{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LIKAOSALNJY3UFQKX55X36AQIU","short_pith_number":"pith:LIKAOSAL","canonical_record":{"source":{"id":"2412.12997","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:21:28Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"91bfc0a2fc527b9d14def92abd976dddc362d3a52c2c855cd9c1b5a89bb9de5a","abstract_canon_sha256":"6db3f8adb5f8b3bed8cb27e2f5aa93f9801b66e8cd49557863046f04a42df76f"},"schema_version":"1.0"},"canonical_sha256":"5a1407480b6a71ba160abf7b7df810450aa4d44f0eaac5129e3d0952121ce023","source":{"kind":"arxiv","id":"2412.12997","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12997","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12997v3","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12997","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"LIKAOSALNJY3","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"LIKAOSALNJY3UFQK","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"LIKAOSAL","created_at":"2026-07-05T10:44:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LIKAOSALNJY3UFQKX55X36AQIU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12997","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:21:28Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"91bfc0a2fc527b9d14def92abd976dddc362d3a52c2c855cd9c1b5a89bb9de5a","abstract_canon_sha256":"6db3f8adb5f8b3bed8cb27e2f5aa93f9801b66e8cd49557863046f04a42df76f"},"schema_version":"1.0"},"canonical_sha256":"5a1407480b6a71ba160abf7b7df810450aa4d44f0eaac5129e3d0952121ce023","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:20.889325Z","signature_b64":"H/tVaKtiPJmnLTmdrUMSwjfxWnR7Jjh8VXKInRnebpTIWSL10gjwkY8Z5VGFweir5eH6XZFSG1V3aFFkDZyHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a1407480b6a71ba160abf7b7df810450aa4d44f0eaac5129e3d0952121ce023","last_reissued_at":"2026-07-05T10:44:20.888835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:20.888835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12997","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BWCzr7vyTJ2WOslSUNuv1Ze7XGXAAHdwvKvVG9jeZI2npQOP1Tmm9vqA1nv98m/fwkHpLKbed/3cjglmeHeZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:59:32.991689Z"},"content_sha256":"ccc617304a9fa2907d105ffba80cf57b14030f38559fefdd6b7cb7728bd9243b","schema_version":"1.0","event_id":"sha256:ccc617304a9fa2907d105ffba80cf57b14030f38559fefdd6b7cb7728bd9243b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LIKAOSALNJY3UFQKX55X36AQIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"G\\\"unter Neumann, Stalin Varanasi, Umer Butt","submitted_at":"2024-12-17T15:21:28Z","abstract_excerpt":"As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity, addressing the needs of low-resource languages remains a significant challenge. This paper introduces the first large-scale Urdu IR dataset, created by translating the MS MARCO dataset through machine translation. We establish baseline results through zero-shot learning for IR in Urdu and subsequently apply the mMARCO multilingual IR methodology to this newly translated dataset. Our findings demonstrate that the fine-tuned model (Urdu-mT5-mMARCO) achieves a Mean Reciprocal Rank (MRR@10) of 0.247 and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12997","kind":"arxiv","version":3},"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/2412.12997/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":"2026-07-05T10:44:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WextOa0V6AeDLMuD1XFETo/goCKRYDwX4x54gUHw2A92RwK/Cw1Q5SN0KyCqkfQu25fb0UNVfMoc7Ht2uJ2aDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T15:59:32.992307Z"},"content_sha256":"1e2bd41906d6489647a81b3f25281b4c0752c789655fa7c6793eb10384f80068","schema_version":"1.0","event_id":"sha256:1e2bd41906d6489647a81b3f25281b4c0752c789655fa7c6793eb10384f80068"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIKAOSALNJY3UFQKX55X36AQIU/bundle.json","state_url":"https://pith.science/pith/LIKAOSALNJY3UFQKX55X36AQIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIKAOSALNJY3UFQKX55X36AQIU/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":"2026-08-15T15:59:32Z","links":{"resolver":"https://pith.science/pith/LIKAOSALNJY3UFQKX55X36AQIU","bundle":"https://pith.science/pith/LIKAOSALNJY3UFQKX55X36AQIU/bundle.json","state":"https://pith.science/pith/LIKAOSALNJY3UFQKX55X36AQIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIKAOSALNJY3UFQKX55X36AQIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LIKAOSALNJY3UFQKX55X36AQIU","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":"6db3f8adb5f8b3bed8cb27e2f5aa93f9801b66e8cd49557863046f04a42df76f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:21:28Z","title_canon_sha256":"91bfc0a2fc527b9d14def92abd976dddc362d3a52c2c855cd9c1b5a89bb9de5a"},"schema_version":"1.0","source":{"id":"2412.12997","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12997","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12997v3","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12997","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"LIKAOSALNJY3","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"LIKAOSALNJY3UFQK","created_at":"2026-07-05T10:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"LIKAOSAL","created_at":"2026-07-05T10:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:1e2bd41906d6489647a81b3f25281b4c0752c789655fa7c6793eb10384f80068","target":"graph","created_at":"2026-07-05T10:44:20Z","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/2412.12997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the Information Retrieval (IR) field increasingly recognizes the importance of inclusivity, addressing the needs of low-resource languages remains a significant challenge. This paper introduces the first large-scale Urdu IR dataset, created by translating the MS MARCO dataset through machine translation. We establish baseline results through zero-shot learning for IR in Urdu and subsequently apply the mMARCO multilingual IR methodology to this newly translated dataset. Our findings demonstrate that the fine-tuned model (Urdu-mT5-mMARCO) achieves a Mean Reciprocal Rank (MRR@10) of 0.247 and ","authors_text":"G\\\"unter Neumann, Stalin Varanasi, Umer Butt","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:21:28Z","title":"Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12997","kind":"arxiv","version":3},"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:ccc617304a9fa2907d105ffba80cf57b14030f38559fefdd6b7cb7728bd9243b","target":"record","created_at":"2026-07-05T10:44:20Z","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":"6db3f8adb5f8b3bed8cb27e2f5aa93f9801b66e8cd49557863046f04a42df76f","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-17T15:21:28Z","title_canon_sha256":"91bfc0a2fc527b9d14def92abd976dddc362d3a52c2c855cd9c1b5a89bb9de5a"},"schema_version":"1.0","source":{"id":"2412.12997","kind":"arxiv","version":3}},"canonical_sha256":"5a1407480b6a71ba160abf7b7df810450aa4d44f0eaac5129e3d0952121ce023","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a1407480b6a71ba160abf7b7df810450aa4d44f0eaac5129e3d0952121ce023","first_computed_at":"2026-07-05T10:44:20.888835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:20.888835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H/tVaKtiPJmnLTmdrUMSwjfxWnR7Jjh8VXKInRnebpTIWSL10gjwkY8Z5VGFweir5eH6XZFSG1V3aFFkDZyHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:20.889325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12997","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc617304a9fa2907d105ffba80cf57b14030f38559fefdd6b7cb7728bd9243b","sha256:1e2bd41906d6489647a81b3f25281b4c0752c789655fa7c6793eb10384f80068"],"state_sha256":"c24697df3d724c541c6681fa94540440b4229ab2128a16b5837208978e4ccd71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cy0Fz8fBVSCI+4qQ1FgbeWME2cuWBzraLwke1KAZMg9LYncf4zpJdXNvbiNd0RT8HQNM8kr5yek3eme0prBrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T15:59:32.996872Z","bundle_sha256":"60b4ff1cde3a80ea54c300d92ed5c32620798db8ab6497538ff634424fd42981"}}