{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RJ7M6Q6YO2AAN3TKRWPOLB3OOU","short_pith_number":"pith:RJ7M6Q6Y","canonical_record":{"source":{"id":"2110.07560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T17:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"965d057312a420dbf65047b9a93fcf21d97fc39816911d7951232363967c9ebf","abstract_canon_sha256":"fe7e3fbe950385c0fe158e35db209a41e88662d209aa587649ed6d45de9bb7fc"},"schema_version":"1.0"},"canonical_sha256":"8a7ecf43d8768006ee6a8d9ee5876e753dd41795ae0edd0ceb10fd2ae8a22b51","source":{"kind":"arxiv","id":"2110.07560","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07560","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07560v2","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07560","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_12","alias_value":"RJ7M6Q6YO2AA","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_16","alias_value":"RJ7M6Q6YO2AAN3TK","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_8","alias_value":"RJ7M6Q6Y","created_at":"2026-07-05T05:40:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RJ7M6Q6YO2AAN3TKRWPOLB3OOU","target":"record","payload":{"canonical_record":{"source":{"id":"2110.07560","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T17:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"965d057312a420dbf65047b9a93fcf21d97fc39816911d7951232363967c9ebf","abstract_canon_sha256":"fe7e3fbe950385c0fe158e35db209a41e88662d209aa587649ed6d45de9bb7fc"},"schema_version":"1.0"},"canonical_sha256":"8a7ecf43d8768006ee6a8d9ee5876e753dd41795ae0edd0ceb10fd2ae8a22b51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:04.429156Z","signature_b64":"SDe96RFOzNLSTiOvOTUo2MemHdtLTJpsT2gORKciylbr15PTDb0ucLriq8X3Gk5tBBHRu5ZGbGOZp1koVDwfAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a7ecf43d8768006ee6a8d9ee5876e753dd41795ae0edd0ceb10fd2ae8a22b51","last_reissued_at":"2026-07-05T05:40:04.428693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:04.428693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.07560","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:40:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Pb4O1nangWdlMOBCgaybMiToR80BijaaFr12e6DxFWmg21DW/XI6uFMDygY7YhxkJGlgvc0NfhEK+uF4gAACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:34:42.635270Z"},"content_sha256":"0a96ae2c8d05fdcb24f78e80a03ed6076ea92102fee2c4ee6caf006b47f99749","schema_version":"1.0","event_id":"sha256:0a96ae2c8d05fdcb24f78e80a03ed6076ea92102fee2c4ee6caf006b47f99749"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RJ7M6Q6YO2AAN3TKRWPOLB3OOU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan Ansell, Anna Korhonen, Edoardo Maria Ponti, Ivan Vuli\\'c","submitted_at":"2021-10-14T17:27:29Z","abstract_excerpt":"Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07560","kind":"arxiv","version":2},"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/2110.07560/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":"2026-07-05T05:40:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9i5S08qvx4lObX+DrkOEfoSRs+DfIS2S02fpOXFBHOc7RWNk16heu2/13Urb+FlbG4ekgMpNng3MzWerefpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:34:42.635817Z"},"content_sha256":"5e68a0437ab38a2e2a62f8ea216e08e4fabc7eee3aa1948849329f4826f30845","schema_version":"1.0","event_id":"sha256:5e68a0437ab38a2e2a62f8ea216e08e4fabc7eee3aa1948849329f4826f30845"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU/bundle.json","state_url":"https://pith.science/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU/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":"2026-08-11T20:34:42Z","links":{"resolver":"https://pith.science/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU","bundle":"https://pith.science/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU/bundle.json","state":"https://pith.science/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJ7M6Q6YO2AAN3TKRWPOLB3OOU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RJ7M6Q6YO2AAN3TKRWPOLB3OOU","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":"fe7e3fbe950385c0fe158e35db209a41e88662d209aa587649ed6d45de9bb7fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T17:27:29Z","title_canon_sha256":"965d057312a420dbf65047b9a93fcf21d97fc39816911d7951232363967c9ebf"},"schema_version":"1.0","source":{"id":"2110.07560","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07560","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07560v2","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07560","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_12","alias_value":"RJ7M6Q6YO2AA","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_16","alias_value":"RJ7M6Q6YO2AAN3TK","created_at":"2026-07-05T05:40:04Z"},{"alias_kind":"pith_short_8","alias_value":"RJ7M6Q6Y","created_at":"2026-07-05T05:40:04Z"}],"graph_snapshots":[{"event_id":"sha256:5e68a0437ab38a2e2a62f8ea216e08e4fabc7eee3aa1948849329f4826f30845","target":"graph","created_at":"2026-07-05T05:40:04Z","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/2110.07560/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properti","authors_text":"Alan Ansell, Anna Korhonen, Edoardo Maria Ponti, Ivan Vuli\\'c","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T17:27:29Z","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07560","kind":"arxiv","version":2},"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":"sha256:0a96ae2c8d05fdcb24f78e80a03ed6076ea92102fee2c4ee6caf006b47f99749","target":"record","created_at":"2026-07-05T05:40:04Z","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":"fe7e3fbe950385c0fe158e35db209a41e88662d209aa587649ed6d45de9bb7fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-14T17:27:29Z","title_canon_sha256":"965d057312a420dbf65047b9a93fcf21d97fc39816911d7951232363967c9ebf"},"schema_version":"1.0","source":{"id":"2110.07560","kind":"arxiv","version":2}},"canonical_sha256":"8a7ecf43d8768006ee6a8d9ee5876e753dd41795ae0edd0ceb10fd2ae8a22b51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a7ecf43d8768006ee6a8d9ee5876e753dd41795ae0edd0ceb10fd2ae8a22b51","first_computed_at":"2026-07-05T05:40:04.428693Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:04.428693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SDe96RFOzNLSTiOvOTUo2MemHdtLTJpsT2gORKciylbr15PTDb0ucLriq8X3Gk5tBBHRu5ZGbGOZp1koVDwfAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:04.429156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07560","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a96ae2c8d05fdcb24f78e80a03ed6076ea92102fee2c4ee6caf006b47f99749","sha256:5e68a0437ab38a2e2a62f8ea216e08e4fabc7eee3aa1948849329f4826f30845"],"state_sha256":"c4766782ec741aad7a0caa461ceb2888bb76573b895b8059d623e2c52b949a09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2eSP2Iq7Ojj+3uUPz7EkJLaI55Jv8JbQF8RBw+rCodMpWI6OXtg2fjpq4klJYSTakOZenvNL9QEIa2lmg8EYCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:34:42.641681Z","bundle_sha256":"352dbce60f3f48f31f3969730a1f33469c54816c5628ddaeee13f2141b36d2b3"}}