{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2LJOASN4XXPBIKMKQZ5EXL4AHB","short_pith_number":"pith:2LJOASN4","schema_version":"1.0","canonical_sha256":"d2d2e049bcbdde14298a867a4baf80386963244db1abab551ce5bde2dac19bab","source":{"kind":"arxiv","id":"2007.01423","version":2},"attestation_state":"computed","paper":{"title":"Maximizing Cohesion and Separation in Graph Representation Learning: A Distance-aware Negative Sampling Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anuj Karpatne, M. Maruf","submitted_at":"2020-07-02T22:40:38Z","abstract_excerpt":"The objective of unsupervised graph representation learning (GRL) is to learn a low-dimensional space of node embeddings that reflect the structure of a given unlabeled graph. Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes (referred to as \"cohesion\") by maintaining positive and negative corpus of node pairs. While positive samples are drawn from node pairs that co-occur in short random walks, conventional approaches construct negative corpus by uniformly sampling random pairs, thus ignoring valuable informa"},"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":"2007.01423","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-02T22:40:38Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"5728b34bbcb10a942526944fa70e7bab9b76c0b33041cd35edfbe2998ddfd0f0","abstract_canon_sha256":"ee3aa3ae7ed37104d9b7131554471b6419d16c73b743b361b06bcc5c57866921"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:30.342098Z","signature_b64":"M94DGNHm8xDAJdfmBKJBqYm4VDL8ire8N6dtLsMR2BShwBnz2JZuevzxbpNxcZFbjmMCPNjWXejSZHefZHlsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d2e049bcbdde14298a867a4baf80386963244db1abab551ce5bde2dac19bab","last_reissued_at":"2026-07-05T02:08:30.341673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:30.341673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximizing Cohesion and Separation in Graph Representation Learning: A Distance-aware Negative Sampling Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anuj Karpatne, M. Maruf","submitted_at":"2020-07-02T22:40:38Z","abstract_excerpt":"The objective of unsupervised graph representation learning (GRL) is to learn a low-dimensional space of node embeddings that reflect the structure of a given unlabeled graph. Existing algorithms for this task rely on negative sampling objectives that maximize the similarity in node embeddings at nearby nodes (referred to as \"cohesion\") by maintaining positive and negative corpus of node pairs. While positive samples are drawn from node pairs that co-occur in short random walks, conventional approaches construct negative corpus by uniformly sampling random pairs, thus ignoring valuable informa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01423","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/2007.01423/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":"2007.01423","created_at":"2026-07-05T02:08:30.341733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01423v2","created_at":"2026-07-05T02:08:30.341733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01423","created_at":"2026-07-05T02:08:30.341733+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LJOASN4XXPB","created_at":"2026-07-05T02:08:30.341733+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LJOASN4XXPBIKMK","created_at":"2026-07-05T02:08:30.341733+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LJOASN4","created_at":"2026-07-05T02:08:30.341733+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/2LJOASN4XXPBIKMKQZ5EXL4AHB","json":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB.json","graph_json":"https://pith.science/api/pith-number/2LJOASN4XXPBIKMKQZ5EXL4AHB/graph.json","events_json":"https://pith.science/api/pith-number/2LJOASN4XXPBIKMKQZ5EXL4AHB/events.json","paper":"https://pith.science/paper/2LJOASN4"},"agent_actions":{"view_html":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB","download_json":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB.json","view_paper":"https://pith.science/paper/2LJOASN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01423&json=true","fetch_graph":"https://pith.science/api/pith-number/2LJOASN4XXPBIKMKQZ5EXL4AHB/graph.json","fetch_events":"https://pith.science/api/pith-number/2LJOASN4XXPBIKMKQZ5EXL4AHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB/action/storage_attestation","attest_author":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB/action/author_attestation","sign_citation":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB/action/citation_signature","submit_replication":"https://pith.science/pith/2LJOASN4XXPBIKMKQZ5EXL4AHB/action/replication_record"}},"created_at":"2026-07-05T02:08:30.341733+00:00","updated_at":"2026-07-05T02:08:30.341733+00:00"}