{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MNQLPIQF7GTNYFDR4ZVFTV6FH4","short_pith_number":"pith:MNQLPIQF","schema_version":"1.0","canonical_sha256":"6360b7a205f9a6dc1471e66a59d7c53f094b9fa78b3025858469ac6385d50d49","source":{"kind":"arxiv","id":"2608.03105","version":1},"attestation_state":"computed","paper":{"title":"HomoEnsNER: Does Language Alignment Outperform Architectural Complexity in Gujarati Named Entity Recognition?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandrakant K. Bhogayata","submitted_at":"2026-08-04T04:21:35Z","abstract_excerpt":"Named Entity Recognition (NER) for Gujarati remains underexplored, hindered by the absence of capitalization cues, rich morphology, lexical ambiguity, and free word order. Prior ensemble work has emphasized architectural diversity by combining heterogeneous classifiers, multilingual encoders, or classical sequence models, rather than exploiting language-aligned monolingual pretraining. This study asks whether, for a low-resource, morphologically rich language like Gujarati, a homogeneous ensemble of a single monolingual encoder outperforms such architectural diversity. We propose HomoEnsNER, a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03105","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T04:21:35Z","cross_cats_sorted":[],"title_canon_sha256":"ab14d0367a90a69e916a54d191ff409e693a297cb46a46c15a34f4b884cc76c0","abstract_canon_sha256":"c4af5ada9a0d1aa6b441dfc35f1e1ffda889d7088b87ce6571fea7dce4d1f7d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:45:41.470478Z","signature_b64":"GHD0CkPEw3lH2kxWgwAezM/uwmmGv8F8e2g4O0ouFB05eWjW8rYA1kZyYQrt1//skejTBHaQPNlQ/9No+6f3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6360b7a205f9a6dc1471e66a59d7c53f094b9fa78b3025858469ac6385d50d49","last_reissued_at":"2026-08-05T00:45:41.467743Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:45:41.467743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HomoEnsNER: Does Language Alignment Outperform Architectural Complexity in Gujarati Named Entity Recognition?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chandrakant K. Bhogayata","submitted_at":"2026-08-04T04:21:35Z","abstract_excerpt":"Named Entity Recognition (NER) for Gujarati remains underexplored, hindered by the absence of capitalization cues, rich morphology, lexical ambiguity, and free word order. Prior ensemble work has emphasized architectural diversity by combining heterogeneous classifiers, multilingual encoders, or classical sequence models, rather than exploiting language-aligned monolingual pretraining. This study asks whether, for a low-resource, morphologically rich language like Gujarati, a homogeneous ensemble of a single monolingual encoder outperforms such architectural diversity. We propose HomoEnsNER, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03105","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/2608.03105/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03105","created_at":"2026-08-05T00:45:41.468792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03105v1","created_at":"2026-08-05T00:45:41.468792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03105","created_at":"2026-08-05T00:45:41.468792+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNQLPIQF7GTN","created_at":"2026-08-05T00:45:41.468792+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNQLPIQF7GTNYFDR","created_at":"2026-08-05T00:45:41.468792+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNQLPIQF","created_at":"2026-08-05T00:45:41.468792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4","json":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4.json","graph_json":"https://pith.science/api/pith-number/MNQLPIQF7GTNYFDR4ZVFTV6FH4/graph.json","events_json":"https://pith.science/api/pith-number/MNQLPIQF7GTNYFDR4ZVFTV6FH4/events.json","paper":"https://pith.science/paper/MNQLPIQF"},"agent_actions":{"view_html":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4","download_json":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4.json","view_paper":"https://pith.science/paper/MNQLPIQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03105&json=true","fetch_graph":"https://pith.science/api/pith-number/MNQLPIQF7GTNYFDR4ZVFTV6FH4/graph.json","fetch_events":"https://pith.science/api/pith-number/MNQLPIQF7GTNYFDR4ZVFTV6FH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4/action/storage_attestation","attest_author":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4/action/author_attestation","sign_citation":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4/action/citation_signature","submit_replication":"https://pith.science/pith/MNQLPIQF7GTNYFDR4ZVFTV6FH4/action/replication_record"}},"created_at":"2026-08-05T00:45:41.468792+00:00","updated_at":"2026-08-05T00:45:41.468792+00:00"}