{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V76AMI4O7BWMVOAROS6DNMJUCA","short_pith_number":"pith:V76AMI4O","canonical_record":{"source":{"id":"2502.07188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T02:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"11cd54ac5a64837ab887a235f897d3bb08275324d7b4d3e62839c36ecf7f4100","abstract_canon_sha256":"e4103e79af5737f58d641ce069b7ae4e271c326fb18e0e967c5a2fca74fbaa61"},"schema_version":"1.0"},"canonical_sha256":"affc06238ef86ccab81174bc36b1341037995a1d9047c9970f151b3070ba5201","source":{"kind":"arxiv","id":"2502.07188","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07188","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07188v1","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07188","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"V76AMI4O7BWM","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"V76AMI4O7BWMVOAR","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"V76AMI4O","created_at":"2026-07-05T10:12:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V76AMI4O7BWMVOAROS6DNMJUCA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T02:30:21Z","cross_cats_sorted":[],"title_canon_sha256":"11cd54ac5a64837ab887a235f897d3bb08275324d7b4d3e62839c36ecf7f4100","abstract_canon_sha256":"e4103e79af5737f58d641ce069b7ae4e271c326fb18e0e967c5a2fca74fbaa61"},"schema_version":"1.0"},"canonical_sha256":"affc06238ef86ccab81174bc36b1341037995a1d9047c9970f151b3070ba5201","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:34.078901Z","signature_b64":"lRYH7mz2KlSqTNNPjOF2DKGfTqjYZyHJ7rzVjLSK4RQCp2sUOMAsByX5fNvL5GRY0hN0sAsCy8O85zmNgkV5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"affc06238ef86ccab81174bc36b1341037995a1d9047c9970f151b3070ba5201","last_reissued_at":"2026-07-05T10:12:34.078403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:34.078403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07188","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":"2026-07-05T10:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C5y6d7yG/P7PJ9RZzFv+ZyKhikjlIrVqyoTybgklM+8jo/PX7j8gCDRwqC+xIX/CMVJ7BjwMknHzBMOwtJRmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:12:05.278750Z"},"content_sha256":"78fd9bec478dcff6860cecc5e196c0dd67a69ed11a9b6664a1c5c02d1bf7d936","schema_version":"1.0","event_id":"sha256:78fd9bec478dcff6860cecc5e196c0dd67a69ed11a9b6664a1c5c02d1bf7d936"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V76AMI4O7BWMVOAROS6DNMJUCA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large-Scale Benchmark for Vietnamese Sentence Paraphrases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kiet Van Nguyen, Sang Quang Nguyen","submitted_at":"2025-02-11T02:30:21Z","abstract_excerpt":"This paper presents ViSP, a high-quality Vietnamese dataset for sentence paraphrasing, consisting of 1.2M original-paraphrase pairs collected from various domains. The dataset was constructed using a hybrid approach that combines automatic paraphrase generation with manual evaluation to ensure high quality. We conducted experiments using methods such as back-translation, EDA, and baseline models like BART and T5, as well as large language models (LLMs), including GPT-4o, Gemini-1.5, Aya, Qwen-2.5, and Meta-Llama-3.1 variants. To the best of our knowledge, this is the first large-scale study on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07188","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/2502.07188/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":"2026-07-05T10:12:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJ/EiEqeYHfVDL9jYQBsADxlUzSFzGa3rq1wdzBE+bHH5Cgx5Ecqck4x8MBG7l80tdPPXbD3PyKJpvVh028IBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:12:05.279294Z"},"content_sha256":"6d72c1d0db38d86e9236ef999c7e4942a758f289e2955d51cab75915dc71d133","schema_version":"1.0","event_id":"sha256:6d72c1d0db38d86e9236ef999c7e4942a758f289e2955d51cab75915dc71d133"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V76AMI4O7BWMVOAROS6DNMJUCA/bundle.json","state_url":"https://pith.science/pith/V76AMI4O7BWMVOAROS6DNMJUCA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