{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:W3LZ3V3NPRB2FESE2XRYFIZJWU","short_pith_number":"pith:W3LZ3V3N","canonical_record":{"source":{"id":"2312.04764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T00:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"9d8b9b322da8f9f6697436458d5018b40a61958932ada10cf76eaa6dd3db58d3","abstract_canon_sha256":"a609210190713fde878985ada671b5e33558b890e4e420b2ca52cb3e48552011"},"schema_version":"1.0"},"canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","source":{"kind":"arxiv","id":"2312.04764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04764","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04764v1","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04764","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"W3LZ3V3NPRB2","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"W3LZ3V3NPRB2FESE","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"W3LZ3V3N","created_at":"2026-07-05T07:21:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:W3LZ3V3NPRB2FESE2XRYFIZJWU","target":"record","payload":{"canonical_record":{"source":{"id":"2312.04764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T00:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"9d8b9b322da8f9f6697436458d5018b40a61958932ada10cf76eaa6dd3db58d3","abstract_canon_sha256":"a609210190713fde878985ada671b5e33558b890e4e420b2ca52cb3e48552011"},"schema_version":"1.0"},"canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:51.047376Z","signature_b64":"HgDodxaP13/f7EmIVf/s2dhudYadzRCKQrH3MSLcnh+iqTXdCy2wV2rzkWkv60pElpyJ0hLl1Pna54hCDPYeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","last_reissued_at":"2026-07-05T07:21:51.046898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:51.046898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.04764","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":"2026-07-05T07:21:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xwCjWtv6W6LJjjI3TfQbXwCTbswedBBTpbmeONSoI3KweoP2+f034aErza9h/lhUsV9m3apHEf2toCxTmZedDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:55:30.076592Z"},"content_sha256":"791b0bfc4efbaf608b88d5ccede96650534cd0e9d74687f278f12fdb29e3d6ae","schema_version":"1.0","event_id":"sha256:791b0bfc4efbaf608b88d5ccede96650534cd0e9d74687f278f12fdb29e3d6ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:W3LZ3V3NPRB2FESE2XRYFIZJWU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananya Kalita, Atnafu Lambebo Tonja, Jugal Kalita, Melkamu Mersha, Olga Kolesnikova","submitted_at":"2023-12-08T00:28:41Z","abstract_excerpt":"This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04764","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/2312.04764/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":"2026-07-05T07:21:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ytk9Y4FVp7crBjONsUIBU41sk5g2Su3lGd38RwOg/rcd1PQWw8H7LBvlZ/5rLIn/gqfYpPGX0tF8Rn/HSYCyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:55:30.077109Z"},"content_sha256":"2a1bdd4a9f4a35e9b46e2dfecf6626d087c1d2db93141524cd469009e4180fa7","schema_version":"1.0","event_id":"sha256:2a1bdd4a9f4a35e9b46e2dfecf6626d087c1d2db93141524cd469009e4180fa7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/bundle.json","state_url":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/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":"2026-08-07T19:55:30Z","links":{"resolver":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU","bundle":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/bundle.json","state":"https://pith.science/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3LZ3V3NPRB2FESE2XRYFIZJWU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W3LZ3V3NPRB2FESE2XRYFIZJWU","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":"a609210190713fde878985ada671b5e33558b890e4e420b2ca52cb3e48552011","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T00:28:41Z","title_canon_sha256":"9d8b9b322da8f9f6697436458d5018b40a61958932ada10cf76eaa6dd3db58d3"},"schema_version":"1.0","source":{"id":"2312.04764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.04764","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.04764v1","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04764","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"W3LZ3V3NPRB2","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"W3LZ3V3NPRB2FESE","created_at":"2026-07-05T07:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"W3LZ3V3N","created_at":"2026-07-05T07:21:51Z"}],"graph_snapshots":[{"event_id":"sha256:2a1bdd4a9f4a35e9b46e2dfecf6626d087c1d2db93141524cd469009e4180fa7","target":"graph","created_at":"2026-07-05T07:21:51Z","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/2312.04764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents the creation of initial bilingual corpora for thirteen very low-resource languages of India, all from Northeast India. It also presents the results of initial translation efforts in these languages. It creates the first-ever parallel corpora for these languages and provides initial benchmark neural machine translation results for these languages. We intend to extend these corpora to include a large number of low-resource Indian languages and integrate the effort with our prior work with African and American-Indian languages to create corpora covering a large number of langu","authors_text":"Ananya Kalita, Atnafu Lambebo Tonja, Jugal Kalita, Melkamu Mersha, Olga Kolesnikova","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T00:28:41Z","title":"First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04764","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":"sha256:791b0bfc4efbaf608b88d5ccede96650534cd0e9d74687f278f12fdb29e3d6ae","target":"record","created_at":"2026-07-05T07:21:51Z","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":"a609210190713fde878985ada671b5e33558b890e4e420b2ca52cb3e48552011","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-08T00:28:41Z","title_canon_sha256":"9d8b9b322da8f9f6697436458d5018b40a61958932ada10cf76eaa6dd3db58d3"},"schema_version":"1.0","source":{"id":"2312.04764","kind":"arxiv","version":1}},"canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6d79dd76d7c43a29244d5e382a329b53da729f9cb7406114d0b341b81b2a848","first_computed_at":"2026-07-05T07:21:51.046898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:21:51.046898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HgDodxaP13/f7EmIVf/s2dhudYadzRCKQrH3MSLcnh+iqTXdCy2wV2rzkWkv60pElpyJ0hLl1Pna54hCDPYeDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:21:51.047376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.04764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:791b0bfc4efbaf608b88d5ccede96650534cd0e9d74687f278f12fdb29e3d6ae","sha256:2a1bdd4a9f4a35e9b46e2dfecf6626d087c1d2db93141524cd469009e4180fa7"],"state_sha256":"2bbc44318cdff5e782108aab5f87c1f4cdc49620cd56c18e3e2dd594e2426775"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rdgk9RuKLHNsJV0S/MZ/z3hPflARgr4PnpzsfqsWGZeTaW3OE/YK+td3l3LtrLw+PkXr4wSIVtBNX03dzvoaAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:55:30.082087Z","bundle_sha256":"e8051f9dd7e394fa9ffba97af1193bf44e78f62cdca1a0afa97163f146e69bd5"}}