{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:HETORGIX3LSXTTQRAMCLFJZZFU","short_pith_number":"pith:HETORGIX","canonical_record":{"source":{"id":"2004.01077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-02T15:38:00Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"ed371d2686bc7d2abbb457aafe26057cb11b3f6898e6fd88f386275487a64046","abstract_canon_sha256":"f6afe233abea5282dd27def48b939717c7b68a7cefe5500d438c7e5837daf811"},"schema_version":"1.0"},"canonical_sha256":"3926e89917dae579ce110304b2a7392d0dee9876a413442e6ba67936eeef0e83","source":{"kind":"arxiv","id":"2004.01077","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.01077","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.01077v2","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.01077","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"pith_short_12","alias_value":"HETORGIX3LSX","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"pith_short_16","alias_value":"HETORGIX3LSXTTQR","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"pith_short_8","alias_value":"HETORGIX","created_at":"2026-07-05T04:13:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:HETORGIX3LSXTTQRAMCLFJZZFU","target":"record","payload":{"canonical_record":{"source":{"id":"2004.01077","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-02T15:38:00Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"ed371d2686bc7d2abbb457aafe26057cb11b3f6898e6fd88f386275487a64046","abstract_canon_sha256":"f6afe233abea5282dd27def48b939717c7b68a7cefe5500d438c7e5837daf811"},"schema_version":"1.0"},"canonical_sha256":"3926e89917dae579ce110304b2a7392d0dee9876a413442e6ba67936eeef0e83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:08.286226Z","signature_b64":"7yAAyFVCXI4v3OWEUEwhckXjT351wfx8Q/9JxJEwQZAnods9vpvK9Od3NH+Nxzlbl6QZsd3Df1MUdxaB8CwlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3926e89917dae579ce110304b2a7392d0dee9876a413442e6ba67936eeef0e83","last_reissued_at":"2026-07-05T04:13:08.285837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:08.285837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.01077","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":"2026-07-05T04:13:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mg4CGfg/qkSOyzvGT18kABF4pgybUlh0LqF58gEAYRw/7J+Xaqgxe0AXK/HkGqYXx55wUgioGuF2WYJOFMWDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:46:13.568515Z"},"content_sha256":"6c2e385ced7b82860b55c307f7ac9aea93df66e0dca3cffa5e975532ea9381ef","schema_version":"1.0","event_id":"sha256:6c2e385ced7b82860b55c307f7ac9aea93df66e0dca3cffa5e975532ea9381ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:HETORGIX3LSXTTQRAMCLFJZZFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arturo Marban, Daniel Becking, Simon Wiedemann, Wojciech Samek","submitted_at":"2020-04-02T15:38:00Z","abstract_excerpt":"Deep neural networks (DNN) have shown remarkable success in a variety of machine learning applications. The capacity of these models (i.e., number of parameters), endows them with expressive power and allows them to reach the desired performance. In recent years, there is an increasing interest in deploying DNNs to resource-constrained devices (i.e., mobile devices) with limited energy, memory, and computational budget. To address this problem, we propose Entropy-Constrained Trained Ternarization (EC2T), a general framework to create sparse and ternary neural networks which are efficient in te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.01077","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/2004.01077/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":"2026-07-05T04:13:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6bmdDjrOTF/gzW3qW67Fyjy3werz9EwyALjKkir7F77xYqTXtdAUQ9LZJP9zSJrD7I138+5AnQBg+9X4U8uRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T19:46:13.569547Z"},"content_sha256":"17bea24de070f758f4fb953807dcc13a2e868d21955ee688d625b570baa94ac4","schema_version":"1.0","event_id":"sha256:17bea24de070f758f4fb953807dcc13a2e868d21955ee688d625b570baa94ac4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HETORGIX3LSXTTQRAMCLFJZZFU/bundle.json","state_url":"https://pith.science/pith/