{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YGHF5NPXSVISPG7XP5WBDWPANR","short_pith_number":"pith:YGHF5NPX","canonical_record":{"source":{"id":"2210.05109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T02:52:31Z","cross_cats_sorted":[],"title_canon_sha256":"71fb834665fbbe0a0249297a776406c1514927dadca446b5c0d85230e28744e8","abstract_canon_sha256":"409f3e75780529c5b41b74847482b8efb23e7c3905269fbf868570993d0b9051"},"schema_version":"1.0"},"canonical_sha256":"c18e5eb5f79551279bf77f6c11d9e06c635f62cfdd5d3ef670f83596ce73cffd","source":{"kind":"arxiv","id":"2210.05109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05109","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05109v1","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05109","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"YGHF5NPXSVIS","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"YGHF5NPXSVISPG7X","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"YGHF5NPX","created_at":"2026-07-05T05:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YGHF5NPXSVISPG7XP5WBDWPANR","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T02:52:31Z","cross_cats_sorted":[],"title_canon_sha256":"71fb834665fbbe0a0249297a776406c1514927dadca446b5c0d85230e28744e8","abstract_canon_sha256":"409f3e75780529c5b41b74847482b8efb23e7c3905269fbf868570993d0b9051"},"schema_version":"1.0"},"canonical_sha256":"c18e5eb5f79551279bf77f6c11d9e06c635f62cfdd5d3ef670f83596ce73cffd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:12.958586Z","signature_b64":"n4+tpQbwPVYP3S5Uw5kbeueo5UMNtxxqbTTV3GoDsAbXc4LfKDVqd9RsF78DSN/muIAJFp7Tps9E9TS/e3zoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c18e5eb5f79551279bf77f6c11d9e06c635f62cfdd5d3ef670f83596ce73cffd","last_reissued_at":"2026-07-05T05:05:12.957992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:12.957992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05109","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":"2026-07-05T05:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUy5I42I/UCFN1uIaPAFQamnHCxlVQ9BI+XmFy56FakchV9WyqyrwUnQrAC0H0gG9v0bm11riv3ceWy3q9skBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:44.478447Z"},"content_sha256":"848d20a76065d2b16c20db9b550bef467b230414ff9150f9dd903a7653e2d825","schema_version":"1.0","event_id":"sha256:848d20a76065d2b16c20db9b550bef467b230414ff9150f9dd903a7653e2d825"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YGHF5NPXSVISPG7XP5WBDWPANR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Ajwad Akil, Najrin Sultana, Rifat Shahriyar","submitted_at":"2022-10-11T02:52:31Z","abstract_excerpt":"In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline. We aim to take a step towards alleviating the low resource status of the Bangla language in the NLP domain through the introduction of BanglaParaphrase, which ensures quality by preserving both semantics and diversity, making it particularly useful to enhance other Bangla datasets. We show a detailed comparative analysis between our dataset and models trained on it with other existing works to establish the viability of our synthetic paraphrase data generation pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05109","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/2210.05109/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":"2026-07-05T05:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6j5qytiLR/QeS/YhZjmUXwqwSrZjPK57vlwzzouAxvAN/KdJzEAfgkJYkfM+r5+YFmxMpxnYjl99eHFUSCkLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:55:44.478979Z"},"content_sha256":"81147e63869b6739bb8bea6913c143d12fdd6f00577d7a8d71a65d7608934d98","schema_version":"1.0","event_id":"sha256:81147e63869b6739bb8bea6913c143d12fdd6f00577d7a8d71a65d7608934d98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGHF5NPXSVISPG7XP5WBDWPANR/bundle.json","state_url":"https://pith.science/pith/YGHF5NPXSVISPG7XP5WBDWPANR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGHF5NPXSVISPG7XP5WBDWPANR/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":"2026-08-03T15:55:44Z","links":{"resolver":"https://pith.science/pith/YGHF5NPXSVISPG7XP5WBDWPANR","bundle":"https://pith.science/pith/YGHF5NPXSVISPG7XP5WBDWPANR/bundle.json","state":"https://pith.science/pith/YGHF5NPXSVISPG7XP5WBDWPANR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGHF5NPXSVISPG7XP5WBDWPANR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YGHF5NPXSVISPG7XP5WBDWPANR","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":"409f3e75780529c5b41b74847482b8efb23e7c3905269fbf868570993d0b9051","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T02:52:31Z","title_canon_sha256":"71fb834665fbbe0a0249297a776406c1514927dadca446b5c0d85230e28744e8"},"schema_version":"1.0","source":{"id":"2210.05109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05109","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05109v1","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05109","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"YGHF5NPXSVIS","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"YGHF5NPXSVISPG7X","created_at":"2026-07-05T05:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"YGHF5NPX","created_at":"2026-07-05T05:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:81147e63869b6739bb8bea6913c143d12fdd6f00577d7a8d71a65d7608934d98","target":"graph","created_at":"2026-07-05T05:05:12Z","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/2210.05109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline. We aim to take a step towards alleviating the low resource status of the Bangla language in the NLP domain through the introduction of BanglaParaphrase, which ensures quality by preserving both semantics and diversity, making it particularly useful to enhance other Bangla datasets. We show a detailed comparative analysis between our dataset and models trained on it with other existing works to establish the viability of our synthetic paraphrase data generation pi","authors_text":"Abhik Bhattacharjee, Ajwad Akil, Najrin Sultana, Rifat Shahriyar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T02:52:31Z","title":"BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05109","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":"sha256:848d20a76065d2b16c20db9b550bef467b230414ff9150f9dd903a7653e2d825","target":"record","created_at":"2026-07-05T05:05:12Z","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":"409f3e75780529c5b41b74847482b8efb23e7c3905269fbf868570993d0b9051","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-11T02:52:31Z","title_canon_sha256":"71fb834665fbbe0a0249297a776406c1514927dadca446b5c0d85230e28744e8"},"schema_version":"1.0","source":{"id":"2210.05109","kind":"arxiv","version":1}},"canonical_sha256":"c18e5eb5f79551279bf77f6c11d9e06c635f62cfdd5d3ef670f83596ce73cffd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c18e5eb5f79551279bf77f6c11d9e06c635f62cfdd5d3ef670f83596ce73cffd","first_computed_at":"2026-07-05T05:05:12.957992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:12.957992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n4+tpQbwPVYP3S5Uw5kbeueo5UMNtxxqbTTV3GoDsAbXc4LfKDVqd9RsF78DSN/muIAJFp7Tps9E9TS/e3zoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:12.958586Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:848d20a76065d2b16c20db9b550bef467b230414ff9150f9dd903a7653e2d825","sha256:81147e63869b6739bb8bea6913c143d12fdd6f00577d7a8d71a65d7608934d98"],"state_sha256":"936a8842b473f3970200863440ea72b315ecd312ca39e618fadcdd477efad0bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUxJlh/w1W+RRmfVHveitFJgSmq7ZALRRoxFfiAaIaxImkATlxbN4oPJvNA8/Kt9kBegyaqMlDjrEljbp4cWCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:55:44.482613Z","bundle_sha256":"4475e2d2a7bcd7e0e77d990b2d72a4edfa0f2bc40128fb81f9f89072595d3812"}}