{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YOQLBRDOFKHA42GY4Z23SQXKJ4","short_pith_number":"pith:YOQLBRDO","canonical_record":{"source":{"id":"2103.14542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-26T15:48:52Z","cross_cats_sorted":[],"title_canon_sha256":"021fa252b3026d6b0f7b60c857453c119bd42d3a7db897436ab2c6ece2a8871e","abstract_canon_sha256":"dda8923d3f9b2cc1ed3597980bd143cf36cffaec88543ae3de3d0f36f574b94f"},"schema_version":"1.0"},"canonical_sha256":"c3a0b0c46e2a8e0e68d8e675b942ea4f20db000b5efc3432bb2f80664f7fcef5","source":{"kind":"arxiv","id":"2103.14542","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14542","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14542v1","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14542","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"YOQLBRDOFKHA","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"YOQLBRDOFKHA42GY","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"YOQLBRDO","created_at":"2026-07-05T02:26:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YOQLBRDOFKHA42GY4Z23SQXKJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2103.14542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-26T15:48:52Z","cross_cats_sorted":[],"title_canon_sha256":"021fa252b3026d6b0f7b60c857453c119bd42d3a7db897436ab2c6ece2a8871e","abstract_canon_sha256":"dda8923d3f9b2cc1ed3597980bd143cf36cffaec88543ae3de3d0f36f574b94f"},"schema_version":"1.0"},"canonical_sha256":"c3a0b0c46e2a8e0e68d8e675b942ea4f20db000b5efc3432bb2f80664f7fcef5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:42.158559Z","signature_b64":"H2HMY9BWzFXAqTAZidRx79duni8B8jI7Ew8j2MIGsGBGQ5tjtoH1uWGP+CA5UaySJwi64spVdRsiNtCkipkeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3a0b0c46e2a8e0e68d8e675b942ea4f20db000b5efc3432bb2f80664f7fcef5","last_reissued_at":"2026-07-05T02:26:42.158058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:42.158058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.14542","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":"2026-07-05T02:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MCH6Qp9SnksnP2ywvzPk9/ejKOoHtvGhPL11aD2rZC737pCLky9b/Q220r5mco1zlPQMc1SBkTta8jqDD/EXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:38:21.922485Z"},"content_sha256":"a4a09b2e6c67f5fb3f34ed9915850925f64d50c027d0ebdc0a6053bd985c6801","schema_version":"1.0","event_id":"sha256:a4a09b2e6c67f5fb3f34ed9915850925f64d50c027d0ebdc0a6053bd985c6801"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YOQLBRDOFKHA42GY4Z23SQXKJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Document Embedding via Contrastive Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Zong, Dongjin Song, Dongsheng Luo, Haifeng Chen, Jingchao Ni, Wei Cheng, Wenchao Yu, Xiang Zhang, Xuchao Zhang, Yanchi Liu, Zhengzhang Chen","submitted_at":"2021-03-26T15:48:52Z","abstract_excerpt":"We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining, we hypothesize that high-quality document embedding should be invariant to diverse paraphrases that preserve the semantics of the original document. With different backbones and contrastive learning frameworks, our study reveals the enormous benefits of contrastive augmentation for document representation learning with two additional insights: 1) including "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14542","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/2103.14542/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":"2026-07-05T02:26:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5qd+bDB0YDPaquHevHs0kAxro9sHW7rVJieggxYrZ8bENVUsp+foXuYIQa5csC1Au9ScfjE+CKZVSoR/RpGTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T03:38:21.923114Z"},"content_sha256":"405b42f763fb82c3f8788656ff2d22ee6ac1ffd4ffab7720cbd6b4c46c8dd181","schema_version":"1.0","event_id":"sha256:405b42f763fb82c3f8788656ff2d22ee6ac1ffd4ffab7720cbd6b4c46c8dd181"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4/bundle.json","state_url":"https://pith.science/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4/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":"2026-08-19T03:38:21Z","links":{"resolver":"https://pith.science/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4","bundle":"https://pith.science/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4/bundle.json","state":"https://pith.science/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOQLBRDOFKHA42GY4Z23SQXKJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YOQLBRDOFKHA42GY4Z23SQXKJ4","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":"dda8923d3f9b2cc1ed3597980bd143cf36cffaec88543ae3de3d0f36f574b94f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-26T15:48:52Z","title_canon_sha256":"021fa252b3026d6b0f7b60c857453c119bd42d3a7db897436ab2c6ece2a8871e"},"schema_version":"1.0","source":{"id":"2103.14542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.14542","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"arxiv_version","alias_value":"2103.14542v1","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14542","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_12","alias_value":"YOQLBRDOFKHA","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"YOQLBRDOFKHA42GY","created_at":"2026-07-05T02:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"YOQLBRDO","created_at":"2026-07-05T02:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:405b42f763fb82c3f8788656ff2d22ee6ac1ffd4ffab7720cbd6b4c46c8dd181","target":"graph","created_at":"2026-07-05T02:26:42Z","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/2103.14542/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining, we hypothesize that high-quality document embedding should be invariant to diverse paraphrases that preserve the semantics of the original document. With different backbones and contrastive learning frameworks, our study reveals the enormous benefits of contrastive augmentation for document representation learning with two additional insights: 1) including ","authors_text":"Bo Zong, Dongjin Song, Dongsheng Luo, Haifeng Chen, Jingchao Ni, Wei Cheng, Wenchao Yu, Xiang Zhang, Xuchao Zhang, Yanchi Liu, Zhengzhang Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-26T15:48:52Z","title":"Unsupervised Document Embedding via Contrastive Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14542","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:a4a09b2e6c67f5fb3f34ed9915850925f64d50c027d0ebdc0a6053bd985c6801","target":"record","created_at":"2026-07-05T02:26:42Z","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":"dda8923d3f9b2cc1ed3597980bd143cf36cffaec88543ae3de3d0f36f574b94f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-26T15:48:52Z","title_canon_sha256":"021fa252b3026d6b0f7b60c857453c119bd42d3a7db897436ab2c6ece2a8871e"},"schema_version":"1.0","source":{"id":"2103.14542","kind":"arxiv","version":1}},"canonical_sha256":"c3a0b0c46e2a8e0e68d8e675b942ea4f20db000b5efc3432bb2f80664f7fcef5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a0b0c46e2a8e0e68d8e675b942ea4f20db000b5efc3432bb2f80664f7fcef5","first_computed_at":"2026-07-05T02:26:42.158058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:42.158058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H2HMY9BWzFXAqTAZidRx79duni8B8jI7Ew8j2MIGsGBGQ5tjtoH1uWGP+CA5UaySJwi64spVdRsiNtCkipkeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:42.158559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.14542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4a09b2e6c67f5fb3f34ed9915850925f64d50c027d0ebdc0a6053bd985c6801","sha256:405b42f763fb82c3f8788656ff2d22ee6ac1ffd4ffab7720cbd6b4c46c8dd181"],"state_sha256":"dcf24ff6b84010b3d1a845c4715ae6c1f05bb6313296d5791ff6d19c9784536d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PUbsagkMdHvxjlExcdTmOYA+ChKGzaMCG4aYySGwIl3qlxAAy1FnaR3WrAxZHxSWEme2qdEizA6IY+pECP4FDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T03:38:21.929470Z","bundle_sha256":"8cdc3cfa85c221c331e4e1f7f3256de8cea4d006aadabbc5d41d4e23cbc93a9a"}}