{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OPY4AHA2XQMXLJNCF2TOFNGBYA","short_pith_number":"pith:OPY4AHA2","canonical_record":{"source":{"id":"2506.19734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T15:53:18Z","cross_cats_sorted":[],"title_canon_sha256":"d51954dc2b70e8b2a143db1191f124f417e2b7a93ca55505e9a90d220d27df93","abstract_canon_sha256":"2c95b94cb387069396aca39ad91e6887dce2799764e74665163028234dd022f2"},"schema_version":"1.0"},"canonical_sha256":"73f1c01c1abc1975a5a22ea6e2b4c1c00da609ad24366f0a98500d89f86a3092","source":{"kind":"arxiv","id":"2506.19734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19734","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19734v1","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19734","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"pith_short_12","alias_value":"OPY4AHA2XQMX","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"OPY4AHA2XQMXLJNC","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"OPY4AHA2","created_at":"2026-07-05T11:26:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OPY4AHA2XQMXLJNCF2TOFNGBYA","target":"record","payload":{"canonical_record":{"source":{"id":"2506.19734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T15:53:18Z","cross_cats_sorted":[],"title_canon_sha256":"d51954dc2b70e8b2a143db1191f124f417e2b7a93ca55505e9a90d220d27df93","abstract_canon_sha256":"2c95b94cb387069396aca39ad91e6887dce2799764e74665163028234dd022f2"},"schema_version":"1.0"},"canonical_sha256":"73f1c01c1abc1975a5a22ea6e2b4c1c00da609ad24366f0a98500d89f86a3092","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:37.795914Z","signature_b64":"UAeOl/kd7LSY5H1R5zNajnetd2nHa/98rYwgOWbHiOFbHfgKfHNid/Sh7pgbjK/hqyT1Q8QGcdifQOfEsRFnDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73f1c01c1abc1975a5a22ea6e2b4c1c00da609ad24366f0a98500d89f86a3092","last_reissued_at":"2026-07-05T11:26:37.795376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:37.795376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.19734","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":"2026-07-05T11:26:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"siVRuynOK9KdHuuT55pdbrUSRmwHktgiFaLqxKVf8OTqfIYQdu0ov+Ul74QvnmkT5szCF5PIMUZJ5QpLU5EeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:49:44.000124Z"},"content_sha256":"676afa9bd713d50c65884938f1f16d7028067f605b1e5e9f159ec338d5f0c437","schema_version":"1.0","event_id":"sha256:676afa9bd713d50c65884938f1f16d7028067f605b1e5e9f159ec338d5f0c437"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OPY4AHA2XQMXLJNCF2TOFNGBYA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ben Keslaki","submitted_at":"2025-06-24T15:53:18Z","abstract_excerpt":"Modern deep learning architectures excel at optimization, but only after the data has entered the network. The true bottleneck lies in preparing the right input: minimal, salient, and structured in a way that reflects the essential patterns of the data. We propose DRIFT (Data Reduction via Informative Feature Transformation), a novel preprocessing technique inspired by vibrational analysis in physical systems, to identify and extract the most resonant modes of input data prior to training. Unlike traditional models that attempt to learn amidst both signal and noise, DRIFT mimics physics percep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19734","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/2506.19734/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":"2026-07-05T11:26:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3djqYWai198ybMdQdp5lOFfKBVqokQyr/FkvQ0QbSMM86BEgmZ3kK/fs7Ctempz/uwMXO2Nn7FQpTRnj/jJxCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:49:44.000638Z"},"content_sha256":"5e7bf8dff4b5d9d613c8c3f9d74a9eb59115152f0ae8f9c20219026de97984a4","schema_version":"1.0","event_id":"sha256:5e7bf8dff4b5d9d613c8c3f9d74a9eb59115152f0ae8f9c20219026de97984a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA/bundle.json","state_url":"https://pith.science/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA/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":"2026-08-22T08:49:44Z","links":{"resolver":"https://pith.science/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA","bundle":"https://pith.science/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA/bundle.json","state":"https://pith.science/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OPY4AHA2XQMXLJNCF2TOFNGBYA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OPY4AHA2XQMXLJNCF2TOFNGBYA","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":"2c95b94cb387069396aca39ad91e6887dce2799764e74665163028234dd022f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T15:53:18Z","title_canon_sha256":"d51954dc2b70e8b2a143db1191f124f417e2b7a93ca55505e9a90d220d27df93"},"schema_version":"1.0","source":{"id":"2506.19734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19734","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19734v1","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19734","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"pith_short_12","alias_value":"OPY4AHA2XQMX","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"pith_short_16","alias_value":"OPY4AHA2XQMXLJNC","created_at":"2026-07-05T11:26:37Z"},{"alias_kind":"pith_short_8","alias_value":"OPY4AHA2","created_at":"2026-07-05T11:26:37Z"}],"graph_snapshots":[{"event_id":"sha256:5e7bf8dff4b5d9d613c8c3f9d74a9eb59115152f0ae8f9c20219026de97984a4","target":"graph","created_at":"2026-07-05T11:26:37Z","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/2506.19734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern deep learning architectures excel at optimization, but only after the data has entered the network. The true bottleneck lies in preparing the right input: minimal, salient, and structured in a way that reflects the essential patterns of the data. We propose DRIFT (Data Reduction via Informative Feature Transformation), a novel preprocessing technique inspired by vibrational analysis in physical systems, to identify and extract the most resonant modes of input data prior to training. Unlike traditional models that attempt to learn amidst both signal and noise, DRIFT mimics physics percep","authors_text":"Ben Keslaki","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T15:53:18Z","title":"DRIFT: Data Reduction via Informative Feature Transformation- Generalization Begins Before Deep Learning starts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19734","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":"sha256:676afa9bd713d50c65884938f1f16d7028067f605b1e5e9f159ec338d5f0c437","target":"record","created_at":"2026-07-05T11:26:37Z","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":"2c95b94cb387069396aca39ad91e6887dce2799764e74665163028234dd022f2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T15:53:18Z","title_canon_sha256":"d51954dc2b70e8b2a143db1191f124f417e2b7a93ca55505e9a90d220d27df93"},"schema_version":"1.0","source":{"id":"2506.19734","kind":"arxiv","version":1}},"canonical_sha256":"73f1c01c1abc1975a5a22ea6e2b4c1c00da609ad24366f0a98500d89f86a3092","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73f1c01c1abc1975a5a22ea6e2b4c1c00da609ad24366f0a98500d89f86a3092","first_computed_at":"2026-07-05T11:26:37.795376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:37.795376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UAeOl/kd7LSY5H1R5zNajnetd2nHa/98rYwgOWbHiOFbHfgKfHNid/Sh7pgbjK/hqyT1Q8QGcdifQOfEsRFnDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:37.795914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:676afa9bd713d50c65884938f1f16d7028067f605b1e5e9f159ec338d5f0c437","sha256:5e7bf8dff4b5d9d613c8c3f9d74a9eb59115152f0ae8f9c20219026de97984a4"],"state_sha256":"6d07b7261b2aca1ddec05d60b30a30aa14a00a0cafdebe7609ae5a17c69f7ef8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Of0WvplEtX+qLIp06FaFkazuWu2DtUneBlEhbdDNfk1T+2tzFNPg3C1yIhvNi7WMlH80blGX6ld1o3t+MW9lCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:49:44.004481Z","bundle_sha256":"e0c351a9ee37cef625fe3ea020a8cc5fdfc5bc0fc86d7def96f8bab00cabacc7"}}