V76AMI4O7BWMVOAROS6DNMJUCA/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":"2026-08-09T02:12:05Z","links":{"resolver":"https://pith.science/pith/V76AMI4O7BWMVOAROS6DNMJUCA","bundle":"https://pith.science/pith/V76AMI4O7BWMVOAROS6DNMJUCA/bundle.json","state":"https://pith.science/pith/V76AMI4O7BWMVOAROS6DNMJUCA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V76AMI4O7BWMVOAROS6DNMJUCA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V76AMI4O7BWMVOAROS6DNMJUCA","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":"e4103e79af5737f58d641ce069b7ae4e271c326fb18e0e967c5a2fca74fbaa61","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T02:30:21Z","title_canon_sha256":"11cd54ac5a64837ab887a235f897d3bb08275324d7b4d3e62839c36ecf7f4100"},"schema_version":"1.0","source":{"id":"2502.07188","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07188","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07188v1","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07188","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"pith_short_12","alias_value":"V76AMI4O7BWM","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"pith_short_16","alias_value":"V76AMI4O7BWMVOAR","created_at":"2026-07-05T10:12:34Z"},{"alias_kind":"pith_short_8","alias_value":"V76AMI4O","created_at":"2026-07-05T10:12:34Z"}],"graph_snapshots":[{"event_id":"sha256:6d72c1d0db38d86e9236ef999c7e4942a758f289e2955d51cab75915dc71d133","target":"graph","created_at":"2026-07-05T10:12:34Z","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/2502.07188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents ViSP, a high-quality Vietnamese dataset for sentence paraphrasing, consisting of 1.2M original-paraphrase pairs collected from various domains. The dataset was constructed using a hybrid approach that combines automatic paraphrase generation with manual evaluation to ensure high quality. We conducted experiments using methods such as back-translation, EDA, and baseline models like BART and T5, as well as large language models (LLMs), including GPT-4o, Gemini-1.5, Aya, Qwen-2.5, and Meta-Llama-3.1 variants. To the best of our knowledge, this is the first large-scale study on","authors_text":"Kiet Van Nguyen, Sang Quang Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T02:30:21Z","title":"A Large-Scale Benchmark for Vietnamese Sentence Paraphrases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07188","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":"sha256:78fd9bec478dcff6860cecc5e196c0dd67a69ed11a9b6664a1c5c02d1bf7d936","target":"record","created_at":"2026-07-05T10:12:34Z","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":"e4103e79af5737f58d641ce069b7ae4e271c326fb18e0e967c5a2fca74fbaa61","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-11T02:30:21Z","title_canon_sha256":"11cd54ac5a64837ab887a235f897d3bb08275324d7b4d3e62839c36ecf7f4100"},"schema_version":"1.0","source":{"id":"2502.07188","kind":"arxiv","version":1}},"canonical_sha256":"affc06238ef86ccab81174bc36b1341037995a1d9047c9970f151b3070ba5201","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"affc06238ef86ccab81174bc36b1341037995a1d9047c9970f151b3070ba5201","first_computed_at":"2026-07-05T10:12:34.078403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:34.078403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lRYH7mz2KlSqTNNPjOF2DKGfTqjYZyHJ7rzVjLSK4RQCp2sUOMAsByX5fNvL5GRY0hN0sAsCy8O85zmNgkV5CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:34.078901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07188","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78fd9bec478dcff6860cecc5e196c0dd67a69ed11a9b6664a1c5c02d1bf7d936","sha256:6d72c1d0db38d86e9236ef999c7e4942a758f289e2955d51cab75915dc71d133"],"state_sha256":"438dd26d8becfe19afee90406435ecd66133c32d7e74c1f991969a9b61f059ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bw4HRDptQBFve9b0075DfNYrtn1vPnaH+d+5lLzlf3giHs8/jPjFpS3UdFXPrhcMsiay6PmjknO0Whh7l7kQAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:12:05.283717Z","bundle_sha256":"bbd92bfb337fc3ab77688a37607e3c05c3282e7caef708689f92d73ba9bcf8bb"}}