{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3FUWOAMXYZSSNZLADU2LMQY436","short_pith_number":"pith:3FUWOAMX","canonical_record":{"source":{"id":"2606.04171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T19:35:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5ea0646352bba31c3a7cc5a48fdf29f154ba81b6c11aeacd9ab381160eb48fce","abstract_canon_sha256":"b5f1f11e2981964d29ccec0fe289a5d689e93c451549ce2727e59e6eacc81970"},"schema_version":"1.0"},"canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","source":{"kind":"arxiv","id":"2606.04171","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04171","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04171v1","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04171","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"3FUWOAMXYZSS","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"3FUWOAMXYZSSNZLA","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"3FUWOAMX","created_at":"2026-06-04T01:08:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3FUWOAMXYZSSNZLADU2LMQY436","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T19:35:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5ea0646352bba31c3a7cc5a48fdf29f154ba81b6c11aeacd9ab381160eb48fce","abstract_canon_sha256":"b5f1f11e2981964d29ccec0fe289a5d689e93c451549ce2727e59e6eacc81970"},"schema_version":"1.0"},"canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:18.792768Z","signature_b64":"c5pAQEFaMbEFv+7z9YfH+dVlkXIyAJpsAg8EtMMIxj8CN4icvXNKiassMQr330eOPTBRywUc/5ZZgw6jSb3UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","last_reissued_at":"2026-06-04T01:08:18.791716Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:18.791716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04171","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":"2026-06-04T01:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0Y1L4Min+WXSjZ9oCfYH7gd/IiRJB2Nr584SyfMUwka6D59FWU9a0MozO8XQuGMBe4suriZn+KtKBPOV9jCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:53:13.509520Z"},"content_sha256":"4fced587879db752b9b4fe52552a0ddf92c37f8e1cc46783bc02e44895729e3e","schema_version":"1.0","event_id":"sha256:4fced587879db752b9b4fe52552a0ddf92c37f8e1cc46783bc02e44895729e3e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3FUWOAMXYZSSNZLADU2LMQY436","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael J. Bommarito II","submitted_at":"2026-06-02T19:35:44Z","abstract_excerpt":"File-type classification underlies many workflows like malware triage, forensic carving, packet inspection, and storage indexing. Learned systems such as Google's Magika assume whole-file access at a known offset, so they break on the inputs many of these tasks actually produce, like a single packet payload, a header-less carved fragment, a random disk block, or a chunked upload. We introduce MimeLens, a family of small BERT-style encoders pretrained on binary content from windows sampled at a uniformly random offset within each file, with no privileged head-of-file position, in standard- and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04171","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/2606.04171/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":"2026-06-04T01:08:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5z2Lrjq+Pbzdpl5qWosqbhtkLoV27EWIhoibFIVOpBPHchwUzFSAwJKpHoi9/hScjNW7f5nQgfK94WgI2C/DDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T14:53:13.509900Z"},"content_sha256":"9e35c93326dd55ccc6617132ab6f64d52088fd2765cbe78418d16c8d4808d7ea","schema_version":"1.0","event_id":"sha256:9e35c93326dd55ccc6617132ab6f64d52088fd2765cbe78418d16c8d4808d7ea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/bundle.json","state_url":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FUWOAMXYZSSNZLADU2LMQY436/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":"2026-06-09T14:53:13Z","links":{"resolver":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436","bundle":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/bundle.json","state":"https://pith.science/pith/3FUWOAMXYZSSNZLADU2LMQY436/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FUWOAMXYZSSNZLADU2LMQY436/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3FUWOAMXYZSSNZLADU2LMQY436","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":"b5f1f11e2981964d29ccec0fe289a5d689e93c451549ce2727e59e6eacc81970","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T19:35:44Z","title_canon_sha256":"5ea0646352bba31c3a7cc5a48fdf29f154ba81b6c11aeacd9ab381160eb48fce"},"schema_version":"1.0","source":{"id":"2606.04171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04171","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04171v1","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04171","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"3FUWOAMXYZSS","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"3FUWOAMXYZSSNZLA","created_at":"2026-06-04T01:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"3FUWOAMX","created_at":"2026-06-04T01:08:18Z"}],"graph_snapshots":[{"event_id":"sha256:9e35c93326dd55ccc6617132ab6f64d52088fd2765cbe78418d16c8d4808d7ea","target":"graph","created_at":"2026-06-04T01:08:18Z","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/2606.04171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"File-type classification underlies many workflows like malware triage, forensic carving, packet inspection, and storage indexing. Learned systems such as Google's Magika assume whole-file access at a known offset, so they break on the inputs many of these tasks actually produce, like a single packet payload, a header-less carved fragment, a random disk block, or a chunked upload. We introduce MimeLens, a family of small BERT-style encoders pretrained on binary content from windows sampled at a uniformly random offset within each file, with no privileged head-of-file position, in standard- and ","authors_text":"Michael J. Bommarito II","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T19:35:44Z","title":"MimeLens: Position-Agnostic Content-Type Detection for Binary Fragments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04171","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":"sha256:4fced587879db752b9b4fe52552a0ddf92c37f8e1cc46783bc02e44895729e3e","target":"record","created_at":"2026-06-04T01:08:18Z","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":"b5f1f11e2981964d29ccec0fe289a5d689e93c451549ce2727e59e6eacc81970","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-02T19:35:44Z","title_canon_sha256":"5ea0646352bba31c3a7cc5a48fdf29f154ba81b6c11aeacd9ab381160eb48fce"},"schema_version":"1.0","source":{"id":"2606.04171","kind":"arxiv","version":1}},"canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d969670197c66526e5601d34b6431cdf9b9553079b974a960fca205876139633","first_computed_at":"2026-06-04T01:08:18.791716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:18.791716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c5pAQEFaMbEFv+7z9YfH+dVlkXIyAJpsAg8EtMMIxj8CN4icvXNKiassMQr330eOPTBRywUc/5ZZgw6jSb3UAQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:18.792768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fced587879db752b9b4fe52552a0ddf92c37f8e1cc46783bc02e44895729e3e","sha256:9e35c93326dd55ccc6617132ab6f64d52088fd2765cbe78418d16c8d4808d7ea"],"state_sha256":"b42dff7c0cce28f9149edf8219a247382c401e8a4ff4a215817f0e54cb8c0844"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TuJJo3+RELk2PZL2pnDR+mLEwXkYKqrpIXQlKHJyIsDJ2K4P6OjqNj1BXfX0czBYC7ngo4RFt2zv+FfXWDjoDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T14:53:13.511918Z","bundle_sha256":"beb3c2de0f061e5da9b694907ad1ec65ee453319306d3f02b37a924488154bd6"}}