{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JFM3JVALK5YOKLK2BVAW5ETOVV","short_pith_number":"pith:JFM3JVAL","canonical_record":{"source":{"id":"2506.06765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-07T11:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"958e02d9ba4ed6e89a647bac280105a4f6e86ed24418cd99727b65948c887e23","abstract_canon_sha256":"afe9d0934cca00c8d30d80de07de4f85d9356d60c4918e066e39c0bad65c8e88"},"schema_version":"1.0"},"canonical_sha256":"4959b4d40b5770e52d5a0d416e926ead712c63f8a288ccb2984095f2d7ba9f7d","source":{"kind":"arxiv","id":"2506.06765","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06765","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06765v1","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06765","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"JFM3JVALK5YO","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"JFM3JVALK5YOKLK2","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"JFM3JVAL","created_at":"2026-07-05T11:17:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JFM3JVALK5YOKLK2BVAW5ETOVV","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06765","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-07T11:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"958e02d9ba4ed6e89a647bac280105a4f6e86ed24418cd99727b65948c887e23","abstract_canon_sha256":"afe9d0934cca00c8d30d80de07de4f85d9356d60c4918e066e39c0bad65c8e88"},"schema_version":"1.0"},"canonical_sha256":"4959b4d40b5770e52d5a0d416e926ead712c63f8a288ccb2984095f2d7ba9f7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:55.266876Z","signature_b64":"DdI3Ext9jRiTFbXMuTE5FsFEbiryOgEMV+qNj79ybW7hZ3qoh18FHbN6pUcb6fXrslN7I593VKiGft4dyTlPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4959b4d40b5770e52d5a0d416e926ead712c63f8a288ccb2984095f2d7ba9f7d","last_reissued_at":"2026-07-05T11:17:55.266521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:55.266521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06765","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":"2026-07-05T11:17:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7nsiNP7DG6iYFKH5DJwA2ft7mPo4PZDT6x4vsfOvGu1IxldiUVT50zFNKbM8rfx9osm9+dan32afpEc92uy5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:53:36.861686Z"},"content_sha256":"b915671887bfbb4aea57363ab793c615c1a84d1733baf1c792bca89330f84d7c","schema_version":"1.0","event_id":"sha256:b915671887bfbb4aea57363ab793c615c1a84d1733baf1c792bca89330f84d7c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JFM3JVALK5YOKLK2BVAW5ETOVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Employing Discrete Fourier Transform in Representational Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Edmondo Trentin, Raoof HojatJalali","submitted_at":"2025-06-07T11:17:24Z","abstract_excerpt":"Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using autoencoders to extract latent representations at the network's compression point. These representations are valuable because they retain essential information necessary for reconstructing the original input from the compressed latent space. In this paper, we propose an alternative learning objective. Instead of using the raw input as the reconstruction target, we empl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06765","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/2506.06765/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":"2026-07-05T11:17:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"29NyD9g+DjbLTOY8RT1BK/YjQxuVKwkse7anOIEgLHLl/U17qqTmnuc1Q8tjM2spjIPPILkBBB/NNcTsi7G3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:53:36.862181Z"},"content_sha256":"b8c2b48a6246db95e8ce7a6f951c7532a874252c7cdea2aa91a7a4c426755145","schema_version":"1.0","event_id":"sha256:b8c2b48a6246db95e8ce7a6f951c7532a874252c7cdea2aa91a7a4c426755145"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JFM3JVALK5YOKLK2BVAW5ETOVV/bundle.json","state_url":"https://pith.science/pith/JFM3JVALK5YOKLK2BVAW5ETOVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JFM3JVALK5YOKLK2BVAW5ETOVV/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":"2026-08-08T22:53:36Z","links":{"resolver":"https://pith.science/pith/JFM3JVALK5YOKLK2BVAW5ETOVV","bundle":"https://pith.science/pith/JFM3JVALK5YOKLK2BVAW5ETOVV/bundle.json","state":"https://pith.science/pith/JFM3JVALK5YOKLK2BVAW5ETOVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JFM3JVALK5YOKLK2BVAW5ETOVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JFM3JVALK5YOKLK2BVAW5ETOVV","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":"afe9d0934cca00c8d30d80de07de4f85d9356d60c4918e066e39c0bad65c8e88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-07T11:17:24Z","title_canon_sha256":"958e02d9ba4ed6e89a647bac280105a4f6e86ed24418cd99727b65948c887e23"},"schema_version":"1.0","source":{"id":"2506.06765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06765","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06765v1","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06765","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"pith_short_12","alias_value":"JFM3JVALK5YO","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"pith_short_16","alias_value":"JFM3JVALK5YOKLK2","created_at":"2026-07-05T11:17:55Z"},{"alias_kind":"pith_short_8","alias_value":"JFM3JVAL","created_at":"2026-07-05T11:17:55Z"}],"graph_snapshots":[{"event_id":"sha256:b8c2b48a6246db95e8ce7a6f951c7532a874252c7cdea2aa91a7a4c426755145","target":"graph","created_at":"2026-07-05T11:17:55Z","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/2506.06765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using autoencoders to extract latent representations at the network's compression point. These representations are valuable because they retain essential information necessary for reconstructing the original input from the compressed latent space. In this paper, we propose an alternative learning objective. Instead of using the raw input as the reconstruction target, we empl","authors_text":"Edmondo Trentin, Raoof HojatJalali","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-07T11:17:24Z","title":"Employing Discrete Fourier Transform in Representational Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06765","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:b915671887bfbb4aea57363ab793c615c1a84d1733baf1c792bca89330f84d7c","target":"record","created_at":"2026-07-05T11:17:55Z","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":"afe9d0934cca00c8d30d80de07de4f85d9356d60c4918e066e39c0bad65c8e88","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-07T11:17:24Z","title_canon_sha256":"958e02d9ba4ed6e89a647bac280105a4f6e86ed24418cd99727b65948c887e23"},"schema_version":"1.0","source":{"id":"2506.06765","kind":"arxiv","version":1}},"canonical_sha256":"4959b4d40b5770e52d5a0d416e926ead712c63f8a288ccb2984095f2d7ba9f7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4959b4d40b5770e52d5a0d416e926ead712c63f8a288ccb2984095f2d7ba9f7d","first_computed_at":"2026-07-05T11:17:55.266521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:55.266521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DdI3Ext9jRiTFbXMuTE5FsFEbiryOgEMV+qNj79ybW7hZ3qoh18FHbN6pUcb6fXrslN7I593VKiGft4dyTlPDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:55.266876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b915671887bfbb4aea57363ab793c615c1a84d1733baf1c792bca89330f84d7c","sha256:b8c2b48a6246db95e8ce7a6f951c7532a874252c7cdea2aa91a7a4c426755145"],"state_sha256":"e9951708de3549d2d2e664732a109f8b0f8a846e1c9551ac615a4303f01ca606"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O/Y6zOYhfHSHyweQ0OAEo635paYFH/VFicW57JWbZFy1OxifPNg0xm4JEwoRYZsOLLWU5TjRdkj0yKntpdvCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:53:36.866500Z","bundle_sha256":"d7c6c9bc9f6b2baa5e0be490546ab4ba8eea03ff10db74950d3153cf3880d972"}}