{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:55J5GNWPVZH5XTUFXDOXUMTL5H","short_pith_number":"pith:55J5GNWP","canonical_record":{"source":{"id":"2607.13425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T04:03:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2424a55cd84df30bdb0c267aba23e0c3504395c2fb1b4dcb1d38f2b0c4da640b","abstract_canon_sha256":"019d5a3b4d73d57603f8f38f57fa1b11aaab6034deff7bcb68b1e40ec19ae553"},"schema_version":"1.0"},"canonical_sha256":"ef53d336cfae4fdbce85b8dd7a326be9c3c153c0cadef6c3d9036761b1a4ba76","source":{"kind":"arxiv","id":"2607.13425","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13425","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13425v1","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13425","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"55J5GNWPVZH5","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"55J5GNWPVZH5XTUF","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"55J5GNWP","created_at":"2026-07-16T00:22:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:55J5GNWPVZH5XTUFXDOXUMTL5H","target":"record","payload":{"canonical_record":{"source":{"id":"2607.13425","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T04:03:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2424a55cd84df30bdb0c267aba23e0c3504395c2fb1b4dcb1d38f2b0c4da640b","abstract_canon_sha256":"019d5a3b4d73d57603f8f38f57fa1b11aaab6034deff7bcb68b1e40ec19ae553"},"schema_version":"1.0"},"canonical_sha256":"ef53d336cfae4fdbce85b8dd7a326be9c3c153c0cadef6c3d9036761b1a4ba76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:22:17.320042Z","signature_b64":"1LeBjp6MuMg0W9kJRgqwFVAEhQxbZeUj2ED2vsbcR8VCJoCEKaZ9bqrWaoW+eFexXsJXMfl4fpMLkMzlXZIbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef53d336cfae4fdbce85b8dd7a326be9c3c153c0cadef6c3d9036761b1a4ba76","last_reissued_at":"2026-07-16T00:22:17.319183Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:22:17.319183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.13425","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":"2026-07-16T00:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JUnMywoWWe3DhsV9/Hjipg2ImI5SiQdnTRzf3xMcsfvHa/ci8W8uxnVttbkS4Vp3LjGdHeVzccQQkZQPI10UAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:47:54.423114Z"},"content_sha256":"e161746719d524222aed86438798ff6f42eecc48221a64daa3c7a74bbdf563ee","schema_version":"1.0","event_id":"sha256:e161746719d524222aed86438798ff6f42eecc48221a64daa3c7a74bbdf563ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:55J5GNWPVZH5XTUFXDOXUMTL5H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chandan Singh, Charlotte Siska, Jianfeng Gao, Tsui-Wei Weng, Tuomas Oikarinen, Zixiao Chen","submitted_at":"2026-07-15T04:03:24Z","abstract_excerpt":"Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to struggle when faced with few samples for difficult tasks. To meet this challenge, we propose Attention Head Reweighting (AHR), a data-efficient method that adapts LLMs to new text-classification tasks by learning only a single scalar per attention head. This drastically reduces the number of parameters that need to be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13425","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/2607.13425/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":"2026-07-16T00:22:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kMfhhnAsqFD+Lmg8L3NZ/upfhEIfvXgrKyUjt0nCHkitTd151cInB4bAIc3Y9GrFv4MtXGw9KWZ4XxSiykJnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:47:54.424204Z"},"content_sha256":"769886d9e6e35a78e8e8e6dc8d68d68b9da2d1c6d5bac45720b6a0b2724eb307","schema_version":"1.0","event_id":"sha256:769886d9e6e35a78e8e8e6dc8d68d68b9da2d1c6d5bac45720b6a0b2724eb307"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55J5GNWPVZH5XTUFXDOXUMTL5H/bundle.json","state_url":"https://pith.science/pith/55J5GNWPVZH5XTUFXDOXUMTL5H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55J5GNWPVZH5XTUFXDOXUMTL5H/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