{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UHA5VG465HSN426QRRETXFWV4V","short_pith_number":"pith:UHA5VG46","canonical_record":{"source":{"id":"2607.09287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T10:55:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2f04817b9fc4716b44129a080b0ece85a88a6ee687d5181e5810d2ba107d4a9","abstract_canon_sha256":"23dbff30b9635f550c1fbb9d13e0c29537960fb2e62853d3b03587c5748df153"},"schema_version":"1.0"},"canonical_sha256":"a1c1da9b9ee9e4de6bd08c493b96d5e55b82eb9c7f480d4382c8944e0ca31e34","source":{"kind":"arxiv","id":"2607.09287","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09287","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09287v1","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09287","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"UHA5VG465HSN","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"UHA5VG465HSN426Q","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"UHA5VG46","created_at":"2026-07-13T01:18:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UHA5VG465HSN426QRRETXFWV4V","target":"record","payload":{"canonical_record":{"source":{"id":"2607.09287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T10:55:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a2f04817b9fc4716b44129a080b0ece85a88a6ee687d5181e5810d2ba107d4a9","abstract_canon_sha256":"23dbff30b9635f550c1fbb9d13e0c29537960fb2e62853d3b03587c5748df153"},"schema_version":"1.0"},"canonical_sha256":"a1c1da9b9ee9e4de6bd08c493b96d5e55b82eb9c7f480d4382c8944e0ca31e34","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:18:58.913279Z","signature_b64":"PgoSWOofiYY+vCBk5WHAPu2tZ3p3SB1SDTeQitYVb+w52eRhSSQfOaDzdNrTT2sYKt5SzMF/qZJa7KjX6vaKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1c1da9b9ee9e4de6bd08c493b96d5e55b82eb9c7f480d4382c8944e0ca31e34","last_reissued_at":"2026-07-13T01:18:58.912262Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:18:58.912262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.09287","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":"2026-07-13T01:18:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dRx0DF6MAHTkknvz2ASjgZ/LgthbC8URji/vA8OX323wVutLxOKmoCHpCb1gnW0gb7nn3KLTkHIeO4IDz4usAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:28:45.716361Z"},"content_sha256":"e9cb306485341aa76ff2ed565e5e6e02cd70c22f5f2c604f7f174872d8b78f54","schema_version":"1.0","event_id":"sha256:e9cb306485341aa76ff2ed565e5e6e02cd70c22f5f2c604f7f174872d8b78f54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UHA5VG465HSN426QRRETXFWV4V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ivan Ilin, Peter Richt\\'arik, Philip Zmushko","submitted_at":"2026-07-10T10:55:28Z","abstract_excerpt":"Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage. We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt. We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support using a Wanda-style activation-weighted magnitude score [Sun et al., 2023] computed from a calibration pass. We then introduce Supra, a hybrid adapter that combines this sparse update with LoRA while preserving a matched t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09287","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/2607.09287/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":"2026-07-13T01:18:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gGbiGnUjKMwKrk+/InIabIvCnukb3h6dfF7U4eyMwZoMsQ3hD6szzkIBUj9DyyCaWk4Jfp1lbAwSPNowxtqrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:28:45.717308Z"},"content_sha256":"49da552f279569019253bdeddd19c38cc8bbfc227bb712e7655ba6d677a57590","schema_version":"1.0","event_id":"sha256:49da552f279569019253bdeddd19c38cc8bbfc227bb712e7655ba6d677a57590"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHA5VG465HSN426QRRETXFWV4V/bundle.json","state_url":"https://pith.science/pith/UHA5VG465HSN426QRRETXFWV4V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHA5VG465HSN426QRRETXFWV4V/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":"2026-08-04T18:28:45Z","links":{"resolver":"https://pith.science/pith/UHA5VG465HSN426QRRETXFWV4V","bundle":"https://pith.science/pith/UHA5VG465HSN426QRRETXFWV4V/bundle.json","state":"https://pith.science/pith/UHA5VG465HSN426QRRETXFWV4V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHA5VG465HSN426QRRETXFWV4V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UHA5VG465HSN426QRRETXFWV4V","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":"23dbff30b9635f550c1fbb9d13e0c29537960fb2e62853d3b03587c5748df153","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T10:55:28Z","title_canon_sha256":"a2f04817b9fc4716b44129a080b0ece85a88a6ee687d5181e5810d2ba107d4a9"},"schema_version":"1.0","source":{"id":"2607.09287","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09287","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09287v1","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09287","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"pith_short_12","alias_value":"UHA5VG465HSN","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"pith_short_16","alias_value":"UHA5VG465HSN426Q","created_at":"2026-07-13T01:18:58Z"},{"alias_kind":"pith_short_8","alias_value":"UHA5VG46","created_at":"2026-07-13T01:18:58Z"}],"graph_snapshots":[{"event_id":"sha256:49da552f279569019253bdeddd19c38cc8bbfc227bb712e7655ba6d677a57590","target":"graph","created_at":"2026-07-13T01:18:58Z","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/2607.09287/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) remain expensive to fine-tune because full-parameter updates require substantial memory, compute, and per-task storage. We study whether saliency signals originally developed for pruning can be reused to choose where a model should adapt. We propose Super, a sparse parameter-efficient fine-tuning (PEFT) method that fixes a small trainable support using a Wanda-style activation-weighted magnitude score [Sun et al., 2023] computed from a calibration pass. We then introduce Supra, a hybrid adapter that combines this sparse update with LoRA while preserving a matched t","authors_text":"Ivan Ilin, Peter Richt\\'arik, Philip Zmushko","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T10:55:28Z","title":"Super-Tuning: From Activation-Aware Pruning to Sparse Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09287","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:e9cb306485341aa76ff2ed565e5e6e02cd70c22f5f2c604f7f174872d8b78f54","target":"record","created_at":"2026-07-13T01:18:58Z","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":"23dbff30b9635f550c1fbb9d13e0c29537960fb2e62853d3b03587c5748df153","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-10T10:55:28Z","title_canon_sha256":"a2f04817b9fc4716b44129a080b0ece85a88a6ee687d5181e5810d2ba107d4a9"},"schema_version":"1.0","source":{"id":"2607.09287","kind":"arxiv","version":1}},"canonical_sha256":"a1c1da9b9ee9e4de6bd08c493b96d5e55b82eb9c7f480d4382c8944e0ca31e34","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1c1da9b9ee9e4de6bd08c493b96d5e55b82eb9c7f480d4382c8944e0ca31e34","first_computed_at":"2026-07-13T01:18:58.912262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:18:58.912262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PgoSWOofiYY+vCBk5WHAPu2tZ3p3SB1SDTeQitYVb+w52eRhSSQfOaDzdNrTT2sYKt5SzMF/qZJa7KjX6vaKCg==","signature_status":"signed_v1","signed_at":"2026-07-13T01:18:58.913279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09287","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9cb306485341aa76ff2ed565e5e6e02cd70c22f5f2c604f7f174872d8b78f54","sha256:49da552f279569019253bdeddd19c38cc8bbfc227bb712e7655ba6d677a57590"],"state_sha256":"dcf705608a5f4ab30782d810a9a1256c843ab5fb4feaa1d6e882e2859f8b2fee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHrJQik09R7/0HHEjBgdQ7Vy4rbDhZpv1KFrVnm+UCshym/d7ac7VFWzHMmaogsMKvri+xawXN9DMg1LipcxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:28:45.723040Z","bundle_sha256":"d737870d00acba8c91815117dbb7793a060a93e4333fcefd5da66a34ddfbd213"}}