{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YSLS67TDDJKNW5H3WEQ7KQMB3C","short_pith_number":"pith:YSLS67TD","canonical_record":{"source":{"id":"2608.07727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T19:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"b742cfb3c952e8a0d545ececc3de4d1108840c5ceaff176f425c9b4941047be1","abstract_canon_sha256":"3075fca6a8719d10e5152df8dc71ec3441de5a76461e2580cf5f3aa9b0bfa853"},"schema_version":"1.0"},"canonical_sha256":"c4972f7e631a54db74fbb121f54181d8b175a974500796549a3467d255ae3f05","source":{"kind":"arxiv","id":"2608.07727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07727","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07727v1","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07727","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"YSLS67TDDJKN","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"YSLS67TDDJKNW5H3","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"YSLS67TD","created_at":"2026-08-11T00:15:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YSLS67TDDJKNW5H3WEQ7KQMB3C","target":"record","payload":{"canonical_record":{"source":{"id":"2608.07727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T19:33:11Z","cross_cats_sorted":[],"title_canon_sha256":"b742cfb3c952e8a0d545ececc3de4d1108840c5ceaff176f425c9b4941047be1","abstract_canon_sha256":"3075fca6a8719d10e5152df8dc71ec3441de5a76461e2580cf5f3aa9b0bfa853"},"schema_version":"1.0"},"canonical_sha256":"c4972f7e631a54db74fbb121f54181d8b175a974500796549a3467d255ae3f05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T00:15:47.693200Z","signature_b64":"UwkvGtd1D3YkzlDxL90UG4rdrHWcnhZqwCOWiyjJK5pb0mE2Htzo7ddiZFVg0Xma0wxT/yL/5BFfl/LJAb0vBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4972f7e631a54db74fbb121f54181d8b175a974500796549a3467d255ae3f05","last_reissued_at":"2026-08-11T00:15:47.690896Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T00:15:47.690896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.07727","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":"2026-08-11T00:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvxrhgxaUF3XdwKqic6SChCufeVENIOzXK+VjpAGcDF66lLvnFfP0INusxWc1SeP6Dz+cO+PTZrY5kASPha2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:30:02.938643Z"},"content_sha256":"98a999a39ecb7aef9342431144ac7111f5be300b73a7845fedad02e376e441fe","schema_version":"1.0","event_id":"sha256:98a999a39ecb7aef9342431144ac7111f5be300b73a7845fedad02e376e441fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YSLS67TDDJKNW5H3WEQ7KQMB3C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Dedicated Monolingual and Joint Multilingual Causal Models for Dravidian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Venkata Naga Sai Vishnu Rohit Pulipaka","submitted_at":"2026-08-07T19:33:11Z","abstract_excerpt":"Dravidian languages, mainly Tamil, Telugu, Kannada, and Malayalam make up only a small part of the data used to train multilingual language models, so it's not clear how much per-language ability these models actually keep. I have trained five GPT-2 architecture models from scratch to compare four monolingual models (one each for Tamil, Telugu, Kannada, and Malayalam, each with its own 32K-vocabulary subword tokenizer) against one multilingual model sharing a 64K-vocabulary subword tokenizer across all four languages. All the 5 models are trained on cleaned CC-100, Wikipedia, and Samanantar da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07727","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/2608.07727/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":"2026-08-11T00:15:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"re7pnx0b1PE0D2+///C5/7xINOdkRLZ8LiKeSfs3WJlam+mbSGjzcPP3ogGulY0DpmcZtLSHUmQgLaLr82hTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:30:02.939148Z"},"content_sha256":"f99e68db082af4633fc460e75a1905e3d078137b77a59138839854262fa69db4","schema_version":"1.0","event_id":"sha256:f99e68db082af4633fc460e75a1905e3d078137b77a59138839854262fa69db4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C/bundle.json","state_url":"https://pith.science/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C/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":"2026-08-12T06:30:02Z","links":{"resolver":"https://pith.science/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C","bundle":"https://pith.science/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C/bundle.json","state":"https://pith.science/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YSLS67TDDJKNW5H3WEQ7KQMB3C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YSLS67TDDJKNW5H3WEQ7KQMB3C","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":"3075fca6a8719d10e5152df8dc71ec3441de5a76461e2580cf5f3aa9b0bfa853","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T19:33:11Z","title_canon_sha256":"b742cfb3c952e8a0d545ececc3de4d1108840c5ceaff176f425c9b4941047be1"},"schema_version":"1.0","source":{"id":"2608.07727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07727","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07727v1","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07727","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"pith_short_12","alias_value":"YSLS67TDDJKN","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"pith_short_16","alias_value":"YSLS67TDDJKNW5H3","created_at":"2026-08-11T00:15:47Z"},{"alias_kind":"pith_short_8","alias_value":"YSLS67TD","created_at":"2026-08-11T00:15:47Z"}],"graph_snapshots":[{"event_id":"sha256:f99e68db082af4633fc460e75a1905e3d078137b77a59138839854262fa69db4","target":"graph","created_at":"2026-08-11T00:15:47Z","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/2608.07727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dravidian languages, mainly Tamil, Telugu, Kannada, and Malayalam make up only a small part of the data used to train multilingual language models, so it's not clear how much per-language ability these models actually keep. I have trained five GPT-2 architecture models from scratch to compare four monolingual models (one each for Tamil, Telugu, Kannada, and Malayalam, each with its own 32K-vocabulary subword tokenizer) against one multilingual model sharing a 64K-vocabulary subword tokenizer across all four languages. All the 5 models are trained on cleaned CC-100, Wikipedia, and Samanantar da","authors_text":"Venkata Naga Sai Vishnu Rohit Pulipaka","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T19:33:11Z","title":"Evaluating Dedicated Monolingual and Joint Multilingual Causal Models for Dravidian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07727","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":"sha256:98a999a39ecb7aef9342431144ac7111f5be300b73a7845fedad02e376e441fe","target":"record","created_at":"2026-08-11T00:15:47Z","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":"3075fca6a8719d10e5152df8dc71ec3441de5a76461e2580cf5f3aa9b0bfa853","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-07T19:33:11Z","title_canon_sha256":"b742cfb3c952e8a0d545ececc3de4d1108840c5ceaff176f425c9b4941047be1"},"schema_version":"1.0","source":{"id":"2608.07727","kind":"arxiv","version":1}},"canonical_sha256":"c4972f7e631a54db74fbb121f54181d8b175a974500796549a3467d255ae3f05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4972f7e631a54db74fbb121f54181d8b175a974500796549a3467d255ae3f05","first_computed_at":"2026-08-11T00:15:47.690896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T00:15:47.690896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UwkvGtd1D3YkzlDxL90UG4rdrHWcnhZqwCOWiyjJK5pb0mE2Htzo7ddiZFVg0Xma0wxT/yL/5BFfl/LJAb0vBg==","signature_status":"signed_v1","signed_at":"2026-08-11T00:15:47.693200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98a999a39ecb7aef9342431144ac7111f5be300b73a7845fedad02e376e441fe","sha256:f99e68db082af4633fc460e75a1905e3d078137b77a59138839854262fa69db4"],"state_sha256":"f2c2bc44ddb549513c6af0eabffd07949f4ffd8f8e810f52a7218f49ae6b3270"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVswfhA+uHMMH+yW1+3VGNQ9O2B6g1Uy4JRGXEOUuIk6ForycA0OQDaugPKbgA6DF8IU6II9WmHhHGLVKiiWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:30:02.944518Z","bundle_sha256":"2e50f9945076e688e21aa7d572b7ce14ef53ae3096f4095ef143cd2f09f982de"}}