{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ARYQOVAEFD5GAUSAEPY4W6G7SD","short_pith_number":"pith:ARYQOVAE","canonical_record":{"source":{"id":"2312.02820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T15:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48980cc9a594e1468dd4c268da39ae7795a69f5641dff0cd4491732ae81bac51","abstract_canon_sha256":"7014f82583a92051ca38be41fb3a23ece9b9d994f732dd11e3d67270115423d0"},"schema_version":"1.0"},"canonical_sha256":"047107540428fa60524023f1cb78df90f19d47c4bde43907c2a0d4d5ee67f32a","source":{"kind":"arxiv","id":"2312.02820","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02820","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02820v1","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02820","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"ARYQOVAEFD5G","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"ARYQOVAEFD5GAUSA","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"ARYQOVAE","created_at":"2026-07-05T07:20:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ARYQOVAEFD5GAUSAEPY4W6G7SD","target":"record","payload":{"canonical_record":{"source":{"id":"2312.02820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T15:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"48980cc9a594e1468dd4c268da39ae7795a69f5641dff0cd4491732ae81bac51","abstract_canon_sha256":"7014f82583a92051ca38be41fb3a23ece9b9d994f732dd11e3d67270115423d0"},"schema_version":"1.0"},"canonical_sha256":"047107540428fa60524023f1cb78df90f19d47c4bde43907c2a0d4d5ee67f32a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:43.387785Z","signature_b64":"/nmGw3lAOsPhPKUwBcK7JHbofkWzw/ikDNeFCRkBApi0SeXQJCMa7OwlzgVc7FWSSK3OKse+cLkbr/3ElqloAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"047107540428fa60524023f1cb78df90f19d47c4bde43907c2a0d4d5ee67f32a","last_reissued_at":"2026-07-05T07:20:43.387340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:43.387340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.02820","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":"2026-07-05T07:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B9WJxltCVJR1Td55EC0fKnNrcsSW/738CBABur/dwlmQXg8Q9OExxP7ufqVRxv6flg7H/PbC9ivs8k6RTz8fCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:22:42.686751Z"},"content_sha256":"a895da596784212e57e14fd7288e858253129babb4c3ab570d0e1b9bc8324ce3","schema_version":"1.0","event_id":"sha256:a895da596784212e57e14fd7288e858253129babb4c3ab570d0e1b9bc8324ce3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ARYQOVAEFD5GAUSAEPY4W6G7SD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Min Zhang, Xinyu Ma, Xuebo Liu","submitted_at":"2023-12-05T15:03:27Z","abstract_excerpt":"In multilingual translation research, the comprehension and utilization of language families are of paramount importance. Nevertheless, clustering languages based solely on their ancestral families can yield suboptimal results due to variations in the datasets employed during the model's training phase. To mitigate this challenge, we introduce an innovative method that leverages the fisher information matrix (FIM) to cluster language families, anchored on the multilingual translation model's characteristics. We hypothesize that language pairs with similar effects on model parameters exhibit a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02820","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/2312.02820/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":"2026-07-05T07:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RzuN/CldMyylqaNSmsmVXPdq6jvaXq4E4JGoxsdDh+rwAyD0U9/7gC88X8jSyA3Jld0qHBoXB8DFJZXXeb6IBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T20:22:42.687293Z"},"content_sha256":"ed74276b74dabb8123c4378671f541b4bf3a94bf029c610fcbc5f5a760665198","schema_version":"1.0","event_id":"sha256:ed74276b74dabb8123c4378671f541b4bf3a94bf029c610fcbc5f5a760665198"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD/bundle.json","state_url":"https://pith.science/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD/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":"2026-08-06T20:22:42Z","links":{"resolver":"https://pith.science/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD","bundle":"https://pith.science/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD/bundle.json","state":"https://pith.science/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ARYQOVAEFD5GAUSAEPY4W6G7SD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ARYQOVAEFD5GAUSAEPY4W6G7SD","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":"7014f82583a92051ca38be41fb3a23ece9b9d994f732dd11e3d67270115423d0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T15:03:27Z","title_canon_sha256":"48980cc9a594e1468dd4c268da39ae7795a69f5641dff0cd4491732ae81bac51"},"schema_version":"1.0","source":{"id":"2312.02820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02820","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02820v1","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02820","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"ARYQOVAEFD5G","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"ARYQOVAEFD5GAUSA","created_at":"2026-07-05T07:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"ARYQOVAE","created_at":"2026-07-05T07:20:43Z"}],"graph_snapshots":[{"event_id":"sha256:ed74276b74dabb8123c4378671f541b4bf3a94bf029c610fcbc5f5a760665198","target":"graph","created_at":"2026-07-05T07:20:43Z","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/2312.02820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In multilingual translation research, the comprehension and utilization of language families are of paramount importance. Nevertheless, clustering languages based solely on their ancestral families can yield suboptimal results due to variations in the datasets employed during the model's training phase. To mitigate this challenge, we introduce an innovative method that leverages the fisher information matrix (FIM) to cluster language families, anchored on the multilingual translation model's characteristics. We hypothesize that language pairs with similar effects on model parameters exhibit a ","authors_text":"Min Zhang, Xinyu Ma, Xuebo Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T15:03:27Z","title":"Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02820","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:a895da596784212e57e14fd7288e858253129babb4c3ab570d0e1b9bc8324ce3","target":"record","created_at":"2026-07-05T07:20:43Z","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":"7014f82583a92051ca38be41fb3a23ece9b9d994f732dd11e3d67270115423d0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-05T15:03:27Z","title_canon_sha256":"48980cc9a594e1468dd4c268da39ae7795a69f5641dff0cd4491732ae81bac51"},"schema_version":"1.0","source":{"id":"2312.02820","kind":"arxiv","version":1}},"canonical_sha256":"047107540428fa60524023f1cb78df90f19d47c4bde43907c2a0d4d5ee67f32a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"047107540428fa60524023f1cb78df90f19d47c4bde43907c2a0d4d5ee67f32a","first_computed_at":"2026-07-05T07:20:43.387340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:43.387340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/nmGw3lAOsPhPKUwBcK7JHbofkWzw/ikDNeFCRkBApi0SeXQJCMa7OwlzgVc7FWSSK3OKse+cLkbr/3ElqloAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:43.387785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a895da596784212e57e14fd7288e858253129babb4c3ab570d0e1b9bc8324ce3","sha256:ed74276b74dabb8123c4378671f541b4bf3a94bf029c610fcbc5f5a760665198"],"state_sha256":"ae5ec7a2db18514d9a52775e94878d66f300fc46a1b5608757652f5c17f9fb72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f0LUPpwKHRd2b4zReCyVXUSSOGAmpg9rwAzukLLBiZPRhhygATngRt8v/hT9sUEqYjR47fyM095uLBHxvqIVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T20:22:42.693232Z","bundle_sha256":"ecedd5fd9fa0cab96f388867b7eaf78e6170d40cc03420f5bb7590435b4610ab"}}