalization ability of models. Recent works use detector-based bounding boxes or patches with regular partitions to represent visual semantics. While current paradigms have made strides, they are still insufficient for fully capturing the nuanced contextual relations among various objects. This paper proposes a comprehensive visual semantic representation module, necessitating the uti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19069","kind":"arxiv","version":2},"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/2501.19069/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":"2501.19069","created_at":"2026-07-05T10:22:12.634507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19069v2","created_at":"2026-07-05T10:22:12.634507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19069","created_at":"2026-07-05T10:22:12.634507+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7PBSYALJ533","created_at":"2026-07-05T10:22:12.634507+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7PBSYALJ533IUDV","created_at":"2026-07-05T10:22:12.634507+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7PBSYAL","created_at":"2026-07-05T10:22:12.634507+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/Z7PBSYALJ533IUDVAV75JZMLX7","json":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7.json","graph_json":"https://pith.science/api/pith-number/Z7PBSYALJ533IUDVAV75JZMLX7/graph.json","events_json":"https://pith.science/api/pith-number/Z7PBSYALJ533IUDVAV75JZMLX7/events.json","paper":"https://pith.science/paper/Z7PBSYAL"},"agent_actions":{"view_html":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7","download_json":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7.json","view_paper":"https://pith.science/paper/Z7PBSYAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19069&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7PBSYALJ533IUDVAV75JZMLX7/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7PBSYALJ533IUDVAV75JZMLX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7/action/storage_attestation","attest_author":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7/action/author_attestation","sign_citation":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7/action/citation_signature","submit_replication":"https://pith.science/pith/Z7PBSYALJ533IUDVAV75JZMLX7/action/replication_record"}},"created_at":"2026-07-05T10:22:12.634507+00:00","updated_at":"2026-07-05T10:22:12.634507+00:00"}