{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I2XVVMQN7PRT5FTC3M6TFTQHBA","short_pith_number":"pith:I2XVVMQN","canonical_record":{"source":{"id":"2503.23687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T03:38:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1518ea67c180aaaeea53487e2e9543383fb990a185dfba1799f481ca7e4a95f0","abstract_canon_sha256":"0bbd6f28f9f624f2823629f9aeffd15ddacd5084d307eee79b220827f7434348"},"schema_version":"1.0"},"canonical_sha256":"46af5ab20dfbe33e9662db3d32ce070812a8d26f56069c15a5eaeed620e07cf1","source":{"kind":"arxiv","id":"2503.23687","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23687","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23687v1","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23687","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"I2XVVMQN7PRT","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"I2XVVMQN7PRT5FTC","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"I2XVVMQN","created_at":"2026-07-05T10:41:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I2XVVMQN7PRT5FTC3M6TFTQHBA","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T03:38:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1518ea67c180aaaeea53487e2e9543383fb990a185dfba1799f481ca7e4a95f0","abstract_canon_sha256":"0bbd6f28f9f624f2823629f9aeffd15ddacd5084d307eee79b220827f7434348"},"schema_version":"1.0"},"canonical_sha256":"46af5ab20dfbe33e9662db3d32ce070812a8d26f56069c15a5eaeed620e07cf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:57.849461Z","signature_b64":"QGHb2N6FNCFgisHKh9yVz7FDEVIKQ/R53sB++32VQ2p0FH7HAvUhNxIXcXW3A6nREg0H1OeJOjGFscQyBUvlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46af5ab20dfbe33e9662db3d32ce070812a8d26f56069c15a5eaeed620e07cf1","last_reissued_at":"2026-07-05T10:41:57.849038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:57.849038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23687","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":"2026-07-05T10:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+EJe5Z730ZLzQsKh2bFYfn7lA8UEHwk+yVjrFJI0ZIxH2yRq2VTGXZOLchvwlDGbdz0FLza+MveLFmmj6rKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:53:04.530532Z"},"content_sha256":"e4a89e09193643fcc586acc2ee3364491dc1ea5e40bb479f25ed5344f5771cde","schema_version":"1.0","event_id":"sha256:e4a89e09193643fcc586acc2ee3364491dc1ea5e40bb479f25ed5344f5771cde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I2XVVMQN7PRT5FTC3M6TFTQHBA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MKA: Leveraging Cross-Lingual Consensus for Model Abstention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Sharad Duwal","submitted_at":"2025-03-31T03:38:12Z","abstract_excerpt":"Reliability of LLMs is questionable even as they get better at more tasks. A wider adoption of LLMs is contingent on whether they are usably factual. And if they are not, on whether they can properly calibrate their confidence in their responses. This work focuses on utilizing the multilingual knowledge of an LLM to inform its decision to abstain or answer when prompted. We develop a multilingual pipeline to calibrate the model's confidence and let it abstain when uncertain. We run several multilingual models through the pipeline to profile them across different languages. We find that the per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23687","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/2503.23687/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":"2026-07-05T10:41:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3SNkgFjq0Ua2dZ0bwR13NqRnHPo6Dj0z4HbOIDCWxZY6prrjQ4LTuRXrcLfWFNL3lGms+d9BHHT2Le3UfzfcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:53:04.531040Z"},"content_sha256":"f36e53cf2193b0cde8189a4d118b7cd7fe95b54d521c2703947bb41140467864","schema_version":"1.0","event_id":"sha256:f36e53cf2193b0cde8189a4d118b7cd7fe95b54d521c2703947bb41140467864"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA/bundle.json","state_url":"https://pith.science/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA/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":"2026-08-06T21:53:04Z","links":{"resolver":"https://pith.science/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA","bundle":"https://pith.science/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA/bundle.json","state":"https://pith.science/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2XVVMQN7PRT5FTC3M6TFTQHBA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I2XVVMQN7PRT5FTC3M6TFTQHBA","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":"0bbd6f28f9f624f2823629f9aeffd15ddacd5084d307eee79b220827f7434348","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T03:38:12Z","title_canon_sha256":"1518ea67c180aaaeea53487e2e9543383fb990a185dfba1799f481ca7e4a95f0"},"schema_version":"1.0","source":{"id":"2503.23687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23687","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23687v1","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23687","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"I2XVVMQN7PRT","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"I2XVVMQN7PRT5FTC","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"I2XVVMQN","created_at":"2026-07-05T10:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:f36e53cf2193b0cde8189a4d118b7cd7fe95b54d521c2703947bb41140467864","target":"graph","created_at":"2026-07-05T10:41:57Z","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/2503.23687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliability of LLMs is questionable even as they get better at more tasks. A wider adoption of LLMs is contingent on whether they are usably factual. And if they are not, on whether they can properly calibrate their confidence in their responses. This work focuses on utilizing the multilingual knowledge of an LLM to inform its decision to abstain or answer when prompted. We develop a multilingual pipeline to calibrate the model's confidence and let it abstain when uncertain. We run several multilingual models through the pipeline to profile them across different languages. We find that the per","authors_text":"Sharad Duwal","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T03:38:12Z","title":"MKA: Leveraging Cross-Lingual Consensus for Model Abstention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23687","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:e4a89e09193643fcc586acc2ee3364491dc1ea5e40bb479f25ed5344f5771cde","target":"record","created_at":"2026-07-05T10:41:57Z","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":"0bbd6f28f9f624f2823629f9aeffd15ddacd5084d307eee79b220827f7434348","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T03:38:12Z","title_canon_sha256":"1518ea67c180aaaeea53487e2e9543383fb990a185dfba1799f481ca7e4a95f0"},"schema_version":"1.0","source":{"id":"2503.23687","kind":"arxiv","version":1}},"canonical_sha256":"46af5ab20dfbe33e9662db3d32ce070812a8d26f56069c15a5eaeed620e07cf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46af5ab20dfbe33e9662db3d32ce070812a8d26f56069c15a5eaeed620e07cf1","first_computed_at":"2026-07-05T10:41:57.849038Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:57.849038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QGHb2N6FNCFgisHKh9yVz7FDEVIKQ/R53sB++32VQ2p0FH7HAvUhNxIXcXW3A6nREg0H1OeJOjGFscQyBUvlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:57.849461Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4a89e09193643fcc586acc2ee3364491dc1ea5e40bb479f25ed5344f5771cde","sha256:f36e53cf2193b0cde8189a4d118b7cd7fe95b54d521c2703947bb41140467864"],"state_sha256":"d2aad83c832e1b323b151cd1bf7b6a5f536348f358a3322a95cc55c7fe175d2d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8/36eFghJOgIbd+92ReIfqzkzj/qDVqSescnDmW/M0zVzuOvl0UwC3azPcuaa7DFvMt6XdsJffIFiiqRasaCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:53:04.535327Z","bundle_sha256":"ea41806690d88deba5de4c0b4130d0af411b58c472692df3ce94c0c3cc229c7d"}}