{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2FAOTYDPK4POCG37KTUZ2CC7HG","short_pith_number":"pith:2FAOTYDP","schema_version":"1.0","canonical_sha256":"d140e9e06f571ee11b7f54e99d085f39b747c6ab0c8bb894da6e9319d5c9bf75","source":{"kind":"arxiv","id":"2505.03532","version":1},"attestation_state":"computed","paper":{"title":"Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Yiqiao Chen, Zijian Huang","submitted_at":"2025-05-06T13:41:31Z","abstract_excerpt":"Alignment remains a crucial task in multi-modal deep learning, and contrastive learning has been widely applied in this field. However, when there are more than two modalities, existing methods typically calculate pairwise loss function and aggregate them into a composite loss function for the optimization of model parameters. This limitation mainly stems from the drawbacks of traditional similarity measurement method (i.e. they can only calculate the similarity between two vectors). To address this issue, we propose a novel similarity measurement method: the Joint Generalized Cosine Similarit"},"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":"2505.03532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.AP","submitted_at":"2025-05-06T13:41:31Z","cross_cats_sorted":[],"title_canon_sha256":"83b7bb4c1976ff3673413f4959700b70610dfeaeb840a0de5f99e918e8e7080f","abstract_canon_sha256":"c6e4cc7de6bce1d06227520f7bb8edea12d072ebe720b67b302d2e6419092204"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:17.728871Z","signature_b64":"fSmV/F+vLCQnkeU66XtMKrGqzFqIBwcrOcxCS14FgijiqT6e3sPppfzTdM5C1y8MjvVG966PsbEPA4fLmBZtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d140e9e06f571ee11b7f54e99d085f39b747c6ab0c8bb894da6e9319d5c9bf75","last_reissued_at":"2026-07-05T10:59:17.728460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:17.728460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint Generalized Cosine Similarity: A Novel Method for N-Modal Semantic Alignment Based on Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Yiqiao Chen, Zijian Huang","submitted_at":"2025-05-06T13:41:31Z","abstract_excerpt":"Alignment remains a crucial task in multi-modal deep learning, and contrastive learning has been widely applied in this field. However, when there are more than two modalities, existing methods typically calculate pairwise loss function and aggregate them into a composite loss function for the optimization of model parameters. This limitation mainly stems from the drawbacks of traditional similarity measurement method (i.e. they can only calculate the similarity between two vectors). To address this issue, we propose a novel similarity measurement method: the Joint Generalized Cosine Similarit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03532","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/2505.03532/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":"2505.03532","created_at":"2026-07-05T10:59:17.728520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03532v1","created_at":"2026-07-05T10:59:17.728520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03532","created_at":"2026-07-05T10:59:17.728520+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FAOTYDPK4PO","created_at":"2026-07-05T10:59:17.728520+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FAOTYDPK4POCG37","created_at":"2026-07-05T10:59:17.728520+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FAOTYDP","created_at":"2026-07-05T10:59:17.728520+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/2FAOTYDPK4POCG37KTUZ2CC7HG","json":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG.json","graph_json":"https://pith.science/api/pith-number/2FAOTYDPK4POCG37KTUZ2CC7HG/graph.json","events_json":"https://pith.science/api/pith-number/2FAOTYDPK4POCG37KTUZ2CC7HG/events.json","paper":"https://pith.science/paper/2FAOTYDP"},"agent_actions":{"view_html":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG","download_json":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG.json","view_paper":"https://pith.science/paper/2FAOTYDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03532&json=true","fetch_graph":"https://pith.science/api/pith-number/2FAOTYDPK4POCG37KTUZ2CC7HG/graph.json","fetch_events":"https://pith.science/api/pith-number/2FAOTYDPK4POCG37KTUZ2CC7HG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG/action/storage_attestation","attest_author":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG/action/author_attestation","sign_citation":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG/action/citation_signature","submit_replication":"https://pith.science/pith/2FAOTYDPK4POCG37KTUZ2CC7HG/action/replication_record"}},"created_at":"2026-07-05T10:59:17.728520+00:00","updated_at":"2026-07-05T10:59:17.728520+00:00"}