{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:S6R7IKB4XHZ2SGFKA4CSE2J3IN","short_pith_number":"pith:S6R7IKB4","canonical_record":{"source":{"id":"2210.03963","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T08:07:47Z","cross_cats_sorted":[],"title_canon_sha256":"bed1b2b646606c088b45ced6af74b66c4c3773332ae86624ceb2ae3f5881538a","abstract_canon_sha256":"adfc7b426af2c04fcc0c70c5674e9fa6fdb950acbf2643646e33a58e22a0061f"},"schema_version":"1.0"},"canonical_sha256":"97a3f4283cb9f3a918aa070522693b436b0bb8c81202dafb2aabc6932de3b080","source":{"kind":"arxiv","id":"2210.03963","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03963","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03963v3","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03963","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"S6R7IKB4XHZ2","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"S6R7IKB4XHZ2SGFK","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"S6R7IKB4","created_at":"2026-07-05T08:31:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:S6R7IKB4XHZ2SGFKA4CSE2J3IN","target":"record","payload":{"canonical_record":{"source":{"id":"2210.03963","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T08:07:47Z","cross_cats_sorted":[],"title_canon_sha256":"bed1b2b646606c088b45ced6af74b66c4c3773332ae86624ceb2ae3f5881538a","abstract_canon_sha256":"adfc7b426af2c04fcc0c70c5674e9fa6fdb950acbf2643646e33a58e22a0061f"},"schema_version":"1.0"},"canonical_sha256":"97a3f4283cb9f3a918aa070522693b436b0bb8c81202dafb2aabc6932de3b080","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:38.343806Z","signature_b64":"TowU5tdloi+8TvwOFBBDqkXz0On/6MnJ457EEAUwWC3zsicVyZncTcw9J2trcEbdJZiE7C5aUf/SUee2cfHyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a3f4283cb9f3a918aa070522693b436b0bb8c81202dafb2aabc6932de3b080","last_reissued_at":"2026-07-05T08:31:38.343402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:38.343402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.03963","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kc2UHOzu73bM6LbEV2sP65+shxnN57udT3ufOC6sxmuA3chJd+dU4rd7YcaVyGP69vgXp5UrKxO1jnnV1ZyrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:12:38.169629Z"},"content_sha256":"4ca56e79a40f1d343a06da12d172575c668a9629f6c3fa9ce49f32a9722c94af","schema_version":"1.0","event_id":"sha256:4ca56e79a40f1d343a06da12d172575c668a9629f6c3fa9ce49f32a9722c94af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:S6R7IKB4XHZ2SGFKA4CSE2J3IN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongsheng Zhu, Fei Tan, Jinghui Lu, Rui Zhao, Zhenyu Mao","submitted_at":"2022-10-08T08:07:47Z","abstract_excerpt":"Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a simple dropout mechanism (viewed as continuous augmentation) surprisingly dominates discrete augmentations such as cropping, word deletion, and synonym replacement as reported. To understand the underlying rationales, we revisit existing approaches and attempt to hypothesize the desiderata of reasonable data augmentation methods: balance of semantic consist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03963","kind":"arxiv","version":3},"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/2210.03963/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":"2026-07-05T08:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r/3dnvc0C2Xod8YCXM+Vbw1/f8Rgha7X+pDlAUmcDafkfJcgZwtj1fAf+AMQ0spZ3l4KL9Z6Q4193t/0Z9HmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:12:38.170004Z"},"content_sha256":"38456f7a91c64e2dda8d2ffe09235ea51880bab01f02eaf7e69e0d8fad5ed0a0","schema_version":"1.0","event_id":"sha256:38456f7a91c64e2dda8d2ffe09235ea51880bab01f02eaf7e69e0d8fad5ed0a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN/bundle.json","state_url":"https://pith.science/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN/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":"2026-08-07T14:12:38Z","links":{"resolver":"https://pith.science/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN","bundle":"https://pith.science/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN/bundle.json","state":"https://pith.science/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6R7IKB4XHZ2SGFKA4CSE2J3IN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S6R7IKB4XHZ2SGFKA4CSE2J3IN","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":"adfc7b426af2c04fcc0c70c5674e9fa6fdb950acbf2643646e33a58e22a0061f","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T08:07:47Z","title_canon_sha256":"bed1b2b646606c088b45ced6af74b66c4c3773332ae86624ceb2ae3f5881538a"},"schema_version":"1.0","source":{"id":"2210.03963","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03963","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03963v3","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03963","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"S6R7IKB4XHZ2","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"S6R7IKB4XHZ2SGFK","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"S6R7IKB4","created_at":"2026-07-05T08:31:38Z"}],"graph_snapshots":[{"event_id":"sha256:38456f7a91c64e2dda8d2ffe09235ea51880bab01f02eaf7e69e0d8fad5ed0a0","target":"graph","created_at":"2026-07-05T08:31:38Z","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/2210.03963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a simple dropout mechanism (viewed as continuous augmentation) surprisingly dominates discrete augmentations such as cropping, word deletion, and synonym replacement as reported. To understand the underlying rationales, we revisit existing approaches and attempt to hypothesize the desiderata of reasonable data augmentation methods: balance of semantic consist","authors_text":"Dongsheng Zhu, Fei Tan, Jinghui Lu, Rui Zhao, Zhenyu Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T08:07:47Z","title":"SDA: Simple Discrete Augmentation for Contrastive Sentence Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03963","kind":"arxiv","version":3},"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":"sha256:4ca56e79a40f1d343a06da12d172575c668a9629f6c3fa9ce49f32a9722c94af","target":"record","created_at":"2026-07-05T08:31:38Z","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":"adfc7b426af2c04fcc0c70c5674e9fa6fdb950acbf2643646e33a58e22a0061f","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-08T08:07:47Z","title_canon_sha256":"bed1b2b646606c088b45ced6af74b66c4c3773332ae86624ceb2ae3f5881538a"},"schema_version":"1.0","source":{"id":"2210.03963","kind":"arxiv","version":3}},"canonical_sha256":"97a3f4283cb9f3a918aa070522693b436b0bb8c81202dafb2aabc6932de3b080","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97a3f4283cb9f3a918aa070522693b436b0bb8c81202dafb2aabc6932de3b080","first_computed_at":"2026-07-05T08:31:38.343402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:38.343402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TowU5tdloi+8TvwOFBBDqkXz0On/6MnJ457EEAUwWC3zsicVyZncTcw9J2trcEbdJZiE7C5aUf/SUee2cfHyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:38.343806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03963","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ca56e79a40f1d343a06da12d172575c668a9629f6c3fa9ce49f32a9722c94af","sha256:38456f7a91c64e2dda8d2ffe09235ea51880bab01f02eaf7e69e0d8fad5ed0a0"],"state_sha256":"69db9f0c0240952bc0d00207a2918e4572f127d19dec9a03e7ad541569f05848"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWaq51kkRkq2Xz56sbANAPtY6FjqJYihyV+/IL6CgtKGxZYoQe64q8FkXdirU+H2ug68tM2YNMwQ/bKAuulNBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T14:12:38.172963Z","bundle_sha256":"47c8a3d5eda4d1b354ac5d284c7a2185a624e48ae07abe33888a81bf4ce366b5"}}