{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BZORYYHYHU6IAG2EKV2MJYIXT7","short_pith_number":"pith:BZORYYHY","canonical_record":{"source":{"id":"2607.23319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T18:23:06Z","cross_cats_sorted":["cs.CY","cs.ET","cs.LG"],"title_canon_sha256":"51c401fc6775437ac04c675b473d80413abdea2fb1207e7dac1f43a27cc7823c","abstract_canon_sha256":"bb6f2c19b89a7104791febdcb18d512c99b44a67f15bfd26bdce09c651b1476d"},"schema_version":"1.0"},"canonical_sha256":"0e5d1c60f83d3c801b445574c4e1179ff3a6b52804f355ff418abc3e8823f7dc","source":{"kind":"arxiv","id":"2607.23319","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23319","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23319v1","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23319","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"BZORYYHYHU6I","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"BZORYYHYHU6IAG2E","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"BZORYYHY","created_at":"2026-07-28T01:22:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BZORYYHYHU6IAG2EKV2MJYIXT7","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T18:23:06Z","cross_cats_sorted":["cs.CY","cs.ET","cs.LG"],"title_canon_sha256":"51c401fc6775437ac04c675b473d80413abdea2fb1207e7dac1f43a27cc7823c","abstract_canon_sha256":"bb6f2c19b89a7104791febdcb18d512c99b44a67f15bfd26bdce09c651b1476d"},"schema_version":"1.0"},"canonical_sha256":"0e5d1c60f83d3c801b445574c4e1179ff3a6b52804f355ff418abc3e8823f7dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:47.537964Z","signature_b64":"lqrr2JzCkXOIi3aMWOmAnpY59wXmGCiZT5M/bbFiCq2+XDTDZC9f3lDkjOeZyXsUbQVTMpC23QcqdldnLFIjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e5d1c60f83d3c801b445574c4e1179ff3a6b52804f355ff418abc3e8823f7dc","last_reissued_at":"2026-07-28T01:22:47.537198Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:47.537198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23319","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":"2026-07-28T01:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JuhEbRFkpnqnzKSF+8C5kBHIRB4ECza/fR37nEc3EhDuctBpUm9EYjXcuN2YQW1uDIu5/FGsS2UKrXAwQ1N5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:56:13.892475Z"},"content_sha256":"dd39d05c1c22513a2759e315cbd9acf515941d62f6404d838802a6a7483fb7b6","schema_version":"1.0","event_id":"sha256:dd39d05c1c22513a2759e315cbd9acf515941d62f6404d838802a6a7483fb7b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BZORYYHYHU6IAG2EKV2MJYIXT7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.ET","cs.LG"],"primary_cat":"cs.CL","authors_text":"Lakshmi Rajendran, Pavithra Muruganantham, Poornima Kumaresan, Santhosh Sivasubramani","submitted_at":"2026-07-25T18:23:06Z","abstract_excerpt":"Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages. Sanskrit, Tamil, and other classical Indic languages exhibit agglutinative morphology, productive sandhi (phonological fusion at word boundaries), and domain-specific vocabularies absent from general-purpose training data. This paper presents BHARATI, a set of SentencePiece BPE tokenizers trained on a balanced 781 MB corpus spanning seven languages (English, Hindi, Sansk"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23319","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/2607.23319/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":"2026-07-28T01:22:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2U87l4y7mOfJDJbOlLptxVe+faFja57wwYYr+RTXYpIDo7NxPlFgsc8RFhaZO53b13/igFZPGp5Dz0W+D/tCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:56:13.893003Z"},"content_sha256":"4962c4a1cd8684f5e6bbacdb7652a9f8f30a54e1b6f953ccac8f55e27bfb049c","schema_version":"1.0","event_id":"sha256:4962c4a1cd8684f5e6bbacdb7652a9f8f30a54e1b6f953ccac8f55e27bfb049c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:BZORYYHYHU6IAG2EKV2MJYIXT7","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/P16-1162) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. InProceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 1715–1725. Association for Compu","arxiv_id":"2607.23319","detector":"doi_compliance","evidence":{"ref_index":1,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/","reconstructed_doi":"10.18653/v1/P16-1162"},"severity":"advisory","ref_index":1,"audited_at":"2026-07-31T23:52:34.640043Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/P16-1162","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"278f62193e2277a8d73481643e8c0ee5d2af79c82c8718818425eace986bcaa0","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14628,"payload_sha256":"28ed59934eb5cf141eb252ef53b549abc7dfb581ba5ca8cf8922798ab0ae4fa2","signature_b64":"kcfYBdsqvCyI2PND6airCPvugvZ+a5baUz44tlhtBTa85yLIx3bIgWBqGs4q8suHzcmS71TNh9dcwqLA9EUuBw==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T23:