{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FXGAQ32Q2N2MDFWGNCKUUUR6KV","short_pith_number":"pith:FXGAQ32Q","canonical_record":{"source":{"id":"2511.07329","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T17:31:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b8c460672a7fecdcd0ae888ae9269b98577eb843d0444b29ef8680078a001531","abstract_canon_sha256":"5ff035973712a018bdcbf26a2451f9835912eb8e105b12c8c7c5f07a10275e95"},"schema_version":"1.0"},"canonical_sha256":"2dcc086f50d374c196c668954a523e556221e5bc988a1e849182583f4f56c123","source":{"kind":"arxiv","id":"2511.07329","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.07329","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2511.07329v4","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07329","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"FXGAQ32Q2N2M","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"FXGAQ32Q2N2MDFWG","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"FXGAQ32Q","created_at":"2026-05-20T00:02:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FXGAQ32Q2N2MDFWGNCKUUUR6KV","target":"record","payload":{"canonical_record":{"source":{"id":"2511.07329","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T17:31:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b8c460672a7fecdcd0ae888ae9269b98577eb843d0444b29ef8680078a001531","abstract_canon_sha256":"5ff035973712a018bdcbf26a2451f9835912eb8e105b12c8c7c5f07a10275e95"},"schema_version":"1.0"},"canonical_sha256":"2dcc086f50d374c196c668954a523e556221e5bc988a1e849182583f4f56c123","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:58.381573Z","signature_b64":"wKo1nULZj39z+gIPDXCR/D+w7u/r0zNSG+UgKV/8GjQX5afKUPBjGGjwQM0VnDQJgzm5UQPe0M/DpjDeF0IPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2dcc086f50d374c196c668954a523e556221e5bc988a1e849182583f4f56c123","last_reissued_at":"2026-05-20T00:02:58.380810Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:58.380810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2511.07329","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNsd+gM7cIyoFReIST+HiuNhVYRaRBnwux5FVARBlQ9ne1r45A2bki9Wf5DLKmZP9fBt2Skd+v2JS45i92bHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T18:47:22.467854Z"},"content_sha256":"e36e87636baf7e1c59d582afadc9297f9c5c45c02f85589a00746040333c81ab","schema_version":"1.0","event_id":"sha256:e36e87636baf7e1c59d582afadc9297f9c5c45c02f85589a00746040333c81ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FXGAQ32Q2N2MDFWGNCKUUUR6KV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Fractal templates generate over 1,200 neural network variants that maintain strong performance on CIFAR-10 while remaining computationally efficient.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dmitry Ignatov, Radu Timofte, Yash Mittal","submitted_at":"2025-11-10T17:31:39Z","abstract_excerpt":"This paper proposes FractalNet, a framework based on fractal design principles that automatically generates and evaluates convolutional neural network (CNN) architectures using recursive template patterns. Rather than relying on computationally expensive Neural Architecture Search (NAS) methods, the framework explores a structured architecture space defined by recursive fractal templates that systematically vary key parameters such as fractal depth, column width, and layer configurations. The framework consists of three core components: a generator that produces candidate architectures via con"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The outcomes show that fractal-based architectures are capable of strong performance and are computationally efficient.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That recursive fractal templates combined with layer permutations will reliably produce deeper and wider models that maintain strong performance without additional regularization or longer training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Fractal templates enable systematic creation of more than 1,200 neural network variants that show strong performance and computational efficiency when trained on CIFAR-10 for five epochs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Fractal templates generate over 1,200 neural network variants that maintain strong performance on CIFAR-10 while remaining computationally efficient.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"142621fa29648eb2cb599001f6c63dc6e3f059bd3a10da22504816374985328a"},"source":{"id":"2511.07329","kind":"arxiv","version":4},"verdict":{"id":"1341fd5b-2aee-4b04-8953-91573768e1cb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T23:19:17.278943Z","strongest_claim":"The outcomes show that fractal-based architectures are capable of strong performance and are computationally efficient.","one_line_summary":"Fractal templates enable systematic creation of more than 1,200 neural network variants that show strong performance and computational efficiency when trained on CIFAR-10 for five epochs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That recursive fractal templates combined with layer permutations will reliably produce deeper and wider models that maintain strong performance without additional regularization or longer training.","pith_extraction_headline":"Fractal templates generate over 1,200 neural network variants that maintain strong performance on CIFAR-10 while remaining computationally efficient."