{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IX2K6MDJWBAL333S5UPOJE4TN5","short_pith_number":"pith:IX2K6MDJ","canonical_record":{"source":{"id":"2401.16405","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T18:43:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ac6b6fb08c9559a9a9a1583a3753e703a4198f19a1eca48052f07e97e8e99211","abstract_canon_sha256":"d40b0b4259a2e331f9a36f1a5e6b0cff04c938227611b3183c47063c634eff26"},"schema_version":"1.0"},"canonical_sha256":"45f4af3069b040bdef72ed1ee493936f67348ab57b28dc42455bbc5f78c4442a","source":{"kind":"arxiv","id":"2401.16405","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16405","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16405v2","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16405","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_12","alias_value":"IX2K6MDJWBAL","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_16","alias_value":"IX2K6MDJWBAL333S","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_8","alias_value":"IX2K6MDJ","created_at":"2026-07-05T07:40:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IX2K6MDJWBAL333S5UPOJE4TN5","target":"record","payload":{"canonical_record":{"source":{"id":"2401.16405","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T18:43:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ac6b6fb08c9559a9a9a1583a3753e703a4198f19a1eca48052f07e97e8e99211","abstract_canon_sha256":"d40b0b4259a2e331f9a36f1a5e6b0cff04c938227611b3183c47063c634eff26"},"schema_version":"1.0"},"canonical_sha256":"45f4af3069b040bdef72ed1ee493936f67348ab57b28dc42455bbc5f78c4442a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:43.711267Z","signature_b64":"f17Y1qwy7jC/sT4gHLSYtH2TEGNu2uU4n2nilyg1hZKEtRRPsKeeDTcicVp99jexx9LC6/leATfQTKzidFGUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f4af3069b040bdef72ed1ee493936f67348ab57b28dc42455bbc5f78c4442a","last_reissued_at":"2026-07-05T07:40:43.710690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:43.710690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.16405","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":"2026-07-05T07:40:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQ+wU28F7kuwLeLJ+VX5VKgpxVWRq/ctMWlvH1vVgkp6g68Ya5zpocCQkMeb26InQZFJ7TOlXreSalJGamSHBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:50.702340Z"},"content_sha256":"a0d631b987a52ba0a314f60e6c9254f3643a64ed1cf28e61f9878169bcfb22f4","schema_version":"1.0","event_id":"sha256:a0d631b987a52ba0a314f60e6c9254f3643a64ed1cf28e61f9878169bcfb22f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IX2K6MDJWBAL333S5UPOJE4TN5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Sparse Fine-Tuning to Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Alan Ansell, Anna Korhonen, Edoardo M. Ponti, Hannah Sterz, Ivan Vuli\\'c","submitted_at":"2024-01-29T18:43:49Z","abstract_excerpt":"Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of performance but their memory requirements increase proportionally to the size of the LLMs. In this work, we scale sparse fine-tuning to state-of-the-art LLMs like LLaMA 2 7B and 13B. We propose SpIEL, a novel sparse fine-tuning method which, for a desired density level, maintains an array of parameter indices and the deltas of these parameters relative to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16405","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/2401.16405/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":"2026-07-05T07:40:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9yWcUKCTvkOINSne7OTtwb7RYUzsOcTLqq+hvKdr1ZwiIk8P3nbiHS4q6sskxtIr4KcL/3cqJdxH2tRQ8FxKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:32:50.702896Z"},"content_sha256":"cef3ca0adf23e593a0f2d3cbf8b6d9161b681cf7b0177839ed1ee867983ea3e6","schema_version":"1.0","event_id":"sha256:cef3ca0adf23e593a0f2d3cbf8b6d9161b681cf7b0177839ed1ee867983ea3e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IX2K6MDJWBAL333S5UPOJE4TN5/bundle.json","state_