{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V5GMVV2QEPMLBRVYML4K7HUCWX","short_pith_number":"pith:V5GMVV2Q","canonical_record":{"source":{"id":"2606.06667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T19:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"0757dd904d4edafe2eef8bfce367d6fa65297473df432c63869c362f63f6add0","abstract_canon_sha256":"a811131b40638d5f6ff9755f937a10e43c5965b4a5f1d3d328781030d2ee7d75"},"schema_version":"1.0"},"canonical_sha256":"af4ccad75023d8b0c6b862f8af9e82b5c3d986e75f96fb3a4f3129675f3149f8","source":{"kind":"arxiv","id":"2606.06667","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06667","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06667v1","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06667","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"V5GMVV2QEPML","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"V5GMVV2QEPMLBRVY","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"V5GMVV2Q","created_at":"2026-06-08T01:04:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V5GMVV2QEPMLBRVYML4K7HUCWX","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06667","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T19:32:00Z","cross_cats_sorted":[],"title_canon_sha256":"0757dd904d4edafe2eef8bfce367d6fa65297473df432c63869c362f63f6add0","abstract_canon_sha256":"a811131b40638d5f6ff9755f937a10e43c5965b4a5f1d3d328781030d2ee7d75"},"schema_version":"1.0"},"canonical_sha256":"af4ccad75023d8b0c6b862f8af9e82b5c3d986e75f96fb3a4f3129675f3149f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:21.621223Z","signature_b64":"JOfVbkrs1JXwTtc3/X4JfxXG0kNVHlnA3LE3sZKX1qw73IcjFoyPb7/AX9Qn7ZEHLKKquY9hQCCDG6S2qpryBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af4ccad75023d8b0c6b862f8af9e82b5c3d986e75f96fb3a4f3129675f3149f8","last_reissued_at":"2026-06-08T01:04:21.620496Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:21.620496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06667","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":"2026-06-08T01:04:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VUY45uQ/9IQ/ZydfTxrmzQEjlV/rsB1fKrxDsYs4uCvoOer0EmOUoaPoEhlHz+rcI3Mhiwsw3cFIwFMti7TZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:15:56.681226Z"},"content_sha256":"4f8d233727c35af3c4e045f5a058e4603a1bdf869115a6cfe59ffb6e465d0b75","schema_version":"1.0","event_id":"sha256:4f8d233727c35af3c4e045f5a058e4603a1bdf869115a6cfe59ffb6e465d0b75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V5GMVV2QEPMLBRVYML4K7HUCWX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aryaman Arora, David Bau, Jiachen Zhao, Weiyan Shi, Yiyou Sun, Zhengxuan Wu","submitted_at":"2026-06-04T19:32:00Z","abstract_excerpt":"The mechanisms behind LLMs' broad over-generalization beyond training examples remain unclear. Emergent misalignment (EM) offers a striking case study: finetuning on narrow tasks induces broad misalignment to semantically-unrelated test domains. In this work, we propose the Piggyback Hypothesis: the chat-template tokens can piggyback the finetuned behaviour onto out-of-domain queries. We validate this hypothesis by showing that subtle perturbations to the prefix (tokens preceding all user queries), or patching the prefix representations with those from the unfinetuned model, can restore alignm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06667","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/2606.06667/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":"2026-06-08T01:04:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d910YJhFupmksvGzIpS+BvRMUffZFDonKAu52a83EqzklwfCLjTjTBzCmGpw+6+RxPsm+pZkpVS+JEmRoVPMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T07:15:56.681637Z"},"content_sha256":"77895debcf8d8a0f3c6e05af9fa6a2258c222692aad5dbdcf1cd1dccf5226c0e","schema_version":"1.0","event_id":"sha256:77895debcf8d8a0f3c6e05af9fa6a2258c222692aad5dbdcf1cd1dccf5226c0e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5GMVV2QEPMLBRVYML4K7HUCWX/bundle.json","state_url":"https://pith.science/pith/V5GMVV2QEPMLBRVYML4K7HUCWX