{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VSWEP6CPXQWXQ76K4MDT2RVFAQ","short_pith_number":"pith:VSWEP6CP","canonical_record":{"source":{"id":"2602.14896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T16:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"31a8135bfdef4bbdefcf87594f73f87863a2e9fe9783bf137f8edb432340cd32","abstract_canon_sha256":"a90c7a5291d29cd005bab13ff07c3fb202036361ac7db2195dcd7be34fc1da2b"},"schema_version":"1.0"},"canonical_sha256":"acac47f84fbc2d787fcae3073d46a50422655a621e953f8038313e33a696f925","source":{"kind":"arxiv","id":"2602.14896","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14896","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14896v2","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14896","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"VSWEP6CPXQWX","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"VSWEP6CPXQWXQ76K","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"VSWEP6CP","created_at":"2026-05-20T00:00:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VSWEP6CPXQWXQ76K4MDT2RVFAQ","target":"record","payload":{"canonical_record":{"source":{"id":"2602.14896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T16:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"31a8135bfdef4bbdefcf87594f73f87863a2e9fe9783bf137f8edb432340cd32","abstract_canon_sha256":"a90c7a5291d29cd005bab13ff07c3fb202036361ac7db2195dcd7be34fc1da2b"},"schema_version":"1.0"},"canonical_sha256":"acac47f84fbc2d787fcae3073d46a50422655a621e953f8038313e33a696f925","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:34.628308Z","signature_b64":"oY/gnN/ia+l4hyxojw+qcDxkZ76hHxlzE1OUcLXMNPGJW4OU+ufUOXKgIndYGig38bYN0ZTIaVXvglN6MQzhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acac47f84fbc2d787fcae3073d46a50422655a621e953f8038313e33a696f925","last_reissued_at":"2026-05-20T00:00:34.627773Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:34.627773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.14896","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6aWTLvYB01RaZ5jyoj8fqB6rpk8ZeaPAEFcBTZwbAx92Z/bPuhe+dqUhU0UqIw4foNSS2aPBNEpqCC1IrnOIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T18:44:37.985059Z"},"content_sha256":"6262b3214f6f9843b58035757206b9c7cbe53f116262bd1d475dbedd6a424c20","schema_version":"1.0","event_id":"sha256:6262b3214f6f9843b58035757206b9c7cbe53f116262bd1d475dbedd6a424c20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VSWEP6CPXQWXQ76K4MDT2RVFAQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erik B Dam, Jonathan Wensh{\\o}j, Pedram Bakhtiarifard, Raghavendra Selvan, Tong Chen","submitted_at":"2026-02-16T16:30:38Z","abstract_excerpt":"Large-scale deep learning models are well-suited for compression. Across a variety of tasks, methods like pruning, quantization, and knowledge distillation have been used to achieve massive reductions in model parameters with only marginal performance drops. This raises the central question: *Why are deep neural networks suited for compression?* In this work, we take up the perspective of algorithmic complexity to explain this behavior. We hypothesize that the parameters of trained models have more structure and, hence, exhibit lower algorithmic complexity compared to the weights at (random) i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14896","kind":"arxiv","version":2},"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/2602.14896/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":"2026-05-20T00:00:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZDbXETXtLXzjjSUzCoMxce5gErYKyO9rWEg4UV5AGE2FwFCZ7lW9O156FN/GRYy6ui7iMynzuQViYFFGILeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T18:44:37.985454Z"},"content_sha256":"7c269db8d0d5f3d72983e5a94dbb274b054c604bdbdffde4e6500d6a3bc73477","schema_version":"1.0","event_id":"sha256:7c269db8d0d5f3d72983e5a94dbb274b054c604bdbdffde4e6500d6a3bc73477"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ/bundle.json","state_url":"https://pith.science/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ/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":"2026-05-22T18:44:37Z","links":{"resolver":"https://pith.science/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ","bundle":"https://pith.science/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ/bundle.json","state":"https://pith.science/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VSWEP6CPXQWXQ76K4MDT2RVFAQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VSWEP6CPXQWXQ76K4MDT2RVFAQ","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":"a90c7a5291d29cd005bab13ff07c3fb202036361ac7db2195dcd7be34fc1da2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T16:30:38Z","title_canon_sha256":"31a8135bfdef4bbdefcf87594f73f87863a2e9fe9783bf137f8edb432340cd32"},"schema_version":"1.0","source":{"id":"2602.14896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.14896","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.14896v2","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14896","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_12","alias_value":"VSWEP6CPXQWX","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_16","alias_value":"VSWEP6CPXQWXQ76K","created_at":"2026-05-20T00:00:34Z"},{"alias_kind":"pith_short_8","alias_value":"VSWEP6CP","created_at":"2026-05-20T00:00:34Z"}],"graph_snapshots":[{"event_id":"sha256:7c269db8d0d5f3d72983e5a94dbb274b054c604bdbdffde4e6500d6a3bc73477","target":"graph","created_at":"2026-05-20T00:00:34Z","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/2602.14896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale deep learning models are well-suited for compression. Across a variety of tasks, methods like pruning, quantization, and knowledge distillation have been used to achieve massive reductions in model parameters with only marginal performance drops. This raises the central question: *Why are deep neural networks suited for compression?* In this work, we take up the perspective of algorithmic complexity to explain this behavior. We hypothesize that the parameters of trained models have more structure and, hence, exhibit lower algorithmic complexity compared to the weights at (random) i","authors_text":"Erik B Dam, Jonathan Wensh{\\o}j, Pedram Bakhtiarifard, Raghavendra Selvan, Tong Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T16:30:38Z","title":"Algorithmic Simplification of Neural Networks with Mosaic-of-Motifs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14896","kind":"arxiv","version":2},"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":"sha256:6262b3214f6f9843b58035757206b9c7cbe53f116262bd1d475dbedd6a424c20","target":"record","created_at":"2026-05-20T00:00:34Z","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":"a90c7a5291d29cd005bab13ff07c3fb202036361ac7db2195dcd7be34fc1da2b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-16T16:30:38Z","title_canon_sha256":"31a8135bfdef4bbdefcf87594f73f87863a2e9fe9783bf137f8edb432340cd32"},"schema_version":"1.0","source":{"id":"2602.14896","kind":"arxiv","version":2}},"canonical_sha256":"acac47f84fbc2d787fcae3073d46a50422655a621e953f8038313e33a696f925","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acac47f84fbc2d787fcae3073d46a50422655a621e953f8038313e33a696f925","first_computed_at":"2026-05-20T00:00:34.627773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:34.627773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oY/gnN/ia+l4hyxojw+qcDxkZ76hHxlzE1OUcLXMNPGJW4OU+ufUOXKgIndYGig38bYN0ZTIaVXvglN6MQzhDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:34.628308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.14896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6262b3214f6f9843b58035757206b9c7cbe53f116262bd1d475dbedd6a424c20","sha256:7c269db8d0d5f3d72983e5a94dbb274b054c604bdbdffde4e6500d6a3bc73477"],"state_sha256":"6e1b779614a2dd3b85657fe105d687568151d8bc131e054719af04ead22480be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O0D7RKZOy6VdapScodmEPW3e4nEQVlB7KgBwfN25vXCBcnXd89ubCCLTQMKTqxf11IklGvkrYMM2H6IGmaCxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T18:44:37.987749Z","bundle_sha256":"f8225fc89f2852af53f716a6273495dd3fd9ceda5170655244b2193126c6f387"}}