{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EL6RNSIFM3BECRVVEHRGEEUC7L","short_pith_number":"pith:EL6RNSIF","canonical_record":{"source":{"id":"2607.21366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T14:31:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fd7e8b7a30e621a5cd6cbe99919c964ef203df13f1b09f51df6c9c3778efc3c3","abstract_canon_sha256":"f9c75ff2764fccb66ee6757e9c40e5e06da8683cdfff3b2691af0db29d26f43f"},"schema_version":"1.0"},"canonical_sha256":"22fd16c90566c24146b521e2621282fad2e4ea7313312625a2fac2c516a79401","source":{"kind":"arxiv","id":"2607.21366","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21366","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21366v1","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21366","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"EL6RNSIFM3BE","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"EL6RNSIFM3BECRVV","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"EL6RNSIF","created_at":"2026-07-24T01:24:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EL6RNSIFM3BECRVVEHRGEEUC7L","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21366","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T14:31:16Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"fd7e8b7a30e621a5cd6cbe99919c964ef203df13f1b09f51df6c9c3778efc3c3","abstract_canon_sha256":"f9c75ff2764fccb66ee6757e9c40e5e06da8683cdfff3b2691af0db29d26f43f"},"schema_version":"1.0"},"canonical_sha256":"22fd16c90566c24146b521e2621282fad2e4ea7313312625a2fac2c516a79401","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:28.695372Z","signature_b64":"+EwjJ1wbB4wIvdqtyKK/TBdlKSR6f8aYAfcpJtjKZOSiUH7515aAvYooxsrBH1wVtokdwSpsfztQ0VoabD2hBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22fd16c90566c24146b521e2621282fad2e4ea7313312625a2fac2c516a79401","last_reissued_at":"2026-07-24T01:24:28.694478Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:28.694478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21366","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":"2026-07-24T01:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pz41emHR1BuE2eTo5gPNDz+gxXjDZ9F/MCJ9/pcs4o8jq+clwL/X0OzViHvIoVNbWSsOKB80wwWClA/2IV9uAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:02:52.393344Z"},"content_sha256":"3ffbad50bb60901967d55779ca0bb3919ed1559d946c9028277895b815e41997","schema_version":"1.0","event_id":"sha256:3ffbad50bb60901967d55779ca0bb3919ed1559d946c9028277895b815e41997"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EL6RNSIFM3BECRVVEHRGEEUC7L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hossein Mobahi, Peter L. Bartlett","submitted_at":"2026-07-23T14:31:16Z","abstract_excerpt":"Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge. However, standard compression heuristics often suffer from scale symmetries and architectural biases. To resolve these, we introduce Hilbert Operator for Progressive Encoding (HOPE), a mathematical framework to gradually deconstruct the representations in trained network weights.\n  HOPE shifts network compression from the discrete domain into a Hilbert space of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21366","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/2607.21366/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":"2026-07-24T01:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2jYK/GpKc8wr9bSdBkVFQMDuZZ3AQPreMbw1wrQ59WZ4aNeoDEU/L6Gab5wc+hQHIgC5FJdiAQoulW5IgUu7Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:02:52.393869Z"},"content_sha256":"d70a30fcdbc94af676093569c51dae388b0bd2763ddf88e535da71959d7c7e74","schema_version":"1.0","event_id":"sha256:d70a30fcdbc94af676093569c51dae388b0bd2763ddf88e535da71959d7c7e74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EL6RNSIFM3BECRVVEHRGEEUC7L/bundle.json","state_url":"https://pith.science/pith/EL6RNSIFM3BECRVVEHRGEEUC7L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EL6RNSIFM3BECRVVEHRGEEUC7L/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":"2026-08-04T13:02:52Z","links":{"resolver":"https://pith.science/pith/EL6RNSIFM3BECRVVEHRGEEUC7L","bundle":"https://pith.science/pith/EL6RNSIFM3BECRVVEHRGEEUC7L/bundle.json","state":"https://pith.science/pith/EL6RNSIFM3BECRVVEHRGEEUC7L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EL6RNSIFM3BECRVVEHRGEEUC7L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EL6RNSIFM3BECRVVEHRGEEUC7L","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":"f9c75ff2764fccb66ee6757e9c40e5e06da8683cdfff3b2691af0db29d26f43f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T14:31:16Z","title_canon_sha256":"fd7e8b7a30e621a5cd6cbe99919c964ef203df13f1b09f51df6c9c3778efc3c3"},"schema_version":"1.0","source":{"id":"2607.21366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21366","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21366v1","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21366","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"EL6RNSIFM3BE","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"EL6RNSIFM3BECRVV","created_at":"2026-07-24T01:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"EL6RNSIF","created_at":"2026-07-24T01:24:28Z"}],"graph_snapshots":[{"event_id":"sha256:d70a30fcdbc94af676093569c51dae388b0bd2763ddf88e535da71959d7c7e74","target":"graph","created_at":"2026-07-24T01:24:28Z","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/2607.21366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks encode complex representations, but deconstructing this internal knowledge remains a challenge. Given the link between learning and compression, network compression offers a promising lens to analyze this knowledge. However, standard compression heuristics often suffer from scale symmetries and architectural biases. To resolve these, we introduce Hilbert Operator for Progressive Encoding (HOPE), a mathematical framework to gradually deconstruct the representations in trained network weights.\n  HOPE shifts network compression from the discrete domain into a Hilbert space of","authors_text":"Hossein Mobahi, Peter L. Bartlett","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T14:31:16Z","title":"Hilbert Operator for Progressive Encoding (HOPE): A Mathematical Framework for Deconstructing Learned Representations in Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21366","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":"sha256:3ffbad50bb60901967d55779ca0bb3919ed1559d946c9028277895b815e41997","target":"record","created_at":"2026-07-24T01:24:28Z","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":"f9c75ff2764fccb66ee6757e9c40e5e06da8683cdfff3b2691af0db29d26f43f","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-23T14:31:16Z","title_canon_sha256":"fd7e8b7a30e621a5cd6cbe99919c964ef203df13f1b09f51df6c9c3778efc3c3"},"schema_version":"1.0","source":{"id":"2607.21366","kind":"arxiv","version":1}},"canonical_sha256":"22fd16c90566c24146b521e2621282fad2e4ea7313312625a2fac2c516a79401","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22fd16c90566c24146b521e2621282fad2e4ea7313312625a2fac2c516a79401","first_computed_at":"2026-07-24T01:24:28.694478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:28.694478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+EwjJ1wbB4wIvdqtyKK/TBdlKSR6f8aYAfcpJtjKZOSiUH7515aAvYooxsrBH1wVtokdwSpsfztQ0VoabD2hBg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:28.695372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ffbad50bb60901967d55779ca0bb3919ed1559d946c9028277895b815e41997","sha256:d70a30fcdbc94af676093569c51dae388b0bd2763ddf88e535da71959d7c7e74"],"state_sha256":"956278c2da6f6c4aa8e4ea387a7369504e640bb10ab6d03bab7b41cc11da0f68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ulGw3UyxT9d7/g27O6vzvKDwVztY11U6oHsM7WNHuKC/eU1XqiAknBLuNCp8VfpE11xFEOCyLoCj/9KqjHktCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:02:52.397968Z","bundle_sha256":"bded428805fdd8cc90e613f8b4dc6c40d9c5d0e42272b2fa632d8b205e033b48"}}