{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PJYWPUWZLWXLKRX4VTNPUU56OK","short_pith_number":"pith:PJYWPUWZ","schema_version":"1.0","canonical_sha256":"7a7167d2d95daeb546fcacdafa53be72bb4243e5c3313c93423bdfa4b3d1a9db","source":{"kind":"arxiv","id":"2507.14828","version":1},"attestation_state":"computed","paper":{"title":"eMargin: Revisiting Contrastive Learning with Margin-Based Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abdul-Kazeem Shamba, Gavin Taylor, Kerstin Bach","submitted_at":"2025-07-20T05:39:25Z","abstract_excerpt":"We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether an adaptive margin (eMargin), adjusted based on a predefined similarity threshold, can improve the separation between adjacent but dissimilar time steps and subsequently lead to better performance in downstream tasks. Our study evaluates the impact of this modification on clustering performance and classification in three benchmark datasets. Our findings, however, indicate tha"},"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":"2507.14828","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-20T05:39:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"221d2f3baa80eabf001670ad224ce95363aa78947deece8af34b9e0e3c01520b","abstract_canon_sha256":"c8279d912685323c3b33376f8d7c372748e80570bad5e2ed8917fc789aa7b22a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:14.258198Z","signature_b64":"i2PazgHOR3rjlq185HbPrtoA0fVVll2fntgIijLkRod2enkDOnYp3ujDbZ00WSmIjXzE6K2+TpBhzy6PNe5fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7167d2d95daeb546fcacdafa53be72bb4243e5c3313c93423bdfa4b3d1a9db","last_reissued_at":"2026-07-05T11:40:14.257723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:14.257723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"eMargin: Revisiting Contrastive Learning with Margin-Based Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abdul-Kazeem Shamba, Gavin Taylor, Kerstin Bach","submitted_at":"2025-07-20T05:39:25Z","abstract_excerpt":"We revisit previous contrastive learning frameworks to investigate the effect of introducing an adaptive margin into the contrastive loss function for time series representation learning. Specifically, we explore whether an adaptive margin (eMargin), adjusted based on a predefined similarity threshold, can improve the separation between adjacent but dissimilar time steps and subsequently lead to better performance in downstream tasks. Our study evaluates the impact of this modification on clustering performance and classification in three benchmark datasets. Our findings, however, indicate tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14828","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/2507.14828/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":"2507.14828","created_at":"2026-07-05T11:40:14.257778+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14828v1","created_at":"2026-07-05T11:40:14.257778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14828","created_at":"2026-07-05T11:40:14.257778+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJYWPUWZLWXL","created_at":"2026-07-05T11:40:14.257778+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJYWPUWZLWXLKRX4","created_at":"2026-07-05T11:40:14.257778+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJYWPUWZ","created_at":"2026-07-05T11:40:14.257778+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/PJYWPUWZLWXLKRX4VTNPUU56OK","json":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK.json","graph_json":"https://pith.science/api/pith-number/PJYWPUWZLWXLKRX4VTNPUU56OK/graph.json","events_json":"https://pith.science/api/pith-number/PJYWPUWZLWXLKRX4VTNPUU56OK/events.json","paper":"https://pith.science/paper/PJYWPUWZ"},"agent_actions":{"view_html":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK","download_json":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK.json","view_paper":"https://pith.science/paper/PJYWPUWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14828&json=true","fetch_graph":"https://pith.science/api/pith-number/PJYWPUWZLWXLKRX4VTNPUU56OK/graph.json","fetch_events":"https://pith.science/api/pith-number/PJYWPUWZLWXLKRX4VTNPUU56OK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK/action/storage_attestation","attest_author":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK/action/author_attestation","sign_citation":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK/action/citation_signature","submit_replication":"https://pith.science/pith/PJYWPUWZLWXLKRX4VTNPUU56OK/action/replication_record"}},"created_at":"2026-07-05T11:40:14.257778+00:00","updated_at":"2026-07-05T11:40:14.257778+00:00"}