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xQIlRD+ebJzKV841mMM3rLdIC5zUxxoHO1vaXobItWGqmLfRKHOEYwdvCz51kxEsGeaA7ZrmOzbjyNoDmK4BBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:56:13.897947Z"},"content_sha256":"b98c2867641af0f83ff663217ca1eedbe94ca0aa2d319b7e6d2113c40cf78d15","schema_version":"1.0","event_id":"sha256:b98c2867641af0f83ff663217ca1eedbe94ca0aa2d319b7e6d2113c40cf78d15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZORYYHYHU6IAG2EKV2MJYIXT7/bundle.json","state_url":"https://pith.science/pith/BZORYYHYHU6IAG2EKV2MJYIXT7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZORYYHYHU6IAG2EKV2MJYIXT7/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":"2026-08-08T16:56:13Z","links":{"resolver":"https://pith.science/pith/BZORYYHYHU6IAG2EKV2MJYIXT7","bundle":"https://pith.science/pith/BZORYYHYHU6IAG2EKV2MJYIXT7/bundle.json","state":"https://pith.science/pith/BZORYYHYHU6IAG2EKV2MJYIXT7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZORYYHYHU6IAG2EKV2MJYIXT7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BZORYYHYHU6IAG2EKV2MJYIXT7","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bb6f2c19b89a7104791febdcb18d512c99b44a67f15bfd26bdce09c651b1476d","cross_cats_sorted":["cs.CY","cs.ET","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T18:23:06Z","title_canon_sha256":"51c401fc6775437ac04c675b473d80413abdea2fb1207e7dac1f43a27cc7823c"},"schema_version":"1.0","source":{"id":"2607.23319","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23319","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23319v1","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23319","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"BZORYYHYHU6I","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"BZORYYHYHU6IAG2E","created_at":"2026-07-28T01:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"BZORYYHY","created_at":"2026-07-28T01:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:4962c4a1cd8684f5e6bbacdb7652a9f8f30a54e1b6f953ccac8f55e27bfb049c","target":"graph","created_at":"2026-07-28T01:22:47Z","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/2607.23319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard subword tokenization algorithms such as Byte-Pair Encoding (BPE) and SentencePiece are trained predominantly on modern language corpora and produce inefficient segmentations when applied to classical Indian languages. Sanskrit, Tamil, and other classical Indic languages exhibit agglutinative morphology, productive sandhi (phonological fusion at word boundaries), and domain-specific vocabularies absent from general-purpose training data. This paper presents BHARATI, a set of SentencePiece BPE tokenizers trained on a balanced 781 MB corpus spanning seven languages (English, Hindi, Sansk","authors_text":"Lakshmi Rajendran, Pavithra Muruganantham, Poornima Kumaresan, Santhosh Sivasubramani","cross_cats":["cs.CY","cs.ET","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T18:23:06Z","title":"BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23319","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:dd39d05c1c22513a2759e315cbd9acf515941d62f6404d838802a6a7483fb7b6","target":"record","created_at":"2026-07-28T01:22:47Z","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":"bb6f2c19b89a7104791febdcb18d512c99b44a67f15bfd26bdce09c651b1476d","cross_cats_sorted":["cs.CY","cs.ET","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-25T18:23:06Z","title_canon_sha256":"51c401fc6775437ac04c675b473d80413abdea2fb1207e7dac1f43a27cc7823c"},"schema_version":"1.0","source":{"id":"2607.23319","kind":"arxiv","version":1}},"canonical_sha256":"0e5d1c60f83d3c801b445574c4e1179ff3a6b52804f355ff418abc3e8823f7dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e5d1c60f83d3c801b445574c4e1179ff3a6b52804f355ff418abc3e8823f7dc","first_computed_at":"2026-07-28T01:22:47.537198Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:47.537198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lqrr2JzCkXOIi3aMWOmAnpY59wXmGCiZT5M/bbFiCq2+XDTDZC9f3lDkjOeZyXsUbQVTMpC23QcqdldnLFIjBQ==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:47.537964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23319","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd39d05c1c22513a2759e315cbd9acf515941d62f6404d838802a6a7483fb7b6","sha256:4962c4a1cd8684f5e6bbacdb7652a9f8f30a54e1b6f953ccac8f55e27bfb049c","sha256:b98c2867641af0f83ff663217ca1eedbe94ca0aa2d319b7e6d2113c40cf78d15"],"state_sha256":"225ea77f4207635b88a5e10658d4dc2d910afb1d675f2452c09362bf3da0014b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kvldqzRB2cUnODleIjSTgyQsrVDFmyqCkWV0MaKDVx8qbJXSXaZpj7XzhqUlARw67/Qxj4KI/eMRtx7t+U4yBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:56:13.901520Z","bundle_sha256":"557a51464c31696fe0146d478318d4480e1c9633640d61dc72013511afd1fc02"}}