{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OYR6E4NHE3SFT5AK2YQSPTH7MG","short_pith_number":"pith:OYR6E4NH","canonical_record":{"source":{"id":"2504.04050","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"11b9d8aab4d172b1d18ac1c5fffc3dd9aff25ce815417500b76454967ec6fe0d","abstract_canon_sha256":"6e17a030c917103ea75e33958a35db611fcdd0ab4a0dfa54c945cc330046328d"},"schema_version":"1.0"},"canonical_sha256":"7623e271a726e459f40ad62127ccff6196264ce88e79b70e103740a1c7600c13","source":{"kind":"arxiv","id":"2504.04050","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04050","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04050v3","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04050","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"OYR6E4NHE3SF","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_16","alias_value":"OYR6E4NHE3SFT5AK","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_8","alias_value":"OYR6E4NH","created_at":"2026-07-05T11:09:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OYR6E4NHE3SFT5AK2YQSPTH7MG","target":"record","payload":{"canonical_record":{"source":{"id":"2504.04050","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:05:55Z","cross_cats_sorted":[],"title_canon_sha256":"11b9d8aab4d172b1d18ac1c5fffc3dd9aff25ce815417500b76454967ec6fe0d","abstract_canon_sha256":"6e17a030c917103ea75e33958a35db611fcdd0ab4a0dfa54c945cc330046328d"},"schema_version":"1.0"},"canonical_sha256":"7623e271a726e459f40ad62127ccff6196264ce88e79b70e103740a1c7600c13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:10.887716Z","signature_b64":"xMGOk4klVWFV3donJLIZyS3gNws11RlNzzIMpwmIXyHPPjBETaanAAk33ugYCTny0+i0kB6/WQNcm7O+rUcVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7623e271a726e459f40ad62127ccff6196264ce88e79b70e103740a1c7600c13","last_reissued_at":"2026-07-05T11:09:10.887203Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:10.887203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.04050","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5m6A2iAGyRA6Aw+uE1MkJbvs5sv9yLIBUge0yLM8e50//6dFhOWCfA5IcgqMFcfkLuOwGJs0fnjp1V1x3GGmAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:33:12.298006Z"},"content_sha256":"8e7247119f500a490b87c8b131e742be477913b0cd9b76968009d3305c7e3aca","schema_version":"1.0","event_id":"sha256:8e7247119f500a490b87c8b131e742be477913b0cd9b76968009d3305c7e3aca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OYR6E4NHE3SFT5AK2YQSPTH7MG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FISH-Tuning: Enhancing PEFT Methods with Fisher Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kang Xue, Ming Dong, Tingting He, Xinhui Tu","submitted_at":"2025-04-05T04:05:55Z","abstract_excerpt":"The rapid growth in the parameter size of Large Language Models (LLMs) has spurred the development of Parameter-Efficient Fine-Tuning (PEFT) methods to mitigate the substantial computational costs of fine-tuning. Among these, Fisher Induced Sparse uncHanging (FISH) Mask is a selection-based PEFT technique that identifies a critical subset of pre-trained parameters using approximate Fisher information. While addition-based and reparameterization-based PEFT methods like LoRA and Adapter already fine-tune only a small number of parameters, the newly introduced parameters within these methods them"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04050","kind":"arxiv","version":3},"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/2504.04050/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":"2026-07-05T11:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dO3mrs5ze2YJJgOclD6U4L/n60yMxcL+bmB4Q4+nlkST7fJnyKIsX/Pt4Mb54UWKQzkJoX0bzl2bsqZsGjO1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T00:33:12.298862Z"},"content_sha256":"2ee23779ac6c803a026067e3e37ba6ceca42e4d0ebaa4e6449ab73ee10f46e06","schema_version":"1.0","event_id":"sha256:2ee23779ac6c803a026067e3e37ba6ceca42e4d0ebaa4e6449ab73ee10f46e06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG/bundle.json","state_url":"https://pith.science/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG/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":"2026-08-14T00:33:12Z","links":{"resolver":"https://pith.science/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG","bundle":"https://pith.science/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG/bundle.json","state":"https://pith.science/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OYR6E4NHE3SFT5AK2YQSPTH7MG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OYR6E4NHE3SFT5AK2YQSPTH7MG","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":"6e17a030c917103ea75e33958a35db611fcdd0ab4a0dfa54c945cc330046328d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:05:55Z","title_canon_sha256":"11b9d8aab4d172b1d18ac1c5fffc3dd9aff25ce815417500b76454967ec6fe0d"},"schema_version":"1.0","source":{"id":"2504.04050","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.04050","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2504.04050v3","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04050","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"OYR6E4NHE3SF","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_16","alias_value":"OYR6E4NHE3SFT5AK","created_at":"2026-07-05T11:09:10Z"},{"alias_kind":"pith_short_8","alias_value":"OYR6E4NH","created_at":"2026-07-05T11:09:10Z"}],"graph_snapshots":[{"event_id":"sha256:2ee23779ac6c803a026067e3e37ba6ceca42e4d0ebaa4e6449ab73ee10f46e06","target":"graph","created_at":"2026-07-05T11:09:10Z","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/2504.04050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid growth in the parameter size of Large Language Models (LLMs) has spurred the development of Parameter-Efficient Fine-Tuning (PEFT) methods to mitigate the substantial computational costs of fine-tuning. Among these, Fisher Induced Sparse uncHanging (FISH) Mask is a selection-based PEFT technique that identifies a critical subset of pre-trained parameters using approximate Fisher information. While addition-based and reparameterization-based PEFT methods like LoRA and Adapter already fine-tune only a small number of parameters, the newly introduced parameters within these methods them","authors_text":"Kang Xue, Ming Dong, Tingting He, Xinhui Tu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:05:55Z","title":"FISH-Tuning: Enhancing PEFT Methods with Fisher Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04050","kind":"arxiv","version":3},"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":"sha256:8e7247119f500a490b87c8b131e742be477913b0cd9b76968009d3305c7e3aca","target":"record","created_at":"2026-07-05T11:09:10Z","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":"6e17a030c917103ea75e33958a35db611fcdd0ab4a0dfa54c945cc330046328d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-05T04:05:55Z","title_canon_sha256":"11b9d8aab4d172b1d18ac1c5fffc3dd9aff25ce815417500b76454967ec6fe0d"},"schema_version":"1.0","source":{"id":"2504.04050","kind":"arxiv","version":3}},"canonical_sha256":"7623e271a726e459f40ad62127ccff6196264ce88e79b70e103740a1c7600c13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7623e271a726e459f40ad62127ccff6196264ce88e79b70e103740a1c7600c13","first_computed_at":"2026-07-05T11:09:10.887203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:10.887203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xMGOk4klVWFV3donJLIZyS3gNws11RlNzzIMpwmIXyHPPjBETaanAAk33ugYCTny0+i0kB6/WQNcm7O+rUcVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:10.887716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.04050","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e7247119f500a490b87c8b131e742be477913b0cd9b76968009d3305c7e3aca","sha256:2ee23779ac6c803a026067e3e37ba6ceca42e4d0ebaa4e6449ab73ee10f46e06"],"state_sha256":"f10ea5e063e5a584a3c37813d7637abb789f6efb40587aaa0b280b8bfd1ab82c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L4JntR8GwKuqF89Sk7G2toMAf18qHtNbkSm98nbqTMEUXiAAD8z+4XncpjJkLSGlSs8YF6IDHpD66k0+VsuXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T00:33:12.327390Z","bundle_sha256":"fb675c2e18880773e86b52e32325f787187d7b1e12f07a91fd2ff8ada9a9d35e"}}