HETORGIX3LSXTTQRAMCLFJZZFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HETORGIX3LSXTTQRAMCLFJZZFU/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":"2026-08-14T19:46:13Z","links":{"resolver":"https://pith.science/pith/HETORGIX3LSXTTQRAMCLFJZZFU","bundle":"https://pith.science/pith/HETORGIX3LSXTTQRAMCLFJZZFU/bundle.json","state":"https://pith.science/pith/HETORGIX3LSXTTQRAMCLFJZZFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HETORGIX3LSXTTQRAMCLFJZZFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:HETORGIX3LSXTTQRAMCLFJZZFU","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":"f6afe233abea5282dd27def48b939717c7b68a7cefe5500d438c7e5837daf811","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-02T15:38:00Z","title_canon_sha256":"ed371d2686bc7d2abbb457aafe26057cb11b3f6898e6fd88f386275487a64046"},"schema_version":"1.0","source":{"id":"2004.01077","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.01077","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.01077v2","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.01077","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"pith_short_12","alias_value":"HETORGIX3LSX","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"pith_short_16","alias_value":"HETORGIX3LSXTTQR","created_at":"2026-07-05T04:13:08Z"},{"alias_kind":"pith_short_8","alias_value":"HETORGIX","created_at":"2026-07-05T04:13:08Z"}],"graph_snapshots":[{"event_id":"sha256:17bea24de070f758f4fb953807dcc13a2e868d21955ee688d625b570baa94ac4","target":"graph","created_at":"2026-07-05T04:13:08Z","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/2004.01077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNN) have shown remarkable success in a variety of machine learning applications. The capacity of these models (i.e., number of parameters), endows them with expressive power and allows them to reach the desired performance. In recent years, there is an increasing interest in deploying DNNs to resource-constrained devices (i.e., mobile devices) with limited energy, memory, and computational budget. To address this problem, we propose Entropy-Constrained Trained Ternarization (EC2T), a general framework to create sparse and ternary neural networks which are efficient in te","authors_text":"Arturo Marban, Daniel Becking, Simon Wiedemann, Wojciech Samek","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-02T15:38:00Z","title":"Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.01077","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":"sha256:6c2e385ced7b82860b55c307f7ac9aea93df66e0dca3cffa5e975532ea9381ef","target":"record","created_at":"2026-07-05T04:13:08Z","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":"f6afe233abea5282dd27def48b939717c7b68a7cefe5500d438c7e5837daf811","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-02T15:38:00Z","title_canon_sha256":"ed371d2686bc7d2abbb457aafe26057cb11b3f6898e6fd88f386275487a64046"},"schema_version":"1.0","source":{"id":"2004.01077","kind":"arxiv","version":2}},"canonical_sha256":"3926e89917dae579ce110304b2a7392d0dee9876a413442e6ba67936eeef0e83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3926e89917dae579ce110304b2a7392d0dee9876a413442e6ba67936eeef0e83","first_computed_at":"2026-07-05T04:13:08.285837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:08.285837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7yAAyFVCXI4v3OWEUEwhckXjT351wfx8Q/9JxJEwQZAnods9vpvK9Od3NH+Nxzlbl6QZsd3Df1MUdxaB8CwlCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:08.286226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.01077","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c2e385ced7b82860b55c307f7ac9aea93df66e0dca3cffa5e975532ea9381ef","sha256:17bea24de070f758f4fb953807dcc13a2e868d21955ee688d625b570baa94ac4"],"state_sha256":"21165f0683f56d22e73ba3d1db365e04e5775a7a75c62c1c897274243bd5b6f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ORpRDPZUwdA1D+aJJ6dRngvIuSjgs/xTEvLxK1o8ngmahhK62xPgLr3CQrTRLMh6fhOomZ1ZTWUxK2dPRy5IBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T19:46:13.577315Z","bundle_sha256":"a8f40c97a8d58dd9d5a67d88c4da569242f63c431f8396fe23cd501f10171902"}}