{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2BPKAW4J7YS7LGJE6T77C52M5N","short_pith_number":"pith:2BPKAW4J","canonical_record":{"source":{"id":"2604.18179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-20T12:34:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"019529845fe4b5c7bbd0dbb2d9a8630d20cc7b8b3299d45284ac36a878cfd2c4","abstract_canon_sha256":"5f511eb5d3842017c46d86ea7b4b1cfeb2542f964a4d0e5314a1e51b4a3bccd4"},"schema_version":"1.0"},"canonical_sha256":"d05ea05b89fe25f59924f4fff1774ceb5e2457537afa7d677a167b32e477028b","source":{"kind":"arxiv","id":"2604.18179","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18179","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18179v2","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18179","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"2BPKAW4J7YS7","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"2BPKAW4J7YS7LGJE","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"2BPKAW4J","created_at":"2026-05-26T01:03:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2BPKAW4J7YS7LGJE6T77C52M5N","target":"record","payload":{"canonical_record":{"source":{"id":"2604.18179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-20T12:34:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"019529845fe4b5c7bbd0dbb2d9a8630d20cc7b8b3299d45284ac36a878cfd2c4","abstract_canon_sha256":"5f511eb5d3842017c46d86ea7b4b1cfeb2542f964a4d0e5314a1e51b4a3bccd4"},"schema_version":"1.0"},"canonical_sha256":"d05ea05b89fe25f59924f4fff1774ceb5e2457537afa7d677a167b32e477028b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:30.670889Z","signature_b64":"nKSz6m/GvRbMEP7tLYH+PdClDzCeayysZxRzawGrOpbHFFNvrattWTMls/wPJCrcZ9MCcinGtDE5mgO6h7q1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d05ea05b89fe25f59924f4fff1774ceb5e2457537afa7d677a167b32e477028b","last_reissued_at":"2026-05-26T01:03:30.670111Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:30.670111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.18179","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fq4HGJI/hvaCzEZO+JpmPuhCSwu/3AvVU3h0RB1jauRTlHRjoNxU6Mg88Lme5m3umUs/Rz5hwj2nJGcRauYdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:36:35.208921Z"},"content_sha256":"7bda82e830169d4c0ce0c76ccdfcb54e9078d8ffa71d8c486f017ed21643fe28","schema_version":"1.0","event_id":"sha256:7bda82e830169d4c0ce0c76ccdfcb54e9078d8ffa71d8c486f017ed21643fe28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2BPKAW4J7YS7LGJE6T77C52M5N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A Merkle-tree commitment to per-position sparse-autoencoder feature traces lets verifiers detect silent model substitution in hosted LLMs even when the provider knows the audit rules in advance.","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Ziyang Liu","submitted_at":"2026-04-20T12:34:56Z","abstract_excerpt":"Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return schemes such as SVIP leave a parallel-serve side-channel, since a dishonest provider can route the verifier's probe to the advertised model while serving ordinary users from a substitute. We propose a commit-open protocol that closes this gap. Before any opening request, the provider commits via a Merkle tree to a per-position sparse-autoencoder (SAE) feature-trace sketch of its served output at a published probe layer. A verifier opens random positions, score"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Of 17 attackers spanning same-family lifts, cross-family substitutes, and rank-<=128 adaptive LoRA, all are rejected at a shared, scale-stable threshold; the same attackers all evade a matched SVIP-style parallel-serve baseline. A white-box end-to-end attack that backpropagates through the frozen SAE encoder does not close the margin, and a feature-forgery attacker that never runs M_hon is bounded in closed form by an intrinsic-dimension argument.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a public named-circuit probe library calibrated with cross-backend noise produces feature traces sufficiently distinctive across models and that the fixed-threshold joint-consistency z-score rule remains reliable when the provider knows the protocol in advance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A Merkle-committed SAE feature-trace protocol detects model substitutions in hosted LLMs at a stable threshold where parallel-probe baselines fail, including against adaptive LoRA attackers.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A Merkle-tree commitment to per-position sparse-autoencoder feature traces lets verifiers detect silent model substitution in hosted LLMs even when the provider knows the audit rules in advance.