{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:M7ZS3TLYBQOD224EGHKB2K6TRS","short_pith_number":"pith:M7ZS3TLY","canonical_record":{"source":{"id":"2403.06350","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T00:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"c1cbb7d090af8b38e987feee6dfc19916dfb55e2093a60d8adf555c9efbd7a54","abstract_canon_sha256":"7b659aa832f7d515fd949aac4ff70d3857b377318c5e25b8573d54fc4820f395"},"schema_version":"1.0"},"canonical_sha256":"67f32dcd780c1c3d6b8431d41d2bd38c96373ac15863a7f268076d67fc9f3166","source":{"kind":"arxiv","id":"2403.06350","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06350","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06350v2","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06350","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"pith_short_12","alias_value":"M7ZS3TLYBQOD","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"pith_short_16","alias_value":"M7ZS3TLYBQOD224E","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"pith_short_8","alias_value":"M7ZS3TLY","created_at":"2026-07-05T09:41:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:M7ZS3TLYBQOD224EGHKB2K6TRS","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06350","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T00:46:56Z","cross_cats_sorted":[],"title_canon_sha256":"c1cbb7d090af8b38e987feee6dfc19916dfb55e2093a60d8adf555c9efbd7a54","abstract_canon_sha256":"7b659aa832f7d515fd949aac4ff70d3857b377318c5e25b8573d54fc4820f395"},"schema_version":"1.0"},"canonical_sha256":"67f32dcd780c1c3d6b8431d41d2bd38c96373ac15863a7f268076d67fc9f3166","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:32.948062Z","signature_b64":"y1rNGv8uya2489IgCkF7vW6Nn+63xH6Qjira3zmR93G5/A/BvwP3K+bHPFuTeK08yKupPEGdKLh5E1KeKs3iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67f32dcd780c1c3d6b8431d41d2bd38c96373ac15863a7f268076d67fc9f3166","last_reissued_at":"2026-07-05T09:41:32.947608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:32.947608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06350","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":"2026-07-05T09:41:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8ZY16g/FnEV+f6RXga1ZEIWivjFLRKqvwLrZF2JIFhRfRDZQXqUWULySs74Ni2L6z9M+4ksJMMwGR+nHVLZlAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:43:31.769086Z"},"content_sha256":"affd6cf0037595efbd1fc517ef448b9598deb3eedec1b0f4e427ae9bd26e5264","schema_version":"1.0","event_id":"sha256:affd6cf0037595efbd1fc517ef448b9598deb3eedec1b0f4e427ae9bd26e5264"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:M7ZS3TLYBQOD224EGHKB2K6TRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ananth Sankar, Anoop Kunchukuttan, Mitesh M. Khapra, Mohammed Safi Ur Rahman Khan, Pratyush Kumar, Priyam Mehta, Raj Dabre, Sparsh Jain, Sumanth Doddapaneni, Suriyaprasaad B, Umashankar Kumaravelan, Varun Balan G","submitted_at":"2024-03-11T00:46:56Z","abstract_excerpt":"Despite the considerable advancements in English LLMs, the progress in building comparable models for other languages has been hindered due to the scarcity of tailored resources. Our work aims to bridge this divide by introducing an expansive suite of resources specifically designed for the development of Indic LLMs, covering 22 languages, containing a total of 251B tokens and 74.8M instruction-response pairs. Recognizing the importance of both data quality and quantity, our approach combines highly curated manually verified data, unverified yet valuable data, and synthetic data. We build a cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06350","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/2403.06350/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":"2026-07-05T09:41:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0RC57rNlW6UdL7vFqBPe0FaFFJ+xs2PmGH7yN9Z+GLXi44/QDkYm85xN/n+Xx7B775n6AWkdN1zLjJXNzB4cAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T05:43:31.769799Z"},"content_sha256":"d01ca84c5f893e350b29ccbbf8bd44ee3d16d1ea5214f5544f664ee6aa8bcd9e","schema_version":"1.0","event_id":"sha256:d01ca84c5f893e350b29ccbbf8bd44ee3d16d1ea5214f5544f664ee6aa8bcd9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7ZS3TLYBQOD224EGHKB2K6TRS/bundle.json","state_url":"https://pith.science/pith/M7ZS3TLYBQOD224EGHKB2K6TRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