":"2026-08-04T00:47:54Z","links":{"resolver":"https://pith.science/pith/55J5GNWPVZH5XTUFXDOXUMTL5H","bundle":"https://pith.science/pith/55J5GNWPVZH5XTUFXDOXUMTL5H/bundle.json","state":"https://pith.science/pith/55J5GNWPVZH5XTUFXDOXUMTL5H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55J5GNWPVZH5XTUFXDOXUMTL5H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:55J5GNWPVZH5XTUFXDOXUMTL5H","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":"019d5a3b4d73d57603f8f38f57fa1b11aaab6034deff7bcb68b1e40ec19ae553","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T04:03:24Z","title_canon_sha256":"2424a55cd84df30bdb0c267aba23e0c3504395c2fb1b4dcb1d38f2b0c4da640b"},"schema_version":"1.0","source":{"id":"2607.13425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13425","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13425v1","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13425","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"55J5GNWPVZH5","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"55J5GNWPVZH5XTUF","created_at":"2026-07-16T00:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"55J5GNWP","created_at":"2026-07-16T00:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:769886d9e6e35a78e8e8e6dc8d68d68b9da2d1c6d5bac45720b6a0b2724eb307","target":"graph","created_at":"2026-07-16T00:22:17Z","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/2607.13425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning effectively from limited data is critical in domains like security where labeled examples are scarce. Large language models (LLMs) have demonstrated some capabilities for data-efficient learning, especially through parameter-efficient adaptation methods, but continue to struggle when faced with few samples for difficult tasks. To meet this challenge, we propose Attention Head Reweighting (AHR), a data-efficient method that adapts LLMs to new text-classification tasks by learning only a single scalar per attention head. This drastically reduces the number of parameters that need to be ","authors_text":"Chandan Singh, Charlotte Siska, Jianfeng Gao, Tsui-Wei Weng, Tuomas Oikarinen, Zixiao Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T04:03:24Z","title":"Data-Efficient Adaptation of LLMs via Attention Head Reweighting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13425","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:e161746719d524222aed86438798ff6f42eecc48221a64daa3c7a74bbdf563ee","target":"record","created_at":"2026-07-16T00:22:17Z","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":"019d5a3b4d73d57603f8f38f57fa1b11aaab6034deff7bcb68b1e40ec19ae553","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-15T04:03:24Z","title_canon_sha256":"2424a55cd84df30bdb0c267aba23e0c3504395c2fb1b4dcb1d38f2b0c4da640b"},"schema_version":"1.0","source":{"id":"2607.13425","kind":"arxiv","version":1}},"canonical_sha256":"ef53d336cfae4fdbce85b8dd7a326be9c3c153c0cadef6c3d9036761b1a4ba76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef53d336cfae4fdbce85b8dd7a326be9c3c153c0cadef6c3d9036761b1a4ba76","first_computed_at":"2026-07-16T00:22:17.319183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:22:17.319183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1LeBjp6MuMg0W9kJRgqwFVAEhQxbZeUj2ED2vsbcR8VCJoCEKaZ9bqrWaoW+eFexXsJXMfl4fpMLkMzlXZIbCg==","signature_status":"signed_v1","signed_at":"2026-07-16T00:22:17.320042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e161746719d524222aed86438798ff6f42eecc48221a64daa3c7a74bbdf563ee","sha256:769886d9e6e35a78e8e8e6dc8d68d68b9da2d1c6d5bac45720b6a0b2724eb307"],"state_sha256":"cf944b7308fa8f29f5bc4aa82290ee1a8c33bb2cab8d0dfa1be66ecf30380033"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6o2AlcT+/1TpffeabXXwTB0nBMrjAYuirTxRfGjmTk5tnISK9YuHO4qI4cE1Bt+o2nVLD53bfPWdhoPUXBAGCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:47:54.497667Z","bundle_sha256":"8164a18c28c92314a78991305bbbed0111602809ba312fea2e5ac2a75390733c"}}