{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Z52T2LKOD5RF3QHGOD52TL5GWN","short_pith_number":"pith:Z52T2LKO","canonical_record":{"source":{"id":"2504.07989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:33:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f26d3d426193cd82829e892561ccda8393d22778a5c46de37989674dd5235013","abstract_canon_sha256":"1f4bef6d06ecf0ba3ffa87bc963165695d196debfa6cba7c37a23cdc3ef54d03"},"schema_version":"1.0"},"canonical_sha256":"cf753d2d4e1f625dc0e670fba9afa6b367ab69f2d8a21d6dcc3b9e6545df1067","source":{"kind":"arxiv","id":"2504.07989","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07989","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07989v2","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07989","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"Z52T2LKOD5RF","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"Z52T2LKOD5RF3QHG","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"Z52T2LKO","created_at":"2026-07-05T10:52:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Z52T2LKOD5RF3QHGOD52TL5GWN","target":"record","payload":{"canonical_record":{"source":{"id":"2504.07989","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:33:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f26d3d426193cd82829e892561ccda8393d22778a5c46de37989674dd5235013","abstract_canon_sha256":"1f4bef6d06ecf0ba3ffa87bc963165695d196debfa6cba7c37a23cdc3ef54d03"},"schema_version":"1.0"},"canonical_sha256":"cf753d2d4e1f625dc0e670fba9afa6b367ab69f2d8a21d6dcc3b9e6545df1067","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:22.217302Z","signature_b64":"d99xLToDYhcFLzgkGZqp9+J+zTcFCLxeNEd8RgemH4r1+Q7K+vQ8nrKlTBUTIjH/vprr2u4iokPSvoagkK34BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf753d2d4e1f625dc0e670fba9afa6b367ab69f2d8a21d6dcc3b9e6545df1067","last_reissued_at":"2026-07-05T10:52:22.216841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:22.216841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.07989","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":"2026-07-05T10:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wI6R8MQmffNLQlVx0qxbecCE6dWBdZ8drW6zmWCUn+tYOYw4I96OqyrI+Ux0VySjuLoCQO7m0fFyJn76SEUCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:47.109263Z"},"content_sha256":"168bec699162de6106a92ce6097a98ae8d1f7e9e7bc42882337b93175d60fdfd","schema_version":"1.0","event_id":"sha256:168bec699162de6106a92ce6097a98ae8d1f7e9e7bc42882337b93175d60fdfd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Z52T2LKOD5RF3QHGOD52TL5GWN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Agnivo Gosai, Anish Joshi, Anish Joshirao, Aryan Sagavekar, Guruprasad Pathak, Malhar Abhay Inamdar, Nirvan Patil, Rajat Dandekar, Raj Dandekar, Sreedath Panat","submitted_at":"2025-04-07T10:33:14Z","abstract_excerpt":"Small Language Models (SLMs) offer efficient alternatives to LLMs for specific domains. The 2023 TinyStories study developed an English dataset that allows SLMs with 1 to 10 million parameters to produce coherent outputs. Our research expands this framework by translating the original dataset into Indian languages and creating synthetic data using LLMs. We focus on Hindi, Marathi, and Bengali, evaluating SLMs for regional language processing and understanding linguistic complexity. We show that SLMs efficiently process regional languages with significantly fewer parameters than LLMs, providing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07989","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/2504.07989/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":"2026-07-05T10:52:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFHWG7IaPvKQXPhaxHJn3QANOWCEMM67gKwkKvE75MNq1Qbc8OqWa1D1cI+aK067yNm5PGBZ3KP6jy8DRiFuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:46:47.109662Z"},"content_sha256":"36b0adbea3b53434dc4cba6db76a0d23370f280d009cd89e09f56af143fab20f","schema_version":"1.0","event_id":"sha256:36b0adbea3b53434dc4cba6db76a0d23370f280d009cd89e09f56af143fab20f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z52T2LKOD5RF3QHGOD52TL5GWN/bundle.json","state_url":"https://pith.science/pith/Z52T2LKOD5RF3QHGOD52TL5GWN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z52T2LKOD5RF3QHGOD52TL5GWN/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":"2026-07-06T18:46:47Z","links":{"resolver":"https://pith.science/pith/Z52T2LKOD5RF3QHGOD52TL5GWN","bundle":"https://pith.science/pith/Z52T2LKOD5RF3QHGOD52TL5GWN/bundle.json","state":"https://pith.science/pith/Z52T2LKOD5RF3QHGOD52TL5GWN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z52T2LKOD5RF3QHGOD52TL5GWN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Z52T2LKOD5RF3QHGOD52TL5GWN","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":"1f4bef6d06ecf0ba3ffa87bc963165695d196debfa6cba7c37a23cdc3ef54d03","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:33:14Z","title_canon_sha256":"f26d3d426193cd82829e892561ccda8393d22778a5c46de37989674dd5235013"},"schema_version":"1.0","source":{"id":"2504.07989","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07989","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07989v2","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07989","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"pith_short_12","alias_value":"Z52T2LKOD5RF","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"pith_short_16","alias_value":"Z52T2LKOD5RF3QHG","created_at":"2026-07-05T10:52:22Z"},{"alias_kind":"pith_short_8","alias_value":"Z52T2LKO","created_at":"2026-07-05T10:52:22Z"}],"graph_snapshots":[{"event_id":"sha256:36b0adbea3b53434dc4cba6db76a0d23370f280d009cd89e09f56af143fab20f","target":"graph","created_at":"2026-07-05T10:52:22Z","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/2504.07989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Small Language Models (SLMs) offer efficient alternatives to LLMs for specific domains. The 2023 TinyStories study developed an English dataset that allows SLMs with 1 to 10 million parameters to produce coherent outputs. Our research expands this framework by translating the original dataset into Indian languages and creating synthetic data using LLMs. We focus on Hindi, Marathi, and Bengali, evaluating SLMs for regional language processing and understanding linguistic complexity. We show that SLMs efficiently process regional languages with significantly fewer parameters than LLMs, providing","authors_text":"Agnivo Gosai, Anish Joshi, Anish Joshirao, Aryan Sagavekar, Guruprasad Pathak, Malhar Abhay Inamdar, Nirvan Patil, Rajat Dandekar, Raj Dandekar, Sreedath Panat","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:33:14Z","title":"Regional Tiny Stories: Using Small Models to Compare Language Learning and Tokenizer Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07989","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":"sha256:168bec699162de6106a92ce6097a98ae8d1f7e9e7bc42882337b93175d60fdfd","target":"record","created_at":"2026-07-05T10:52:22Z","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":"1f4bef6d06ecf0ba3ffa87bc963165695d196debfa6cba7c37a23cdc3ef54d03","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T10:33:14Z","title_canon_sha256":"f26d3d426193cd82829e892561ccda8393d22778a5c46de37989674dd5235013"},"schema_version":"1.0","source":{"id":"2504.07989","kind":"arxiv","version":2}},"canonical_sha256":"cf753d2d4e1f625dc0e670fba9afa6b367ab69f2d8a21d6dcc3b9e6545df1067","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf753d2d4e1f625dc0e670fba9afa6b367ab69f2d8a21d6dcc3b9e6545df1067","first_computed_at":"2026-07-05T10:52:22.216841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:22.216841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d99xLToDYhcFLzgkGZqp9+J+zTcFCLxeNEd8RgemH4r1+Q7K+vQ8nrKlTBUTIjH/vprr2u4iokPSvoagkK34BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:22.217302Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07989","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:168bec699162de6106a92ce6097a98ae8d1f7e9e7bc42882337b93175d60fdfd","sha256:36b0adbea3b53434dc4cba6db76a0d23370f280d009cd89e09f56af143fab20f"],"state_sha256":"d137959c62a532ca138b3ef6741466a74279d124786078ebb1c0da98ab28230d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUE5AMAsj/y66r/RhhDd1nu13AGQefUYkZHk2rsK65uvH8fikGRWGXoS7T932v1JUWErW2D06Xkd/rpLGg0NCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:46:47.111751Z","bundle_sha256":"5d3353c3a183acf7ef5884a7929bbe04318c1ef34479419ff2a2a28098c49864"}}