{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SATFN2H76O46VZOQTBFQGJ2HEV","short_pith_number":"pith:SATFN2H7","canonical_record":{"source":{"id":"2501.00029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897","abstract_canon_sha256":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1"},"schema_version":"1.0"},"canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","source":{"kind":"arxiv","id":"2501.00029","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00029","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00029v1","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00029","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"SATFN2H76O46","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"SATFN2H76O46VZOQ","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"SATFN2H7","created_at":"2026-07-05T09:55:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SATFN2H76O46VZOQTBFQGJ2HEV","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897","abstract_canon_sha256":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1"},"schema_version":"1.0"},"canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:37.891093Z","signature_b64":"foQyH6CA3pbYWgImxtlRnlgxzRlzLjIeM11fS8p5AdLzmgCvvW978MkBEehxxwyXExP73OCuan2owb+B22bZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","last_reissued_at":"2026-07-05T09:55:37.890629Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:37.890629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00029","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":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bB1unq5Uu2qNrKD9CGnBFR3AeqGg9rKX8RkKjxBJEXnJ/QzNrtFpKQTF7sqLct9Sb1X9LO5mnu1KL+l6pJPQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:57:31.991514Z"},"content_sha256":"cc82b377d13ae4286dad12638ee7ba4ad8657a19e98fd2e8e841a4a5acf292cb","schema_version":"1.0","event_id":"sha256:cc82b377d13ae4286dad12638ee7ba4ad8657a19e98fd2e8e841a4a5acf292cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SATFN2H76O46VZOQTBFQGJ2HEV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Breadth-First Catalog of Text Processing, Speech Processing and Multimodal Research in South Asian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pranav Gupta","submitted_at":"2024-12-20T20:08:48Z","abstract_excerpt":"We review the recent literature (January 2022- October 2024) in South Asian languages on text-based language processing, multimodal models, and speech processing, and provide a spotlight analysis focused on 21 low-resource South Asian languages, namely Saraiki, Assamese, Balochi, Bhojpuri, Bodo, Burmese, Chhattisgarhi, Dhivehi, Gujarati, Kannada, Kashmiri, Konkani, Khasi, Malayalam, Meitei, Nepali, Odia, Pashto, Rajasthani, Sindhi, and Telugu. We identify trends, challenges, and future research directions, using a step-wise approach that incorporates relevance classification and clustering bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00029","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/2501.00029/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":"2026-07-05T09:55:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5a8NHhgdSwaDvwqRs3yWJiwCXZdkC3u4DpWOAT/rdCn/T30am/lZHCYqq02BtFIW2FhjEQ+G9HOpRMal/7TDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T03:57:31.992015Z"},"content_sha256":"ee3b2ab521091a5af32f6428aa990af4500da0b06d1e2379ce939038ff7ed56a","schema_version":"1.0","event_id":"sha256:ee3b2ab521091a5af32f6428aa990af4500da0b06d1e2379ce939038ff7ed56a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/bundle.json","state_url":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SATFN2H76O46VZOQTBFQGJ2HEV/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":"2026-08-15T03:57:31Z","links":{"resolver":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV","bundle":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/bundle.json","state":"https://pith.science/pith/SATFN2H76O46VZOQTBFQGJ2HEV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SATFN2H76O46VZOQTBFQGJ2HEV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SATFN2H76O46VZOQTBFQGJ2HEV","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":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897"},"schema_version":"1.0","source":{"id":"2501.00029","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00029","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00029v1","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00029","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_12","alias_value":"SATFN2H76O46","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_16","alias_value":"SATFN2H76O46VZOQ","created_at":"2026-07-05T09:55:37Z"},{"alias_kind":"pith_short_8","alias_value":"SATFN2H7","created_at":"2026-07-05T09:55:37Z"}],"graph_snapshots":[{"event_id":"sha256:ee3b2ab521091a5af32f6428aa990af4500da0b06d1e2379ce939038ff7ed56a","target":"graph","created_at":"2026-07-05T09:55:37Z","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/2501.00029/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We review the recent literature (January 2022- October 2024) in South Asian languages on text-based language processing, multimodal models, and speech processing, and provide a spotlight analysis focused on 21 low-resource South Asian languages, namely Saraiki, Assamese, Balochi, Bhojpuri, Bodo, Burmese, Chhattisgarhi, Dhivehi, Gujarati, Kannada, Kashmiri, Konkani, Khasi, Malayalam, Meitei, Nepali, Odia, Pashto, Rajasthani, Sindhi, and Telugu. We identify trends, challenges, and future research directions, using a step-wise approach that incorporates relevance classification and clustering bas","authors_text":"Pranav Gupta","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","title":"A Breadth-First Catalog of Text Processing, Speech Processing and Multimodal Research in South Asian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00029","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:cc82b377d13ae4286dad12638ee7ba4ad8657a19e98fd2e8e841a4a5acf292cb","target":"record","created_at":"2026-07-05T09:55:37Z","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":"11a943b876030052440eaa738e22aa5f79f78827c67ae43dc84f093a531b73b1","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T20:08:48Z","title_canon_sha256":"46a1957b0fe4aed7afb8638938fea9af174dcffe9577eb92211f714808171897"},"schema_version":"1.0","source":{"id":"2501.00029","kind":"arxiv","version":1}},"canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"902656e8fff3b9eae5d0984b032747257e78fc5ccbcec66534e8f089ece5fddb","first_computed_at":"2026-07-05T09:55:37.890629Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:37.890629Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"foQyH6CA3pbYWgImxtlRnlgxzRlzLjIeM11fS8p5AdLzmgCvvW978MkBEehxxwyXExP73OCuan2owb+B22bZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:37.891093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00029","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc82b377d13ae4286dad12638ee7ba4ad8657a19e98fd2e8e841a4a5acf292cb","sha256:ee3b2ab521091a5af32f6428aa990af4500da0b06d1e2379ce939038ff7ed56a"],"state_sha256":"5d6f63f755be86cb8e62a9a5ad1dc765818159031ad4cddfb072b956f9879df9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Apf7tmRomyqyjJ0d1kb8tjd+dWAkbtVuzzC11LRfBo38QtlvBY13aFPfvS59qWDVKbi7MxtEjpSC79+GRQ5dBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T03:57:31.995657Z","bundle_sha256":"bcfd7fa0df0ac22b4dcae8a43c93653f9e1900fa449217497ce42a1d404bb1eb"}}