{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PBGWULRVXWVH35T7Z5EYG7CIMN","short_pith_number":"pith:PBGWULRV","canonical_record":{"source":{"id":"2304.11082","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T17:50:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed632885193e72f26bb874420cf746a3d1cb85a092b39b4798b724373628e6bb","abstract_canon_sha256":"9a5f9653e691e40249504335f880005d4772ab107e17c0ce441bd0c79688450e"},"schema_version":"1.0"},"canonical_sha256":"784d6a2e35bdaa7df67fcf49837c48637f0a560e4141985e9b758f64d850aaab","source":{"kind":"arxiv","id":"2304.11082","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11082","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11082v6","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11082","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"pith_short_12","alias_value":"PBGWULRVXWVH","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"pith_short_16","alias_value":"PBGWULRVXWVH35T7","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"pith_short_8","alias_value":"PBGWULRV","created_at":"2026-07-05T08:26:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PBGWULRVXWVH35T7Z5EYG7CIMN","target":"record","payload":{"canonical_record":{"source":{"id":"2304.11082","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T17:50:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed632885193e72f26bb874420cf746a3d1cb85a092b39b4798b724373628e6bb","abstract_canon_sha256":"9a5f9653e691e40249504335f880005d4772ab107e17c0ce441bd0c79688450e"},"schema_version":"1.0"},"canonical_sha256":"784d6a2e35bdaa7df67fcf49837c48637f0a560e4141985e9b758f64d850aaab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:11.321221Z","signature_b64":"3IHyQ8GlylB5elPsCRTkCRgSm3TuLNk2I2+1bDJV6P0bKVuWYzZd5Rs8W3/Y2xmRtYkpZhr+cFnsnAuqM1oaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"784d6a2e35bdaa7df67fcf49837c48637f0a560e4141985e9b758f64d850aaab","last_reissued_at":"2026-07-05T08:26:11.320735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:11.320735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.11082","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:26:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3JFpwH8CRopZbkvKbYTe3NYjA3cNQe8Fsy72mxc23PNZck3N9/cLWsQZex7oF2lziLtzyvDB+Hd7kuP/zaICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:28:23.118119Z"},"content_sha256":"c72e1f9b898864ae1f7c638b7703af01c6a2688273b7af0a87b56c44257df8d8","schema_version":"1.0","event_id":"sha256:c72e1f9b898864ae1f7c638b7703af01c6a2688273b7af0a87b56c44257df8d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PBGWULRVXWVH35T7Z5EYG7CIMN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fundamental Limitations of Alignment in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Amnon Shashua, Noam Wies, Oshri Avnery, Yoav Levine, Yotam Wolf","submitted_at":"2023-04-19T17:50:09Z","abstract_excerpt":"An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors and inhibits undesired ones, a process referred to as alignment. In this paper, we propose a theoretical approach called Behavior Expectation Bounds (BEB) which allows us to formally investigate several inherent characteristics and limitations of alignment in large language models. Importantly, we prove that within the limits of this framework, for any behavi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11082","kind":"arxiv","version":6},"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/2304.11082/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":"2026-07-05T08:26:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g1L30EvOX4ujLhX6LmkbhYUbTqBuIwselpHgSM6giBctI8RBjVI+01Jzc2++ziUQoZr/6Ycm+KgO6FXGrs9wAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:28:23.118638Z"},"content_sha256":"56b57c4dc109cd8dcc6b5418f9a58ec84625c7a7895f5840c772f3b9a4cef700","schema_version":"1.0","event_id":"sha256:56b57c4dc109cd8dcc6b5418f9a58ec84625c7a7895f5840c772f3b9a4cef700"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBGWULRVXWVH35T7Z5EYG7CIMN/bundle.json","state_url":"https://pith.science/pith/PBGWULRVXWVH35T7Z5EYG7CIMN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBGWULRVXWVH35T7Z5EYG7CIMN/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":"2026-08-07T00:28:23Z","links":{"resolver":"https://pith.science/pith/PBGWULRVXWVH35T7Z5EYG7CIMN","bundle":"https://pith.science/pith/PBGWULRVXWVH35T7Z5EYG7CIMN/bundle.json","state":"https://pith.science/pith/PBGWULRVXWVH35T7Z5EYG7CIMN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBGWULRVXWVH35T7Z5EYG7CIMN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PBGWULRVXWVH35T7Z5EYG7CIMN","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":"9a5f9653e691e40249504335f880005d4772ab107e17c0ce441bd0c79688450e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T17:50:09Z","title_canon_sha256":"ed632885193e72f26bb874420cf746a3d1cb85a092b39b4798b724373628e6bb"},"schema_version":"1.0","source":{"id":"2304.11082","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11082","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11082v6","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11082","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"pith_short_12","alias_value":"PBGWULRVXWVH","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"pith_short_16","alias_value":"PBGWULRVXWVH35T7","created_at":"2026-07-05T08:26:11Z"},{"alias_kind":"pith_short_8","alias_value":"PBGWULRV","created_at":"2026-07-05T08:26:11Z"}],"graph_snapshots":[{"event_id":"sha256:56b57c4dc109cd8dcc6b5418f9a58ec84625c7a7895f5840c772f3b9a4cef700","target":"graph","created_at":"2026-07-05T08:26:11Z","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/2304.11082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An important aspect in developing language models that interact with humans is aligning their behavior to be useful and unharmful for their human users. This is usually achieved by tuning the model in a way that enhances desired behaviors and inhibits undesired ones, a process referred to as alignment. In this paper, we propose a theoretical approach called Behavior Expectation Bounds (BEB) which allows us to formally investigate several inherent characteristics and limitations of alignment in large language models. Importantly, we prove that within the limits of this framework, for any behavi","authors_text":"Amnon Shashua, Noam Wies, Oshri Avnery, Yoav Levine, Yotam Wolf","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T17:50:09Z","title":"Fundamental Limitations of Alignment in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11082","kind":"arxiv","version":6},"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:c72e1f9b898864ae1f7c638b7703af01c6a2688273b7af0a87b56c44257df8d8","target":"record","created_at":"2026-07-05T08:26:11Z","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":"9a5f9653e691e40249504335f880005d4772ab107e17c0ce441bd0c79688450e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-19T17:50:09Z","title_canon_sha256":"ed632885193e72f26bb874420cf746a3d1cb85a092b39b4798b724373628e6bb"},"schema_version":"1.0","source":{"id":"2304.11082","kind":"arxiv","version":6}},"canonical_sha256":"784d6a2e35bdaa7df67fcf49837c48637f0a560e4141985e9b758f64d850aaab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"784d6a2e35bdaa7df67fcf49837c48637f0a560e4141985e9b758f64d850aaab","first_computed_at":"2026-07-05T08:26:11.320735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:11.320735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3IHyQ8GlylB5elPsCRTkCRgSm3TuLNk2I2+1bDJV6P0bKVuWYzZd5Rs8W3/Y2xmRtYkpZhr+cFnsnAuqM1oaAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:11.321221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11082","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c72e1f9b898864ae1f7c638b7703af01c6a2688273b7af0a87b56c44257df8d8","sha256:56b57c4dc109cd8dcc6b5418f9a58ec84625c7a7895f5840c772f3b9a4cef700"],"state_sha256":"2ae15b2baf1e61f629e3013f5441a11b1b429867074fa4194225723c2e868c48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6EndiyUVZjd8wcDgIJiqFNXtgZht7PMRhvSK68TsX7J7QrwkGF+VVQzIzap10ZdqyVief43Gv53vhHf08JcBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:28:23.122008Z","bundle_sha256":"d00930f33765994fd9d148a9500269c0ac459860ae8b801af17a8b38d3c2a9c1"}}