{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SER5QZS7DZXLRGXT7V7NBDRKP4","short_pith_number":"pith:SER5QZS7","canonical_record":{"source":{"id":"2606.25365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T03:54:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fcb77ac7bcde3d37d9c5d2eaa93c2ea1d58f7854b0c4e98107bd324736810dbd","abstract_canon_sha256":"857b869fe2c6f7af94a28e2627a38f7957af924f34b7f3e52d5bc4a78f775051"},"schema_version":"1.0"},"canonical_sha256":"9123d8665f1e6eb89af3fd7ed08e2a7f2092f0dd134faa6c0137741f14e88567","source":{"kind":"arxiv","id":"2606.25365","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25365","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25365v1","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25365","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"SER5QZS7DZXL","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"SER5QZS7DZXLRGXT","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"SER5QZS7","created_at":"2026-06-25T01:18:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SER5QZS7DZXLRGXT7V7NBDRKP4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25365","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T03:54:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fcb77ac7bcde3d37d9c5d2eaa93c2ea1d58f7854b0c4e98107bd324736810dbd","abstract_canon_sha256":"857b869fe2c6f7af94a28e2627a38f7957af924f34b7f3e52d5bc4a78f775051"},"schema_version":"1.0"},"canonical_sha256":"9123d8665f1e6eb89af3fd7ed08e2a7f2092f0dd134faa6c0137741f14e88567","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:03.314506Z","signature_b64":"rvJMDRD2eKmmfa6ZPvueN7/Jj346rbec8ShNkUDE2uHVL0fKpLpzwv0jS2k6eePnyba8LGnSQLr95DKewi7oDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9123d8665f1e6eb89af3fd7ed08e2a7f2092f0dd134faa6c0137741f14e88567","last_reissued_at":"2026-06-25T01:18:03.314121Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:03.314121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25365","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":"2026-06-25T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"clT0bq17HrJJlmCKg4T991pD1AWmwF3IUPvsXWQu1nES3b+9aKlW6VTZp58S2zlb3qmwcCl0Ftl9eo3ronzhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:21:52.862531Z"},"content_sha256":"86290a76863e454b16ae231140fcc9ac1b6e2d80b8c5365d3d400c3bc142c119","schema_version":"1.0","event_id":"sha256:86290a76863e454b16ae231140fcc9ac1b6e2d80b8c5365d3d400c3bc142c119"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SER5QZS7DZXLRGXT7V7NBDRKP4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Machine Translation for Low-Resource Tangkhul--English","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Agniva Maiti, Chormi Zimik Vashai","submitted_at":"2026-06-24T03:54:46Z","abstract_excerpt":"We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Burman language spoken primarily in Manipur, India, with virtually no prior natural language processing infrastructure. We describe two systems: (1) a primary system based on ByT5-large fine-tuned on 38,336 Tangkhul-English parallel sentence pairs, and (2) a contrastive system based on mT5-small fine-tuned on the same corpus. Our primary ByT5-large system achieves a corpus BLEU score of 39.97, chrF++ of 58.07, BERTScore F1 of 0.8104, and COMET (w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25365","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/2606.25365/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":"2026-06-25T01:18:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qMlESPmMU4VI7WKkNZoGfmzEWW0IjOFuqnDkz6kx4qFpqcBcczNBG4sRW4EH6B+0IvipB+njr8/bvdyIgHUeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:21:52.862910Z"},"content_sha256":"520db86e1cf2c114cb59fded8127e38087ebd1eb9feb130fca709ad59bb40aa8","schema_version":"1.0","event_id":"sha256:520db86e1cf2c114cb59fded8127e38087ebd1eb9feb130fca709ad59bb40aa8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SER5QZS7DZXLRGXT7V7NBDRKP4/bundle.json","state_url":"https://pith.science/pith/SER5QZS7DZXLRGXT7V7NBDRKP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SER5QZS7DZXLRGXT7V7NBDRKP4/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":"2026-07-07T12:21:52Z","links":{"resolver":"https://pith.science/pith/SER5QZS7DZXLRGXT7V7NBDRKP4","bundle":"https://pith.science/pith/SER5QZS7DZXLRGXT7V7NBDRKP4/bundle.json","state":"https://pith.science/pith/SER5QZS7DZXLRGXT7V7NBDRKP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SER5QZS7DZXLRGXT7V7NBDRKP4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SER5QZS7DZXLRGXT7V7NBDRKP4","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":"857b869fe2c6f7af94a28e2627a38f7957af924f34b7f3e52d5bc4a78f775051","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T03:54:46Z","title_canon_sha256":"fcb77ac7bcde3d37d9c5d2eaa93c2ea1d58f7854b0c4e98107bd324736810dbd"},"schema_version":"1.0","source":{"id":"2606.25365","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25365","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25365v1","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25365","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_12","alias_value":"SER5QZS7DZXL","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_16","alias_value":"SER5QZS7DZXLRGXT","created_at":"2026-06-25T01:18:03Z"},{"alias_kind":"pith_short_8","alias_value":"SER5QZS7","created_at":"2026-06-25T01:18:03Z"}],"graph_snapshots":[{"event_id":"sha256:520db86e1cf2c114cb59fded8127e38087ebd1eb9feb130fca709ad59bb40aa8","target":"graph","created_at":"2026-06-25T01:18:03Z","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/2606.25365/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Burman language spoken primarily in Manipur, India, with virtually no prior natural language processing infrastructure. We describe two systems: (1) a primary system based on ByT5-large fine-tuned on 38,336 Tangkhul-English parallel sentence pairs, and (2) a contrastive system based on mT5-small fine-tuned on the same corpus. Our primary ByT5-large system achieves a corpus BLEU score of 39.97, chrF++ of 58.07, BERTScore F1 of 0.8104, and COMET (w","authors_text":"Agniva Maiti, Chormi Zimik Vashai","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T03:54:46Z","title":"Neural Machine Translation for Low-Resource Tangkhul--English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25365","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":"sha256:86290a76863e454b16ae231140fcc9ac1b6e2d80b8c5365d3d400c3bc142c119","target":"record","created_at":"2026-06-25T01:18:03Z","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":"857b869fe2c6f7af94a28e2627a38f7957af924f34b7f3e52d5bc4a78f775051","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T03:54:46Z","title_canon_sha256":"fcb77ac7bcde3d37d9c5d2eaa93c2ea1d58f7854b0c4e98107bd324736810dbd"},"schema_version":"1.0","source":{"id":"2606.25365","kind":"arxiv","version":1}},"canonical_sha256":"9123d8665f1e6eb89af3fd7ed08e2a7f2092f0dd134faa6c0137741f14e88567","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9123d8665f1e6eb89af3fd7ed08e2a7f2092f0dd134faa6c0137741f14e88567","first_computed_at":"2026-06-25T01:18:03.314121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:03.314121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvJMDRD2eKmmfa6ZPvueN7/Jj346rbec8ShNkUDE2uHVL0fKpLpzwv0jS2k6eePnyba8LGnSQLr95DKewi7oDQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:03.314506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25365","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86290a76863e454b16ae231140fcc9ac1b6e2d80b8c5365d3d400c3bc142c119","sha256:520db86e1cf2c114cb59fded8127e38087ebd1eb9feb130fca709ad59bb40aa8"],"state_sha256":"03b77fa168a8226f7f17d8814ea71279a7c6ca76beea04fffe61e06011f1c4be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N43cOyVKhlybedczRzZq5yjgXTzwsFrol93rHD/W7ygdhsnbiY1QcD/P8x7RzGUOh5VBdIULPV7YqFEFx3vVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:21:52.864849Z","bundle_sha256":"78c9899a5e059457653c0e7b3feca446b49a55d28d06a6384e7950ff9b40e219"}}