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"84cdf7501e3b2bbe3af736d0628ce033ff6960694c7b6247750d00ab6f70c960"},"source":{"id":"2604.18179","kind":"arxiv","version":2},"verdict":{"id":"5365b309-4754-40c1-8503-6051a00ffa59","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T04:47:50.457417Z","strongest_claim":"Of 17 attackers spanning same-family lifts, cross-family substitutes, and rank-<=128 adaptive LoRA, all are rejected at a shared, scale-stable threshold; the same attackers all evade a matched SVIP-style parallel-serve baseline. A white-box end-to-end attack that backpropagates through the frozen SAE encoder does not close the margin, and a feature-forgery attacker that never runs M_hon is bounded in closed form by an intrinsic-dimension argument.","one_line_summary":"A Merkle-committed SAE feature-trace protocol detects model substitutions in hosted LLMs at a stable threshold where parallel-probe baselines fail, including against adaptive LoRA attackers.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a public named-circuit probe library calibrated with cross-backend noise produces feature traces sufficiently distinctive across models and that the fixed-threshold joint-consistency z-score rule remains reliable when the provider knows the protocol in advance.","pith_extraction_headline":"A Merkle-tree commitment to per-position sparse-autoencoder feature traces lets verifiers detect silent model substitution in hosted LLMs even when the provider knows the audit rules in advance."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.18179/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-20T04:22:31.835432Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"e0a5b7484811fe02da9c2090c6ff468905ba9776a8a58c35974fe77877f35543"},"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":"5365b309-4754-40c1-8503-6051a00ffa59"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9XycE9hmYY81SA0xXyDjtW5EybTZdLmKl+87Lw+eXfKlXQo4f854EPmExYSgsL2MzHVHyBkVxjQzsRtI5ssDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:36:35.209455Z"},"content_sha256":"ab16e904234d0f9ad9e6dbb27ec8c8cbfe49a97b6b246ca7b566e90d087a31e4","schema_version":"1.0","event_id":"sha256:ab16e904234d0f9ad9e6dbb27ec8c8cbfe49a97b6b246ca7b566e90d087a31e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BPKAW4J7YS7LGJE6T77C52M5N/bundle.json","state_url":"https://pith.science/pith/2BPKAW4J7YS7LGJE6T77C52M5N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BPKAW4J7YS7LGJE6T77C52M5N/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":"2026-05-26T11:36:35Z","links":{"resolver":"https://pith.science/pith/2BPKAW4J7YS7LGJE6T77C52M5N","bundle":"https://pith.science/pith/2BPKAW4J7YS7LGJE6T77C52M5N/bundle.json","state":"https://pith.science/pith/2BPKAW4J7YS7LGJE6T77C52M5N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BPKAW4J7YS7LGJE6T77C52M5N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2BPKAW4J7YS7LGJE6T77C52M5N","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":"5f511eb5d3842017c46d86ea7b4b1cfeb2542f964a4d0e5314a1e51b4a3bccd4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-20T12:34:56Z","title_canon_sha256":"019529845fe4b5c7bbd0dbb2d9a8630d20cc7b8b3299d45284ac36a878cfd2c4"},"schema_version":"1.0","source":{"id":"2604.18179","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.18179","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2604.18179v2","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.18179","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"2BPKAW4J7YS7","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"2BPKAW4J7YS7LGJE","created_at":"2026-05-26T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"2BPKAW4J","created_at":"2026-05-26T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:ab16e904234d0f9ad9e6dbb27ec8c8cbfe49a97b6b246ca7b566e90d087a31e4","target":"graph","created_at":"2026-05-26T01:03:30Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Of 17 attackers spanning same-family lifts, cross-family substitutes, and rank-<=128 adaptive LoRA, all are rejected at a shared, scale-stable threshold; the same attackers all evade a matched SVIP-style parallel-serve baseline. A white-box end-to-end attack that backpropagates through the frozen SAE encoder does not close the margin, and a feature-forgery attacker that never runs M_hon is bounded in closed form by an intrinsic-dimension argument."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a public named-circuit probe library calibrated with cross-backend noise produces feature traces sufficiently distinctive across models and that the fixed-threshold joint-consistency z-score rule remains reliable when the provider knows the protocol in advance."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A Merkle-committed SAE feature-trace protocol detects model substitutions in hosted LLMs at a stable threshold where parallel-probe baselines fail, including against adaptive LoRA attackers."