{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MXOVDSLG2TFUQOZ4QCBBY366VP","short_pith_number":"pith:MXOVDSLG","canonical_record":{"source":{"id":"2106.03958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T20:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"1b10f8486e10621e56b9cf382d7369ee8bb51363d46cf5c5c22c3d573e9474df","abstract_canon_sha256":"386c6436e119b78c28bffb49e52e05ecd28b2b65c7b559dccffade582043f25f"},"schema_version":"1.0"},"canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","source":{"kind":"arxiv","id":"2106.03958","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03958","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03958v2","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03958","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"pith_short_12","alias_value":"MXOVDSLG2TFU","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"pith_short_16","alias_value":"MXOVDSLG2TFUQOZ4","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"pith_short_8","alias_value":"MXOVDSLG","created_at":"2026-07-05T02:47:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MXOVDSLG2TFUQOZ4QCBBY366VP","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T20:43:02Z","cross_cats_sorted":[],"title_canon_sha256":"1b10f8486e10621e56b9cf382d7369ee8bb51363d46cf5c5c22c3d573e9474df","abstract_canon_sha256":"386c6436e119b78c28bffb49e52e05ecd28b2b65c7b559dccffade582043f25f"},"schema_version":"1.0"},"canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:46.398176Z","signature_b64":"vID/oLJubkGIe4w6sbC3E4rCvoB2W2KEPxzFctCB0TQWyLkHywVW6xdtMzKdevEUZycinngIPgJ+n257lCopDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","last_reissued_at":"2026-07-05T02:47:46.397757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:46.397757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03958","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:47:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bJZbSnlB24StsRDf+1v1IzVcUErn+MHTnC3k/279kmDX62raaRbyt3D5zXzhrTfWJy2NSO/AvybVkr36uu+UDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:58.429246Z"},"content_sha256":"499aa4c0d1b2fc02a06426410e536e5f25f50dd7de902470d89e3df98e8392e7","schema_version":"1.0","event_id":"sha256:499aa4c0d1b2fc02a06426410e536e5f25f50dd7de902470d89e3df98e8392e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MXOVDSLG2TFUQOZ4QCBBY366VP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhijeet Awasthi, Partha Talukdar, Sarvesh Mehtani, Sunita Sarawagi, Vaidehi Patil, Yash Khemchandani","submitted_at":"2021-06-07T20:43:02Z","abstract_excerpt":"Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable transfer of supervision from high resource languages to LRLs. However, incorporating a new language in an LM still remains a challenge, particularly for languages with limited corpora and in unseen scripts. In this paper we argue that relatedness among languages in a language family may be exploited to overcome some of the corpora limitations of LRLs, and propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03958","kind":"arxiv","version":2},"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/2106.03958/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":"2026-07-05T02:47:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kRcG6nR7UN31I5gL9EECtWX1q3ItRvr6Jo0U/1T6UVTE1RrTn7VHQUtyyJrFiml/iup38GhNZbjEf1VwKJK7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:46:58.429747Z"},"content_sha256":"b53527415ff08bcfcea4eea592cd3f4a6fb339dfce4a6e0a89efa01f60f19cd3","schema_version":"1.0","event_id":"sha256:b53527415ff08bcfcea4eea592cd3f4a6fb339dfce4a6e0a89efa01f60f19cd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/bundle.json","state_url":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/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":"2026-08-07T04:46:58Z","links":{"resolver":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP","bundle":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/bundle.json","state":"https://pith.science/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXOVDSLG2TFUQOZ4QCBBY366VP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MXOVDSLG2TFUQOZ4QCBBY366VP","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":"386c6436e119b78c28bffb49e52e05ecd28b2b65c7b559dccffade582043f25f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T20:43:02Z","title_canon_sha256":"1b10f8486e10621e56b9cf382d7369ee8bb51363d46cf5c5c22c3d573e9474df"},"schema_version":"1.0","source":{"id":"2106.03958","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03958","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03958v2","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03958","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"pith_short_12","alias_value":"MXOVDSLG2TFU","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"pith_short_16","alias_value":"MXOVDSLG2TFUQOZ4","created_at":"2026-07-05T02:47:46Z"},{"alias_kind":"pith_short_8","alias_value":"MXOVDSLG","created_at":"2026-07-05T02:47:46Z"}],"graph_snapshots":[{"event_id":"sha256:b53527415ff08bcfcea4eea592cd3f4a6fb339dfce4a6e0a89efa01f60f19cd3","target":"graph","created_at":"2026-07-05T02:47:46Z","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/2106.03958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent research in multilingual language models (LM) has demonstrated their ability to effectively handle multiple languages in a single model. This holds promise for low web-resource languages (LRL) as multilingual models can enable transfer of supervision from high resource languages to LRLs. However, incorporating a new language in an LM still remains a challenge, particularly for languages with limited corpora and in unseen scripts. In this paper we argue that relatedness among languages in a language family may be exploited to overcome some of the corpora limitations of LRLs, and propose ","authors_text":"Abhijeet Awasthi, Partha Talukdar, Sarvesh Mehtani, Sunita Sarawagi, Vaidehi Patil, Yash Khemchandani","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T20:43:02Z","title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03958","kind":"arxiv","version":2},"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":"sha256:499aa4c0d1b2fc02a06426410e536e5f25f50dd7de902470d89e3df98e8392e7","target":"record","created_at":"2026-07-05T02:47:46Z","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":"386c6436e119b78c28bffb49e52e05ecd28b2b65c7b559dccffade582043f25f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-07T20:43:02Z","title_canon_sha256":"1b10f8486e10621e56b9cf382d7369ee8bb51363d46cf5c5c22c3d573e9474df"},"schema_version":"1.0","source":{"id":"2106.03958","kind":"arxiv","version":2}},"canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65dd51c966d4cb483b3c80821c6fdeabc978b3be04fbff1a8d8308cee3286715","first_computed_at":"2026-07-05T02:47:46.397757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:46.397757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vID/oLJubkGIe4w6sbC3E4rCvoB2W2KEPxzFctCB0TQWyLkHywVW6xdtMzKdevEUZycinngIPgJ+n257lCopDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:46.398176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03958","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:499aa4c0d1b2fc02a06426410e536e5f25f50dd7de902470d89e3df98e8392e7","sha256:b53527415ff08bcfcea4eea592cd3f4a6fb339dfce4a6e0a89efa01f60f19cd3"],"state_sha256":"d7d47ff365ae352be8eddac30d351567c06ca2b563abfcc87124ff6a040c91f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h9nKib+Sv6pjTDn2ycCrPi3vcIzexV7x97xAnybf4FEKpQLtLJYGhz3DuIit0kBkgxh9TrnM1IyHDCJX0MPABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:46:58.434048Z","bundle_sha256":"1824e4824d8ff0826b8e3d980b8edeaf527a5565bbe6125bdbf087ddd0e7b8c1"}}