url":"https://pith.science/pith/IX2K6MDJWBAL333S5UPOJE4TN5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IX2K6MDJWBAL333S5UPOJE4TN5/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":"2026-08-05T10:32:50Z","links":{"resolver":"https://pith.science/pith/IX2K6MDJWBAL333S5UPOJE4TN5","bundle":"https://pith.science/pith/IX2K6MDJWBAL333S5UPOJE4TN5/bundle.json","state":"https://pith.science/pith/IX2K6MDJWBAL333S5UPOJE4TN5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IX2K6MDJWBAL333S5UPOJE4TN5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IX2K6MDJWBAL333S5UPOJE4TN5","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":"d40b0b4259a2e331f9a36f1a5e6b0cff04c938227611b3183c47063c634eff26","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T18:43:49Z","title_canon_sha256":"ac6b6fb08c9559a9a9a1583a3753e703a4198f19a1eca48052f07e97e8e99211"},"schema_version":"1.0","source":{"id":"2401.16405","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16405","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16405v2","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16405","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_12","alias_value":"IX2K6MDJWBAL","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_16","alias_value":"IX2K6MDJWBAL333S","created_at":"2026-07-05T07:40:43Z"},{"alias_kind":"pith_short_8","alias_value":"IX2K6MDJ","created_at":"2026-07-05T07:40:43Z"}],"graph_snapshots":[{"event_id":"sha256:cef3ca0adf23e593a0f2d3cbf8b6d9161b681cf7b0177839ed1ee867983ea3e6","target":"graph","created_at":"2026-07-05T07:40:43Z","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/2401.16405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of performance but their memory requirements increase proportionally to the size of the LLMs. In this work, we scale sparse fine-tuning to state-of-the-art LLMs like LLaMA 2 7B and 13B. We propose SpIEL, a novel sparse fine-tuning method which, for a desired density level, maintains an array of parameter indices and the deltas of these parameters relative to th","authors_text":"Alan Ansell, Anna Korhonen, Edoardo M. Ponti, Hannah Sterz, Ivan Vuli\\'c","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T18:43:49Z","title":"Scaling Sparse Fine-Tuning to Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16405","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:a0d631b987a52ba0a314f60e6c9254f3643a64ed1cf28e61f9878169bcfb22f4","target":"record","created_at":"2026-07-05T07:40:43Z","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":"d40b0b4259a2e331f9a36f1a5e6b0cff04c938227611b3183c47063c634eff26","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-29T18:43:49Z","title_canon_sha256":"ac6b6fb08c9559a9a9a1583a3753e703a4198f19a1eca48052f07e97e8e99211"},"schema_version":"1.0","source":{"id":"2401.16405","kind":"arxiv","version":2}},"canonical_sha256":"45f4af3069b040bdef72ed1ee493936f67348ab57b28dc42455bbc5f78c4442a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f4af3069b040bdef72ed1ee493936f67348ab57b28dc42455bbc5f78c4442a","first_computed_at":"2026-07-05T07:40:43.710690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:43.710690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f17Y1qwy7jC/sT4gHLSYtH2TEGNu2uU4n2nilyg1hZKEtRRPsKeeDTcicVp99jexx9LC6/leATfQTKzidFGUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:43.711267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16405","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0d631b987a52ba0a314f60e6c9254f3643a64ed1cf28e61f9878169bcfb22f4","sha256:cef3ca0adf23e593a0f2d3cbf8b6d9161b681cf7b0177839ed1ee867983ea3e6"],"state_sha256":"72ffb91ecb6888a4f47115c9b0d8b303ab3c4a185653169fe966b3424bfdb4e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6rvFuuLU3fy2u3zLGRLXvyOS/1WQarjjJd1Qsi6JoRSiICoROqNLa3dqthjgO8ZWu4Ce3grKzFXd+FkLaqGBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:32:50.708917Z","bundle_sha256":"4a28ac04a0d2121e0861748a6885f850ec8ce49a2887992ea5c6527e69215cf5"}}