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5GMVV2QEPMLBRVYML4K7HUCWX/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":"2026-07-02T07:15:56Z","links":{"resolver":"https://pith.science/pith/V5GMVV2QEPMLBRVYML4K7HUCWX","bundle":"https://pith.science/pith/V5GMVV2QEPMLBRVYML4K7HUCWX/bundle.json","state":"https://pith.science/pith/V5GMVV2QEPMLBRVYML4K7HUCWX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5GMVV2QEPMLBRVYML4K7HUCWX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V5GMVV2QEPMLBRVYML4K7HUCWX","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":"a811131b40638d5f6ff9755f937a10e43c5965b4a5f1d3d328781030d2ee7d75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T19:32:00Z","title_canon_sha256":"0757dd904d4edafe2eef8bfce367d6fa65297473df432c63869c362f63f6add0"},"schema_version":"1.0","source":{"id":"2606.06667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06667","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06667v1","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06667","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"V5GMVV2QEPML","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"V5GMVV2QEPMLBRVY","created_at":"2026-06-08T01:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"V5GMVV2Q","created_at":"2026-06-08T01:04:21Z"}],"graph_snapshots":[{"event_id":"sha256:77895debcf8d8a0f3c6e05af9fa6a2258c222692aad5dbdcf1cd1dccf5226c0e","target":"graph","created_at":"2026-06-08T01:04:21Z","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/2606.06667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The mechanisms behind LLMs' broad over-generalization beyond training examples remain unclear. Emergent misalignment (EM) offers a striking case study: finetuning on narrow tasks induces broad misalignment to semantically-unrelated test domains. In this work, we propose the Piggyback Hypothesis: the chat-template tokens can piggyback the finetuned behaviour onto out-of-domain queries. We validate this hypothesis by showing that subtle perturbations to the prefix (tokens preceding all user queries), or patching the prefix representations with those from the unfinetuned model, can restore alignm","authors_text":"Aryaman Arora, David Bau, Jiachen Zhao, Weiyan Shi, Yiyou Sun, Zhengxuan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T19:32:00Z","title":"The Piggyback Hypothesis of Generalization: Explaining and Mitigating Emergent Misalignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06667","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":"sha256:4f8d233727c35af3c4e045f5a058e4603a1bdf869115a6cfe59ffb6e465d0b75","target":"record","created_at":"2026-06-08T01:04:21Z","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":"a811131b40638d5f6ff9755f937a10e43c5965b4a5f1d3d328781030d2ee7d75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T19:32:00Z","title_canon_sha256":"0757dd904d4edafe2eef8bfce367d6fa65297473df432c63869c362f63f6add0"},"schema_version":"1.0","source":{"id":"2606.06667","kind":"arxiv","version":1}},"canonical_sha256":"af4ccad75023d8b0c6b862f8af9e82b5c3d986e75f96fb3a4f3129675f3149f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af4ccad75023d8b0c6b862f8af9e82b5c3d986e75f96fb3a4f3129675f3149f8","first_computed_at":"2026-06-08T01:04:21.620496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:21.620496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JOfVbkrs1JXwTtc3/X4JfxXG0kNVHlnA3LE3sZKX1qw73IcjFoyPb7/AX9Qn7ZEHLKKquY9hQCCDG6S2qpryBg==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:21.621223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f8d233727c35af3c4e045f5a058e4603a1bdf869115a6cfe59ffb6e465d0b75","sha256:77895debcf8d8a0f3c6e05af9fa6a2258c222692aad5dbdcf1cd1dccf5226c0e"],"state_sha256":"de9ab1250332540758044108bcbfd3fc95a94b449db7de43c721a7c02d64c8af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/OJg4bYv5VyVu+ovaErcIYp6MExatVoKMxHJtQyGg0+5Fu8m1MIRrh5V6lv/rlyXnr8m3mKNqXLQU1i6QKoXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T07:15:56.683644Z","bundle_sha256":"aba5c2cc99cd80400d5233ff484cabce4939b52ceb0f1beee62bb8553ce77bda"}}