{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4VCDSVGY4PXIS6OLUJUVDWNSIV","short_pith_number":"pith:4VCDSVGY","canonical_record":{"source":{"id":"2404.08701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T01:16:33Z","cross_cats_sorted":[],"title_canon_sha256":"bebb1d6a3d2b2a63902453670d7f9e61bb0dd461071f8a0bd738fe22862dcc48","abstract_canon_sha256":"b48a830937a4c502612622b996c4d2099dcba01f9d9b6126b110f1fb1126d925"},"schema_version":"1.0"},"canonical_sha256":"e5443954d8e3ee8979cba26951d9b245439f86ab1e0bc1afdac531c9fc574a8a","source":{"kind":"arxiv","id":"2404.08701","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08701","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08701v1","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08701","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"4VCDSVGY4PXI","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"4VCDSVGY4PXIS6OL","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"4VCDSVGY","created_at":"2026-07-05T08:07:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4VCDSVGY4PXIS6OLUJUVDWNSIV","target":"record","payload":{"canonical_record":{"source":{"id":"2404.08701","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T01:16:33Z","cross_cats_sorted":[],"title_canon_sha256":"bebb1d6a3d2b2a63902453670d7f9e61bb0dd461071f8a0bd738fe22862dcc48","abstract_canon_sha256":"b48a830937a4c502612622b996c4d2099dcba01f9d9b6126b110f1fb1126d925"},"schema_version":"1.0"},"canonical_sha256":"e5443954d8e3ee8979cba26951d9b245439f86ab1e0bc1afdac531c9fc574a8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:38.408341Z","signature_b64":"ZwggaEozXexwudg+2IUOiFUPbyKUhBNzAqJfdfa1CZOcMYuHYos8t3o0iu5yO0YniiqvktVEgxYrpsRW5DiUCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5443954d8e3ee8979cba26951d9b245439f86ab1e0bc1afdac531c9fc574a8a","last_reissued_at":"2026-07-05T08:07:38.407858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:38.407858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.08701","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H2biHZ/cg3OrHuz9hrKaSJLePv68pqTD6C449bWBEDDBXqjNlSrCRyoSBKL6+Q/3eXjd1lRY07MBkq2YU08kAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:14:33.642452Z"},"content_sha256":"f4ac337ff3a073af7539a35069282d5d94a1817ab85d45b18b895d1fc916e500","schema_version":"1.0","event_id":"sha256:f4ac337ff3a073af7539a35069282d5d94a1817ab85d45b18b895d1fc916e500"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4VCDSVGY4PXIS6OLUJUVDWNSIV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Contrastive Learning Refine Embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jinha Kim, Lihui Liu, Vidit Bansal","submitted_at":"2024-04-11T01:16:33Z","abstract_excerpt":"Recent advancements in contrastive learning have revolutionized self-supervised representation learning and achieved state-of-the-art performance on benchmark tasks. While most existing methods focus on applying contrastive learning to input data modalities such as images, natural language sentences, or networks, they overlook the potential of utilizing outputs from previously trained encoders. In this paper, we introduce SIMSKIP, a novel contrastive learning framework that specifically refines input embeddings for downstream tasks. Unlike traditional unsupervised learning approaches, SIMSKIP "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08701","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/2404.08701/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GC0YYk176hNZxFC6XHD6qhdE9OJSdRTKNRbTPjpd7XEH4IghqmP9esfqfS/MuTcC/gfmAHnr34yHTVsxH2vhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:14:33.642992Z"},"content_sha256":"9ae86551d6a95979522f47823e32e04ba664395b4490412f0bf28ce1956217ab","schema_version":"1.0","event_id":"sha256:9ae86551d6a95979522f47823e32e04ba664395b4490412f0bf28ce1956217ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV/bundle.json","state_url":"https://pith.science/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T02:14:33Z","links":{"resolver":"https://pith.science/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV","bundle":"https://pith.science/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV/bundle.json","state":"https://pith.science/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VCDSVGY4PXIS6OLUJUVDWNSIV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VCDSVGY4PXIS6OLUJUVDWNSIV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b48a830937a4c502612622b996c4d2099dcba01f9d9b6126b110f1fb1126d925","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T01:16:33Z","title_canon_sha256":"bebb1d6a3d2b2a63902453670d7f9e61bb0dd461071f8a0bd738fe22862dcc48"},"schema_version":"1.0","source":{"id":"2404.08701","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.08701","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2404.08701v1","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08701","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"4VCDSVGY4PXI","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"4VCDSVGY4PXIS6OL","created_at":"2026-07-05T08:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"4VCDSVGY","created_at":"2026-07-05T08:07:38Z"}],"graph_snapshots":[{"event_id":"sha256:9ae86551d6a95979522f47823e32e04ba664395b4490412f0bf28ce1956217ab","target":"graph","created_at":"2026-07-05T08:07:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.08701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in contrastive learning have revolutionized self-supervised representation learning and achieved state-of-the-art performance on benchmark tasks. While most existing methods focus on applying contrastive learning to input data modalities such as images, natural language sentences, or networks, they overlook the potential of utilizing outputs from previously trained encoders. In this paper, we introduce SIMSKIP, a novel contrastive learning framework that specifically refines input embeddings for downstream tasks. Unlike traditional unsupervised learning approaches, SIMSKIP ","authors_text":"Jinha Kim, Lihui Liu, Vidit Bansal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T01:16:33Z","title":"Can Contrastive Learning Refine Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08701","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f4ac337ff3a073af7539a35069282d5d94a1817ab85d45b18b895d1fc916e500","target":"record","created_at":"2026-07-05T08:07:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b48a830937a4c502612622b996c4d2099dcba01f9d9b6126b110f1fb1126d925","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-11T01:16:33Z","title_canon_sha256":"bebb1d6a3d2b2a63902453670d7f9e61bb0dd461071f8a0bd738fe22862dcc48"},"schema_version":"1.0","source":{"id":"2404.08701","kind":"arxiv","version":1}},"canonical_sha256":"e5443954d8e3ee8979cba26951d9b245439f86ab1e0bc1afdac531c9fc574a8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5443954d8e3ee8979cba26951d9b245439f86ab1e0bc1afdac531c9fc574a8a","first_computed_at":"2026-07-05T08:07:38.407858Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:38.407858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZwggaEozXexwudg+2IUOiFUPbyKUhBNzAqJfdfa1CZOcMYuHYos8t3o0iu5yO0YniiqvktVEgxYrpsRW5DiUCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:38.408341Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.08701","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4ac337ff3a073af7539a35069282d5d94a1817ab85d45b18b895d1fc916e500","sha256:9ae86551d6a95979522f47823e32e04ba664395b4490412f0bf28ce1956217ab"],"state_sha256":"5a10573695b3794add22fddcbf12fded63356f7ad922ef6aa21a67ea3a3ec09d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NdeY/K55C45P4x1Rxoxpkh0j686kFFyCpfcitw0bGJU9YE0EiBuo+cXVLnJEnMZNyfc2Wnelgt7Z/1IBLv5eBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:14:33.646790Z","bundle_sha256":"37ba879804e4b1f16a28dfc81e31739cf11e93e122bb680e090de12443adc234"}}