{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YPE2S33GBUW3RUT6BKKXDD3BBY","short_pith_number":"pith:YPE2S33G","canonical_record":{"source":{"id":"2606.25239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-23T23:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"912439cb19a10aafbe1416cff8bfabf68e3a49b30a179fe54037e1c8f2e9b080","abstract_canon_sha256":"a7fa5f48d114da3d101a96e35cbf8987113e6a8d8944ba9bdafcfec70e4f7f3c"},"schema_version":"1.0"},"canonical_sha256":"c3c9a96f660d2db8d27e0a95718f610e2e979f4c525d623991bf5f28ab8b24f2","source":{"kind":"arxiv","id":"2606.25239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25239","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25239v1","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25239","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"YPE2S33GBUW3","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_16","alias_value":"YPE2S33GBUW3RUT6","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_8","alias_value":"YPE2S33G","created_at":"2026-06-25T00:18:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YPE2S33GBUW3RUT6BKKXDD3BBY","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25239","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-23T23:56:21Z","cross_cats_sorted":[],"title_canon_sha256":"912439cb19a10aafbe1416cff8bfabf68e3a49b30a179fe54037e1c8f2e9b080","abstract_canon_sha256":"a7fa5f48d114da3d101a96e35cbf8987113e6a8d8944ba9bdafcfec70e4f7f3c"},"schema_version":"1.0"},"canonical_sha256":"c3c9a96f660d2db8d27e0a95718f610e2e979f4c525d623991bf5f28ab8b24f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:21.878072Z","signature_b64":"Zj36ngIc1XOYkbzm8uT9aUf4BS8Mlg1bTHMkGux5AzRRz0BO9KzNm3JxJ9wlpSORqAVK2pc03iDjkVzowKPKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3c9a96f660d2db8d27e0a95718f610e2e979f4c525d623991bf5f28ab8b24f2","last_reissued_at":"2026-06-25T00:18:21.877666Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:21.877666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25239","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":"2026-06-25T00:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hinxl73yv+vI2b63a0wun6Xxx5cxH74w+cSyjtyuGhjNnS29aQo2xLGb0nxuQqu9YHFSouLc3c40bnx1ilq4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:44:25.350064Z"},"content_sha256":"8cb9735f70286b0db8cf92e27c7610463d5ccaf7e865aac6f17ffc4737d7a540","schema_version":"1.0","event_id":"sha256:8cb9735f70286b0db8cf92e27c7610463d5ccaf7e865aac6f17ffc4737d7a540"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YPE2S33GBUW3RUT6BKKXDD3BBY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Guanqin Zhang, Yulei Sui","submitted_at":"2026-06-23T23:56:21Z","abstract_excerpt":"Deep neural networks are increasingly deployed in safety-critical domains such as autonomous driving and medical diagnosis, yet their opaque, high-dimensional parameter spaces make it difficult to systematically assess model reliability on unseen inputs. Existing coverage-guided sequential fuzzing frameworks for DNNs inherit a one-input-per-iteration design from traditional software fuzzing and apply uniform perturbation budgets across all input dimensions, limiting both testing throughput (i.e., inputs processed per unit time) and the precision of input-space exploration. We present a new spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25239","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/2606.25239/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":"2026-06-25T00:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JNKrfdWi/ln8vLATALCAo3qIv+S0o3kalk1oLHKlhqP2Rkg/oJCren/c4QOHnEh+QQgFsTaDndhkHsKqXEApDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T10:44:25.350484Z"},"content_sha256":"5ab865e2f78ac2db0fa30467ffad8e109d86510d5deacba6c839f7f76ae6275c","schema_version":"1.0","event_id":"sha256:5ab865e2f78ac2db0fa30467ffad8e109d86510d5deacba6c839f7f76ae6275c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPE2S33GBUW3RUT6BKKXDD3BBY/bundle.json","state_url":"https://pith.science/pith