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2511.07329/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":"1341fd5b-2aee-4b04-8953-91573768e1cb"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"auRqStsysFItNIpnqoMwAT1Fuy0d911uSliitA7p0CxyKHGRR/RHmqCYKCxx7Q6Wo0fW7DZM4OWgbQpaTI8jDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T18:47:22.468347Z"},"content_sha256":"9004c495d3d354d6c020ca1919045cb6519b2ab5c9bc57b3ee4eb38f9ad92f79","schema_version":"1.0","event_id":"sha256:9004c495d3d354d6c020ca1919045cb6519b2ab5c9bc57b3ee4eb38f9ad92f79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV/bundle.json","state_url":"https://pith.science/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV/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":"2026-06-02T18:47:22Z","links":{"resolver":"https://pith.science/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV","bundle":"https://pith.science/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV/bundle.json","state":"https://pith.science/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FXGAQ32Q2N2MDFWGNCKUUUR6KV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FXGAQ32Q2N2MDFWGNCKUUUR6KV","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":"5ff035973712a018bdcbf26a2451f9835912eb8e105b12c8c7c5f07a10275e95","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T17:31:39Z","title_canon_sha256":"b8c460672a7fecdcd0ae888ae9269b98577eb843d0444b29ef8680078a001531"},"schema_version":"1.0","source":{"id":"2511.07329","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.07329","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"arxiv_version","alias_value":"2511.07329v4","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07329","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"pith_short_12","alias_value":"FXGAQ32Q2N2M","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"pith_short_16","alias_value":"FXGAQ32Q2N2MDFWG","created_at":"2026-05-20T00:02:58Z"},{"alias_kind":"pith_short_8","alias_value":"FXGAQ32Q","created_at":"2026-05-20T00:02:58Z"}],"graph_snapshots":[{"event_id":"sha256:9004c495d3d354d6c020ca1919045cb6519b2ab5c9bc57b3ee4eb38f9ad92f79","target":"graph","created_at":"2026-05-20T00:02:58Z","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":"The outcomes show that fractal-based architectures are capable of strong performance and are computationally efficient."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That recursive fractal templates combined with layer permutations will reliably produce deeper and wider models that maintain strong performance without additional regularization or longer training."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Fractal templates enable systematic creation of more than 1,200 neural network variants that show strong performance and computational efficiency when trained on CIFAR-10 for five epochs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Fractal templates generate over 1,200 neural network variants that maintain strong performance on CIFAR-10 while remaining computationally efficient."}],"snapshot_sha256":"142621fa29648eb2cb599001f6c63dc6e3f059bd3a10da22504816374985328a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2511.07329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes FractalNet, a framework based on fractal design principles that automatically generates and evaluates convolutional neural network (CNN) architectures using recursive template patterns. Rather than relying on computationally expensive Neural Architecture Search (NAS) methods, the framework explores a structured architecture space defined by recursive fractal templates that systematically vary key parameters such as fractal depth, column width, and layer configurations. The framework consists of three core components: a generator that produces candidate architectures via con","authors_text":"Dmitry Ignatov, Radu Timofte, Yash Mittal","cross_cats":["cs.CV"],"headline":"Fractal templates generate over 1,200 neural network variants that maintain strong performance on CIFAR-10 while remaining computationally efficient.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T17:31:39Z","title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07329","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-17T23:19:17.278943Z","id":"1341fd5b-2aee-4b04-8953-91573768e1cb","model_set":{"reader":"grok-4.3"},"one_line_summary":"Fractal templates enable systematic creation of more than 1,200 neural network variants that show strong performance and computational efficiency when trained on CIFAR-10 for five epochs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Fractal templates generate over 1,200 neural network variants that maintain strong performance on CIFAR-10 while remaining computationally efficient.","strongest_claim":"The outcomes show that fractal-based architectures are capable of strong performance and are computationally efficient.","weakest_assumption":"That recursive fractal templates combined with layer permutations will reliably produce deeper and wider models that maintain strong performance without additional regularization or longer training."}},"verdict_id":"1341fd5b-2aee-4b04-8953-91573768e1cb"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e36e87636baf7e1c59d582afadc9297f9c5c45c02f85589a00746040333c81ab","target":"record","created_at":"2026-05-20T00:02:58Z","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":"5ff035973712a018bdcbf26a2451f9835912eb8e105b12c8c7c5f07a10275e95","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-11-10T17:31:39Z","title_canon_sha256":"b8c460672a7fecdcd0ae888ae9269b98577eb843d0444b29ef8680078a001531"},"schema_version":"1.0","source":{"id":"2511.07329","kind":"arxiv","version":4}},"canonical_sha256":"2dcc086f50d374c196c668954a523e556221e5bc988a1e849182583f4f56c123","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dcc086f50d374c196c668954a523e556221e5bc988a1e849182583f4f56c123","first_computed_at":"2026-05-20T00:02:58.380810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:58.380810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wKo1nULZj39z+gIPDXCR/D+w7u/r0zNSG+UgKV/8GjQX5afKUPBjGGjwQM0VnDQJgzm5UQPe0M/DpjDeF0IPCQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:58.381573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.07329","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e36e87636baf7e1c59d582afadc9297f9c5c45c02f85589a00746040333c81ab","sha256:9004c495d3d354d6c020ca1919045cb6519b2ab5c9bc57b3ee4eb38f9ad92f79"],"state_sha256":"c527b4ac2291d4a76621afb6fbcbadec36acc54cabaccf4b002f3f01c96b9ed8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T8w8eAsWTw2SeEM2BmAbCxy4kKIWuaI4+BhUquMELLumRgK0/TzercvkLZGyN92u56FpribVR34k0ISWLDe0CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T18:47:22.470752Z","bundle_sha256":"a16e8e5866b5c6a0974e606393d56c37cb0c22e5aacf9389879240fea0b56d05"}}