7ZS3TLYBQOD224EGHKB2K6TRS/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":"2026-08-17T05:43:31Z","links":{"resolver":"https://pith.science/pith/M7ZS3TLYBQOD224EGHKB2K6TRS","bundle":"https://pith.science/pith/M7ZS3TLYBQOD224EGHKB2K6TRS/bundle.json","state":"https://pith.science/pith/M7ZS3TLYBQOD224EGHKB2K6TRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7ZS3TLYBQOD224EGHKB2K6TRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7ZS3TLYBQOD224EGHKB2K6TRS","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":"7b659aa832f7d515fd949aac4ff70d3857b377318c5e25b8573d54fc4820f395","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T00:46:56Z","title_canon_sha256":"c1cbb7d090af8b38e987feee6dfc19916dfb55e2093a60d8adf555c9efbd7a54"},"schema_version":"1.0","source":{"id":"2403.06350","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06350","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06350v2","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06350","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"pith_short_12","alias_value":"M7ZS3TLYBQOD","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"pith_short_16","alias_value":"M7ZS3TLYBQOD224E","created_at":"2026-07-05T09:41:32Z"},{"alias_kind":"pith_short_8","alias_value":"M7ZS3TLY","created_at":"2026-07-05T09:41:32Z"}],"graph_snapshots":[{"event_id":"sha256:d01ca84c5f893e350b29ccbbf8bd44ee3d16d1ea5214f5544f664ee6aa8bcd9e","target":"graph","created_at":"2026-07-05T09:41:32Z","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/2403.06350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the considerable advancements in English LLMs, the progress in building comparable models for other languages has been hindered due to the scarcity of tailored resources. Our work aims to bridge this divide by introducing an expansive suite of resources specifically designed for the development of Indic LLMs, covering 22 languages, containing a total of 251B tokens and 74.8M instruction-response pairs. Recognizing the importance of both data quality and quantity, our approach combines highly curated manually verified data, unverified yet valuable data, and synthetic data. We build a cl","authors_text":"Ananth Sankar, Anoop Kunchukuttan, Mitesh M. Khapra, Mohammed Safi Ur Rahman Khan, Pratyush Kumar, Priyam Mehta, Raj Dabre, Sparsh Jain, Sumanth Doddapaneni, Suriyaprasaad B, Umashankar Kumaravelan, Varun Balan G","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T00:46:56Z","title":"IndicLLMSuite: A Blueprint for Creating Pre-training and Fine-Tuning Datasets for Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06350","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:affd6cf0037595efbd1fc517ef448b9598deb3eedec1b0f4e427ae9bd26e5264","target":"record","created_at":"2026-07-05T09:41:32Z","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":"7b659aa832f7d515fd949aac4ff70d3857b377318c5e25b8573d54fc4820f395","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T00:46:56Z","title_canon_sha256":"c1cbb7d090af8b38e987feee6dfc19916dfb55e2093a60d8adf555c9efbd7a54"},"schema_version":"1.0","source":{"id":"2403.06350","kind":"arxiv","version":2}},"canonical_sha256":"67f32dcd780c1c3d6b8431d41d2bd38c96373ac15863a7f268076d67fc9f3166","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67f32dcd780c1c3d6b8431d41d2bd38c96373ac15863a7f268076d67fc9f3166","first_computed_at":"2026-07-05T09:41:32.947608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:32.947608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y1rNGv8uya2489IgCkF7vW6Nn+63xH6Qjira3zmR93G5/A/BvwP3K+bHPFuTeK08yKupPEGdKLh5E1KeKs3iCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:32.948062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06350","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:affd6cf0037595efbd1fc517ef448b9598deb3eedec1b0f4e427ae9bd26e5264","sha256:d01ca84c5f893e350b29ccbbf8bd44ee3d16d1ea5214f5544f664ee6aa8bcd9e"],"state_sha256":"5d4c654bb7c31d53749ff935239e00d6ee6b902988ccf25ef52724ac83ae708d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQWgij1UxkLBLdcpHTWq7tomDG+cBHKmRd6MBNOGf81LrRYaoDsndYmVYDJIeEs8YOG0CZtTxSZ7Fs5Xwh2eAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T05:43:31.775887Z","bundle_sha256":"d5235cc411192437a6a81ab7f8024ee91198c4bfdc9603cba04424ed0a4f491d"}}