{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SF5L4TBH6CAV3GNJRF6NJVSJQL","short_pith_number":"pith:SF5L4TBH","schema_version":"1.0","canonical_sha256":"917abe4c27f0815d99a9897cd4d64982d890ff16beadca24dc7598a912d23b7f","source":{"kind":"arxiv","id":"2412.07979","version":1},"attestation_state":"computed","paper":{"title":"AmCLR: Unified Augmented Learning for Cross-Modal Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aayush Upadhyay, Ajay Jagannath, Anant Mehta","submitted_at":"2024-12-10T23:32:36Z","abstract_excerpt":"Contrastive learning has emerged as a pivotal framework for representation learning, underpinning advances in both unimodal and bimodal applications like SimCLR and CLIP. To address fundamental limitations like large batch size dependency and bimodality, methods such as SogCLR leverage stochastic optimization for the global contrastive objective. Inspired by SogCLR's efficiency and adaptability, we introduce AmCLR and xAmCLR objective functions tailored for bimodal vision-language models to further enhance the robustness of contrastive learning. AmCLR integrates diverse augmentations, includin"},"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":"2412.07979","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-10T23:32:36Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"b7a5cac5379a8802853893ac56f2219778e95260468f65e9dd9ad3dce209ad98","abstract_canon_sha256":"c8acd6eeb420da36b681025c21d76498202956209a85a9532d3f34d7444732d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:41.983359Z","signature_b64":"XCjyFb3tPhgHjk+zs0VtE7lG4prLJtaYN4uFV4jvS4mhSLNCExYRFt5z7UmZ8j37V97z1n8x4erxsqBc5SAIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917abe4c27f0815d99a9897cd4d64982d890ff16beadca24dc7598a912d23b7f","last_reissued_at":"2026-07-05T09:47:41.982978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:41.982978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AmCLR: Unified Augmented Learning for Cross-Modal Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Aayush Upadhyay, Ajay Jagannath, Anant Mehta","submitted_at":"2024-12-10T23:32:36Z","abstract_excerpt":"Contrastive learning has emerged as a pivotal framework for representation learning, underpinning advances in both unimodal and bimodal applications like SimCLR and CLIP. To address fundamental limitations like large batch size dependency and bimodality, methods such as SogCLR leverage stochastic optimization for the global contrastive objective. Inspired by SogCLR's efficiency and adaptability, we introduce AmCLR and xAmCLR objective functions tailored for bimodal vision-language models to further enhance the robustness of contrastive learning. AmCLR integrates diverse augmentations, includin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07979","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/2412.07979/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":"2412.07979","created_at":"2026-07-05T09:47:41.983030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07979v1","created_at":"2026-07-05T09:47:41.983030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07979","created_at":"2026-07-05T09:47:41.983030+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF5L4TBH6CAV","created_at":"2026-07-05T09:47:41.983030+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF5L4TBH6CAV3GNJ","created_at":"2026-07-05T09:47:41.983030+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF5L4TBH","created_at":"2026-07-05T09:47:41.983030+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/SF5L4TBH6CAV3GNJRF6NJVSJQL","json":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL.json","graph_json":"https://pith.science/api/pith-number/SF5L4TBH6CAV3GNJRF6NJVSJQL/graph.json","events_json":"https://pith.science/api/pith-number/SF5L4TBH6CAV3GNJRF6NJVSJQL/events.json","paper":"https://pith.science/paper/SF5L4TBH"},"agent_actions":{"view_html":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL","download_json":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL.json","view_paper":"https://pith.science/paper/SF5L4TBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07979&json=true","fetch_graph":"https://pith.science/api/pith-number/SF5L4TBH6CAV3GNJRF6NJVSJQL/graph.json","fetch_events":"https://pith.science/api/pith-number/SF5L4TBH6CAV3GNJRF6NJVSJQL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL/action/storage_attestation","attest_author":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL/action/author_attestation","sign_citation":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL/action/citation_signature","submit_replication":"https://pith.science/pith/SF5L4TBH6CAV3GNJRF6NJVSJQL/action/replication_record"}},"created_at":"2026-07-05T09:47:41.983030+00:00","updated_at":"2026-07-05T09:47:41.983030+00:00"}