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A Merkle-tree commitment to per-position sparse-autoencoder feature traces lets verifiers detect silent model substitution in hosted LLMs even when the provider knows the audit rules in advance."}],"snapshot_sha256":"84cdf7501e3b2bbe3af736d0628ce033ff6960694c7b6247750d00ab6f70c960"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T04:22:31.835432Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.18179/integrity.json","findings":[],"snapshot_sha256":"e0a5b7484811fe02da9c2090c6ff468905ba9776a8a58c35974fe77877f35543","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hosted-LLM providers have a silent-substitution incentive: advertise a stronger model while serving cheaper replies. Probe-after-return schemes such as SVIP leave a parallel-serve side-channel, since a dishonest provider can route the verifier's probe to the advertised model while serving ordinary users from a substitute. We propose a commit-open protocol that closes this gap. Before any opening request, the provider commits via a Merkle tree to a per-position sparse-autoencoder (SAE) feature-trace sketch of its served output at a published probe layer. A verifier opens random positions, score","authors_text":"Ziyang Liu","cross_cats":["cs.AI"],"headline":"A Merkle-tree commitment to per-position sparse-autoencoder feature traces lets verifiers detect silent model substitution in hosted LLMs even when the provider knows the audit rules in advance.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-20T12:34:56Z","title":"Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.18179","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T04:47:50.457417Z","id":"5365b309-4754-40c1-8503-6051a00ffa59","model_set":{"reader":"grok-4.3"},"one_line_summary":"A Merkle-committed SAE feature-trace protocol detects model substitutions in hosted LLMs at a stable threshold where parallel-probe baselines fail, including against adaptive LoRA attackers.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A Merkle-tree commitment to per-position sparse-autoencoder feature traces lets verifiers detect silent model substitution in hosted LLMs even when the provider knows the audit rules in advance.","strongest_claim":"Of 17 attackers spanning same-family lifts, cross-family substitutes, and rank-<=128 adaptive LoRA, all are rejected at a shared, scale-stable threshold; the same attackers all evade a matched SVIP-style parallel-serve baseline. A white-box end-to-end attack that backpropagates through the frozen SAE encoder does not close the margin, and a feature-forgery attacker that never runs M_hon is bounded in closed form by an intrinsic-dimension argument.","weakest_assumption":"That a public named-circuit probe library calibrated with cross-backend noise produces feature traces sufficiently distinctive across models and that the fixed-threshold joint-consistency z-score rule remains reliable when the provider knows the protocol in advance."}},"verdict_id":"5365b309-4754-40c1-8503-6051a00ffa59"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7bda82e830169d4c0ce0c76ccdfcb54e9078d8ffa71d8c486f017ed21643fe28","target":"record","created_at":"2026-05-26T01:03:30Z","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":"5f511eb5d3842017c46d86ea7b4b1cfeb2542f964a4d0e5314a1e51b4a3bccd4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-04-20T12:34:56Z","title_canon_sha256":"019529845fe4b5c7bbd0dbb2d9a8630d20cc7b8b3299d45284ac36a878cfd2c4"},"schema_version":"1.0","source":{"id":"2604.18179","kind":"arxiv","version":2}},"canonical_sha256":"d05ea05b89fe25f59924f4fff1774ceb5e2457537afa7d677a167b32e477028b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d05ea05b89fe25f59924f4fff1774ceb5e2457537afa7d677a167b32e477028b","first_computed_at":"2026-05-26T01:03:30.670111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:30.670111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nKSz6m/GvRbMEP7tLYH+PdClDzCeayysZxRzawGrOpbHFFNvrattWTMls/wPJCrcZ9MCcinGtDE5mgO6h7q1BQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:30.670889Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.18179","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bda82e830169d4c0ce0c76ccdfcb54e9078d8ffa71d8c486f017ed21643fe28","sha256:ab16e904234d0f9ad9e6dbb27ec8c8cbfe49a97b6b246ca7b566e90d087a31e4"],"state_sha256":"32fe6609cd368b8398c9fec8c7e5a7e84d5fa794216fb3dc5804ecaf35f99f47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r4ZNia7/fDuXYaqL9iFuHjSrkB+j/z7XlxlnY080gIU7ZQgs2Wqm1pRabz14bzFBm1rs8V4NbcOdibDJsy/XDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:36:35.212709Z","bundle_sha256":"3c2393531a4e46ef0af65cc3c0a6e3a12f3853110b2be218635669c4451f0d19"}}