/YPE2S33GBUW3RUT6BKKXDD3BBY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPE2S33GBUW3RUT6BKKXDD3BBY/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":"2026-06-26T10:44:25Z","links":{"resolver":"https://pith.science/pith/YPE2S33GBUW3RUT6BKKXDD3BBY","bundle":"https://pith.science/pith/YPE2S33GBUW3RUT6BKKXDD3BBY/bundle.json","state":"https://pith.science/pith/YPE2S33GBUW3RUT6BKKXDD3BBY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPE2S33GBUW3RUT6BKKXDD3BBY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YPE2S33GBUW3RUT6BKKXDD3BBY","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":"a7fa5f48d114da3d101a96e35cbf8987113e6a8d8944ba9bdafcfec70e4f7f3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-23T23:56:21Z","title_canon_sha256":"912439cb19a10aafbe1416cff8bfabf68e3a49b30a179fe54037e1c8f2e9b080"},"schema_version":"1.0","source":{"id":"2606.25239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25239","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25239v1","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25239","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"YPE2S33GBUW3","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_16","alias_value":"YPE2S33GBUW3RUT6","created_at":"2026-06-25T00:18:21Z"},{"alias_kind":"pith_short_8","alias_value":"YPE2S33G","created_at":"2026-06-25T00:18:21Z"}],"graph_snapshots":[{"event_id":"sha256:5ab865e2f78ac2db0fa30467ffad8e109d86510d5deacba6c839f7f76ae6275c","target":"graph","created_at":"2026-06-25T00:18:21Z","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/2606.25239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks are increasingly deployed in safety-critical domains such as autonomous driving and medical diagnosis, yet their opaque, high-dimensional parameter spaces make it difficult to systematically assess model reliability on unseen inputs. Existing coverage-guided sequential fuzzing frameworks for DNNs inherit a one-input-per-iteration design from traditional software fuzzing and apply uniform perturbation budgets across all input dimensions, limiting both testing throughput (i.e., inputs processed per unit time) and the precision of input-space exploration. We present a new spe","authors_text":"Guanqin Zhang, Yulei Sui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-23T23:56:21Z","title":"Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25239","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":"sha256:8cb9735f70286b0db8cf92e27c7610463d5ccaf7e865aac6f17ffc4737d7a540","target":"record","created_at":"2026-06-25T00:18:21Z","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":"a7fa5f48d114da3d101a96e35cbf8987113e6a8d8944ba9bdafcfec70e4f7f3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-23T23:56:21Z","title_canon_sha256":"912439cb19a10aafbe1416cff8bfabf68e3a49b30a179fe54037e1c8f2e9b080"},"schema_version":"1.0","source":{"id":"2606.25239","kind":"arxiv","version":1}},"canonical_sha256":"c3c9a96f660d2db8d27e0a95718f610e2e979f4c525d623991bf5f28ab8b24f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3c9a96f660d2db8d27e0a95718f610e2e979f4c525d623991bf5f28ab8b24f2","first_computed_at":"2026-06-25T00:18:21.877666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T00:18:21.877666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zj36ngIc1XOYkbzm8uT9aUf4BS8Mlg1bTHMkGux5AzRRz0BO9KzNm3JxJ9wlpSORqAVK2pc03iDjkVzowKPKCw==","signature_status":"signed_v1","signed_at":"2026-06-25T00:18:21.878072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cb9735f70286b0db8cf92e27c7610463d5ccaf7e865aac6f17ffc4737d7a540","sha256:5ab865e2f78ac2db0fa30467ffad8e109d86510d5deacba6c839f7f76ae6275c"],"state_sha256":"d16cd9b9d39f55f367c546271ea6d758923ec583dd651138995eae761470a5b5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/QSHaBZM04RELe3heHXdPFwQM95BJHdHIDyvHowUK80vnSdGj5aisdWbTydBq8ywNGQfkYfvtq5qcFGroSNIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T10:44:25.352532Z","bundle_sha256":"853d1a32100827b270438b74e0afc89a93f8def6f403442059f3d59c4009591c"}}