{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CWOMVCXAJQCRGJU5MKMFXYFHEP","short_pith_number":"pith:CWOMVCXA","schema_version":"1.0","canonical_sha256":"159cca8ae04c0513269d62985be0a723c1d4a5fb8be7e02990c3cb63fded9298","source":{"kind":"arxiv","id":"2410.10365","version":1},"attestation_state":"computed","paper":{"title":"SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deyu Meng, Xiangyong Cao, Yuntao Shou","submitted_at":"2024-10-14T10:39:38Z","abstract_excerpt":"Graph Contrastive Learning (GCL) excels at managing noise and fluctuations in input data, making it popular in various fields (e.g., social networks, and knowledge graphs). Our study finds that the difference in high-frequency information between augmented graphs is greater than that in low-frequency information. However, most existing GCL methods focus mainly on the time domain (low-frequency information) for node feature representations and cannot make good use of high-frequency information to speed up model convergence. Furthermore, existing GCL paradigms optimize graph embedding representa"},"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":"2410.10365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T10:39:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b58fba045ed3c0e3b063b81e9a1314c8fb6e6df5f86d24569b7d11dc017f55ef","abstract_canon_sha256":"b3769a40924db0fd64f1bee4fdc1f180c977954364e69022c3c51980c6e418a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:15.244538Z","signature_b64":"D7KU3rPH6u3iaPqbAioZciOGztxiOxhyBfpTZ71qok0g1cL2Q3KmY/zJY/kPaL6uZNdZVoUQIlox8VPvwIyUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"159cca8ae04c0513269d62985be0a723c1d4a5fb8be7e02990c3cb63fded9298","last_reissued_at":"2026-07-05T09:20:15.244083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:15.244083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpeGCL: Self-supervised Graph Spectrum Contrastive Learning without Positive Samples","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deyu Meng, Xiangyong Cao, Yuntao Shou","submitted_at":"2024-10-14T10:39:38Z","abstract_excerpt":"Graph Contrastive Learning (GCL) excels at managing noise and fluctuations in input data, making it popular in various fields (e.g., social networks, and knowledge graphs). Our study finds that the difference in high-frequency information between augmented graphs is greater than that in low-frequency information. However, most existing GCL methods focus mainly on the time domain (low-frequency information) for node feature representations and cannot make good use of high-frequency information to speed up model convergence. Furthermore, existing GCL paradigms optimize graph embedding representa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10365","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/2410.10365/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":"2410.10365","created_at":"2026-07-05T09:20:15.244140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10365v1","created_at":"2026-07-05T09:20:15.244140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10365","created_at":"2026-07-05T09:20:15.244140+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWOMVCXAJQCR","created_at":"2026-07-05T09:20:15.244140+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWOMVCXAJQCRGJU5","created_at":"2026-07-05T09:20:15.244140+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWOMVCXA","created_at":"2026-07-05T09:20:15.244140+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12325","citing_title":"GSDNet: Revisiting Incomplete Multimodal-Diffusion from Graph Spectrum Perspective for Conversation Emotion Recognition","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP","json":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP.json","graph_json":"https://pith.science/api/pith-number/CWOMVCXAJQCRGJU5MKMFXYFHEP/graph.json","events_json":"https://pith.science/api/pith-number/CWOMVCXAJQCRGJU5MKMFXYFHEP/events.json","paper":"https://pith.science/paper/CWOMVCXA"},"agent_actions":{"view_html":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP","download_json":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP.json","view_paper":"https://pith.science/paper/CWOMVCXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10365&json=true","fetch_graph":"https://pith.science/api/pith-number/CWOMVCXAJQCRGJU5MKMFXYFHEP/graph.json","fetch_events":"https://pith.science/api/pith-number/CWOMVCXAJQCRGJU5MKMFXYFHEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP/action/storage_attestation","attest_author":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP/action/author_attestation","sign_citation":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP/action/citation_signature","submit_replication":"https://pith.science/pith/CWOMVCXAJQCRGJU5MKMFXYFHEP/action/replication_record"}},"created_at":"2026-07-05T09:20:15.244140+00:00","updated_at":"2026-07-05T09:20:15.244140+00:00"}