{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3RFHNMGNCHZ72JQR7GNBPIETUK","short_pith_number":"pith:3RFHNMGN","canonical_record":{"source":{"id":"2506.07975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T17:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"df335937279064e02712562ebc9593ae632348c67525eef42706976ab047acc6","abstract_canon_sha256":"3d99000b6caa096c1d6357d80c5c0ba1537355dca93e26953452fd429411ec52"},"schema_version":"1.0"},"canonical_sha256":"dc4a76b0cd11f3fd2611f99a17a093a281cfc119d22c503973a9eb7fb10ef6d2","source":{"kind":"arxiv","id":"2506.07975","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07975","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07975v1","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07975","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"3RFHNMGNCHZ7","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"3RFHNMGNCHZ72JQR","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"3RFHNMGN","created_at":"2026-07-05T11:18:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3RFHNMGNCHZ72JQR7GNBPIETUK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07975","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T17:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"df335937279064e02712562ebc9593ae632348c67525eef42706976ab047acc6","abstract_canon_sha256":"3d99000b6caa096c1d6357d80c5c0ba1537355dca93e26953452fd429411ec52"},"schema_version":"1.0"},"canonical_sha256":"dc4a76b0cd11f3fd2611f99a17a093a281cfc119d22c503973a9eb7fb10ef6d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:36.496768Z","signature_b64":"H7/NHCjFghxCzKn01W/ikFPbBONNnely6j4pFPVHL2yrB70kACGrwwF0vkrfDjYSaFd2Q2LBjv+lG42+c5sBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc4a76b0cd11f3fd2611f99a17a093a281cfc119d22c503973a9eb7fb10ef6d2","last_reissued_at":"2026-07-05T11:18:36.496335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:36.496335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07975","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":"2026-07-05T11:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2FtRgkfz5xAWP54UWUYXRiFGvzcaYdHbQcWoVY2Rtacyp74q00yeAdEpcOkjjtpLFTs2iNuPg3+MiAaCE674Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:30:26.183623Z"},"content_sha256":"4598ec9ffee472de87493f49d778986a228c83b0edf9b5e90909438499425be0","schema_version":"1.0","event_id":"sha256:4598ec9ffee472de87493f49d778986a228c83b0edf9b5e90909438499425be0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3RFHNMGNCHZ72JQR7GNBPIETUK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caleb Zheng, Eli Shlizerman","submitted_at":"2025-06-09T17:49:29Z","abstract_excerpt":"A variety of pruning methods have been introduced for over-parameterized Recurrent Neural Networks to improve efficiency in terms of power consumption and storage utilization. These advances motivate a new paradigm, termed `hyperpruning', which seeks to identify the most suitable pruning strategy for a given network architecture and application. Unlike conventional hyperparameter search, where the optimal configuration's accuracy remains uncertain, in the context of network pruning, the accuracy of the dense model sets the target for the accuracy of the pruned one. The goal, therefore, is to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07975","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/2506.07975/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":"2026-07-05T11:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArHOrVKgtxF2DJd+vlEGJi3hSF5mMRtjsQJnCwph3xjB46vuQF1PTQ4NHO+jryckIkHXEKQ1WNfv/jAmTwBqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:30:26.184114Z"},"content_sha256":"e3fa349aacf609d1b98260c9f0e481bbccbadb5dd818a822791a55be1ff824d0","schema_version":"1.0","event_id":"sha256:e3fa349aacf609d1b98260c9f0e481bbccbadb5dd818a822791a55be1ff824d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RFHNMGNCHZ72JQR7GNBPIETUK/bundle.json","state_url":"https://pith.science/pith/3RFHNMGNCHZ72JQR7GNBPIETUK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RFHNMGNCHZ72JQR7GNBPIETUK/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":"2026-08-09T10:30:26Z","links":{"resolver":"https://pith.science/pith/3RFHNMGNCHZ72JQR7GNBPIETUK","bundle":"https://pith.science/pith/3RFHNMGNCHZ72JQR7GNBPIETUK/bundle.json","state":"https://pith.science/pith/3RFHNMGNCHZ72JQR7GNBPIETUK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RFHNMGNCHZ72JQR7GNBPIETUK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3RFHNMGNCHZ72JQR7GNBPIETUK","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":"3d99000b6caa096c1d6357d80c5c0ba1537355dca93e26953452fd429411ec52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T17:49:29Z","title_canon_sha256":"df335937279064e02712562ebc9593ae632348c67525eef42706976ab047acc6"},"schema_version":"1.0","source":{"id":"2506.07975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07975","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07975v1","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07975","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"3RFHNMGNCHZ7","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"3RFHNMGNCHZ72JQR","created_at":"2026-07-05T11:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"3RFHNMGN","created_at":"2026-07-05T11:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:e3fa349aacf609d1b98260c9f0e481bbccbadb5dd818a822791a55be1ff824d0","target":"graph","created_at":"2026-07-05T11:18:36Z","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/2506.07975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A variety of pruning methods have been introduced for over-parameterized Recurrent Neural Networks to improve efficiency in terms of power consumption and storage utilization. These advances motivate a new paradigm, termed `hyperpruning', which seeks to identify the most suitable pruning strategy for a given network architecture and application. Unlike conventional hyperparameter search, where the optimal configuration's accuracy remains uncertain, in the context of network pruning, the accuracy of the dense model sets the target for the accuracy of the pruned one. The goal, therefore, is to d","authors_text":"Caleb Zheng, Eli Shlizerman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T17:49:29Z","title":"Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07975","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":"sha256:4598ec9ffee472de87493f49d778986a228c83b0edf9b5e90909438499425be0","target":"record","created_at":"2026-07-05T11:18:36Z","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":"3d99000b6caa096c1d6357d80c5c0ba1537355dca93e26953452fd429411ec52","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T17:49:29Z","title_canon_sha256":"df335937279064e02712562ebc9593ae632348c67525eef42706976ab047acc6"},"schema_version":"1.0","source":{"id":"2506.07975","kind":"arxiv","version":1}},"canonical_sha256":"dc4a76b0cd11f3fd2611f99a17a093a281cfc119d22c503973a9eb7fb10ef6d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc4a76b0cd11f3fd2611f99a17a093a281cfc119d22c503973a9eb7fb10ef6d2","first_computed_at":"2026-07-05T11:18:36.496335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:36.496335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H7/NHCjFghxCzKn01W/ikFPbBONNnely6j4pFPVHL2yrB70kACGrwwF0vkrfDjYSaFd2Q2LBjv+lG42+c5sBAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:36.496768Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4598ec9ffee472de87493f49d778986a228c83b0edf9b5e90909438499425be0","sha256:e3fa349aacf609d1b98260c9f0e481bbccbadb5dd818a822791a55be1ff824d0"],"state_sha256":"ddec3b68029af677d353281ad49576f5ddce26f008c8b31006644a3dc6ec3586"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rNEDq46LPhKpfAAW5bNtPcWCOXPv1aGp8nR7CM1wyyl3JGbFs0OP5Vnr25Od3IGzisO1e7IEksZEL+DUp2tXBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:30:26.189531Z","bundle_sha256":"b2018242b0b47531eec07c0ccabc3aa0f044507ee3f50994a57d1a741b3ce524"}}