{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4NOS662V7PXWIOXW6C4NNWHOGK","short_pith_number":"pith:4NOS662V","schema_version":"1.0","canonical_sha256":"e35d2f7b55fbef643af6f0b8d6d8ee3280e85b00a38310cb5aa905403330f273","source":{"kind":"arxiv","id":"2505.20188","version":1},"attestation_state":"computed","paper":{"title":"Research on feature fusion and multimodal patent text based on graph attention network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Hongji Li, Zhenzhen Song, Ziwei Liu","submitted_at":"2025-05-26T16:32:43Z","abstract_excerpt":"Aiming at the problems of cross-modal feature fusion, low efficiency of long text modeling and lack of hierarchical semantic coherence in patent text semantic mining, this study proposes HGM-Net, a deep learning framework that integrates Hierarchical Comparative Learning (HCL), Multi-modal Graph Attention Network (M-GAT) and Multi-Granularity Sparse Attention (MSA), which builds a dynamic mask, contrast and cross-structural similarity constraints on the word, sentence and paragraph hierarchies through HCL. Contrast and cross-structural similarity constraints are constructed at the word and par"},"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":"2505.20188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T16:32:43Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"74e2d6a84ce92f5e354c3ddc9da3e54630c5f9b6a6f75d07ed8d8e2d7cee50c1","abstract_canon_sha256":"65cfe0a245cbb2812014d68d86d7d03b52f8c73da34082c0f1b955324a34998f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:53.904399Z","signature_b64":"dbi48gym3A1UHB33zU+kpjv7wd+RImCQa9xh+hcNjsF/annUCfU1rTeveP38O64mtaqPIat3/8TjnnYV30JvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e35d2f7b55fbef643af6f0b8d6d8ee3280e85b00a38310cb5aa905403330f273","last_reissued_at":"2026-07-05T11:09:53.903870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:53.903870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Research on feature fusion and multimodal patent text based on graph attention network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Hongji Li, Zhenzhen Song, Ziwei Liu","submitted_at":"2025-05-26T16:32:43Z","abstract_excerpt":"Aiming at the problems of cross-modal feature fusion, low efficiency of long text modeling and lack of hierarchical semantic coherence in patent text semantic mining, this study proposes HGM-Net, a deep learning framework that integrates Hierarchical Comparative Learning (HCL), Multi-modal Graph Attention Network (M-GAT) and Multi-Granularity Sparse Attention (MSA), which builds a dynamic mask, contrast and cross-structural similarity constraints on the word, sentence and paragraph hierarchies through HCL. Contrast and cross-structural similarity constraints are constructed at the word and par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20188","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/2505.20188/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":"2505.20188","created_at":"2026-07-05T11:09:53.903943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20188v1","created_at":"2026-07-05T11:09:53.903943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20188","created_at":"2026-07-05T11:09:53.903943+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NOS662V7PXW","created_at":"2026-07-05T11:09:53.903943+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NOS662V7PXWIOXW","created_at":"2026-07-05T11:09:53.903943+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NOS662V","created_at":"2026-07-05T11:09:53.903943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10073","citing_title":"Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10073","citing_title":"Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK","json":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK.json","graph_json":"https://pith.science/api/pith-number/4NOS662V7PXWIOXW6C4NNWHOGK/graph.json","events_json":"https://pith.science/api/pith-number/4NOS662V7PXWIOXW6C4NNWHOGK/events.json","paper":"https://pith.science/paper/4NOS662V"},"agent_actions":{"view_html":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK","download_json":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK.json","view_paper":"https://pith.science/paper/4NOS662V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20188&json=true","fetch_graph":"https://pith.science/api/pith-number/4NOS662V7PXWIOXW6C4NNWHOGK/graph.json","fetch_events":"https://pith.science/api/pith-number/4NOS662V7PXWIOXW6C4NNWHOGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK/action/storage_attestation","attest_author":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK/action/author_attestation","sign_citation":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK/action/citation_signature","submit_replication":"https://pith.science/pith/4NOS662V7PXWIOXW6C4NNWHOGK/action/replication_record"}},"created_at":"2026-07-05T11:09:53.903943+00:00","updated_at":"2026-07-05T11:09:53.903943+00:00"}