{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5YWW3SEKNZZAQVLKZOEZVTU5AN","short_pith_number":"pith:5YWW3SEK","canonical_record":{"source":{"id":"2107.05298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T10:17:53Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"387d45629757738d1bbb5d4569abcf2ff191c9b1d7d991477f6f4eaf55c577d5","abstract_canon_sha256":"905d487c72474ee321503f34925ef14694a00f0b279debd9e93ed00413d2b3a2"},"schema_version":"1.0"},"canonical_sha256":"ee2d6dc88a6e7208556acb899ace9d034ca2f387a25fc34bb562fcb222649a6d","source":{"kind":"arxiv","id":"2107.05298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05298","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05298v1","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05298","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"5YWW3SEKNZZA","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"5YWW3SEKNZZAQVLK","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"5YWW3SEK","created_at":"2026-07-05T02:57:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5YWW3SEKNZZAQVLKZOEZVTU5AN","target":"record","payload":{"canonical_record":{"source":{"id":"2107.05298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T10:17:53Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"387d45629757738d1bbb5d4569abcf2ff191c9b1d7d991477f6f4eaf55c577d5","abstract_canon_sha256":"905d487c72474ee321503f34925ef14694a00f0b279debd9e93ed00413d2b3a2"},"schema_version":"1.0"},"canonical_sha256":"ee2d6dc88a6e7208556acb899ace9d034ca2f387a25fc34bb562fcb222649a6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:01.462263Z","signature_b64":"xM/odrWZOxa3dyOZIQ5ORqhNcgZn6RJaacMADkh6IIK33ncg9jbso36levxJ5k4UhIRUTDojpAWiA4sJ87F8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee2d6dc88a6e7208556acb899ace9d034ca2f387a25fc34bb562fcb222649a6d","last_reissued_at":"2026-07-05T02:57:01.461920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:01.461920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.05298","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":"2026-07-05T02:57:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlDvLXmlWeQkQzhOHi2afANgW5rZ2p3VU52nkupLPz8oUfXpPjF1kAP3vy7Q3yPwU8MEMBypRBcOoLdcQYwiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:50:07.841407Z"},"content_sha256":"b20d183876de4b80defe271db09f67ea4fb74899454778bbe5f69d5fd3fe22cb","schema_version":"1.0","event_id":"sha256:b20d183876de4b80defe271db09f67ea4fb74899454778bbe5f69d5fd3fe22cb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5YWW3SEKNZZAQVLKZOEZVTU5AN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HEMP: High-order Entropy Minimization for neural network comPression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Attilio Fiandrotti, Enzo Tartaglione, Marco Cagnazzo, Marco Grangetto, St\\'ephane Lathuili\\`ere","submitted_at":"2021-07-12T10:17:53Z","abstract_excerpt":"We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent. Our formulation scales efficiently beyond the first order and is agnostic of the quantization scheme. The network can then be trained to minimize the entropy of the quantized parameters, so that they can be optimally compressed via entropy coding. We experiment with our entropy formulation at quantizing and compressing well-known network architectures over multiple datasets. Our approach compares favora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05298","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/2107.05298/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":"2026-07-05T02:57:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iljxRPpcp28RJxeAESi7RQ7ieAcgrJfGf/lfG9XDGkJVQmKsk0dP8dr3xdsvROtpq7qXfMxh7KeqFKyce7D8AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:50:07.842424Z"},"content_sha256":"29592f94a97479841cfe38d2a22c2a1995eb6ad4d9bd1bb012a97c9ded988afb","schema_version":"1.0","event_id":"sha256:29592f94a97479841cfe38d2a22c2a1995eb6ad4d9bd1bb012a97c9ded988afb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN/bundle.json","state_url":"https://pith.science/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN/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":"2026-08-17T20:50:07Z","links":{"resolver":"https://pith.science/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN","bundle":"https://pith.science/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN/bundle.json","state":"https://pith.science/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YWW3SEKNZZAQVLKZOEZVTU5AN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5YWW3SEKNZZAQVLKZOEZVTU5AN","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":"905d487c72474ee321503f34925ef14694a00f0b279debd9e93ed00413d2b3a2","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T10:17:53Z","title_canon_sha256":"387d45629757738d1bbb5d4569abcf2ff191c9b1d7d991477f6f4eaf55c577d5"},"schema_version":"1.0","source":{"id":"2107.05298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05298","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05298v1","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05298","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"5YWW3SEKNZZA","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"5YWW3SEKNZZAQVLK","created_at":"2026-07-05T02:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"5YWW3SEK","created_at":"2026-07-05T02:57:01Z"}],"graph_snapshots":[{"event_id":"sha256:29592f94a97479841cfe38d2a22c2a1995eb6ad4d9bd1bb012a97c9ded988afb","target":"graph","created_at":"2026-07-05T02:57:01Z","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/2107.05298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We formulate the entropy of a quantized artificial neural network as a differentiable function that can be plugged as a regularization term into the cost function minimized by gradient descent. Our formulation scales efficiently beyond the first order and is agnostic of the quantization scheme. The network can then be trained to minimize the entropy of the quantized parameters, so that they can be optimally compressed via entropy coding. We experiment with our entropy formulation at quantizing and compressing well-known network architectures over multiple datasets. Our approach compares favora","authors_text":"Attilio Fiandrotti, Enzo Tartaglione, Marco Cagnazzo, Marco Grangetto, St\\'ephane Lathuili\\`ere","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T10:17:53Z","title":"HEMP: High-order Entropy Minimization for neural network comPression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05298","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:b20d183876de4b80defe271db09f67ea4fb74899454778bbe5f69d5fd3fe22cb","target":"record","created_at":"2026-07-05T02:57:01Z","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":"905d487c72474ee321503f34925ef14694a00f0b279debd9e93ed00413d2b3a2","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T10:17:53Z","title_canon_sha256":"387d45629757738d1bbb5d4569abcf2ff191c9b1d7d991477f6f4eaf55c577d5"},"schema_version":"1.0","source":{"id":"2107.05298","kind":"arxiv","version":1}},"canonical_sha256":"ee2d6dc88a6e7208556acb899ace9d034ca2f387a25fc34bb562fcb222649a6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee2d6dc88a6e7208556acb899ace9d034ca2f387a25fc34bb562fcb222649a6d","first_computed_at":"2026-07-05T02:57:01.461920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:01.461920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xM/odrWZOxa3dyOZIQ5ORqhNcgZn6RJaacMADkh6IIK33ncg9jbso36levxJ5k4UhIRUTDojpAWiA4sJ87F8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:01.462263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.05298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b20d183876de4b80defe271db09f67ea4fb74899454778bbe5f69d5fd3fe22cb","sha256:29592f94a97479841cfe38d2a22c2a1995eb6ad4d9bd1bb012a97c9ded988afb"],"state_sha256":"c2d1c0f5599287defd3ed717ed5fec3ff55011b4c47a01737d53c5458487d345"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0hGfzx9JW1Yfk+tXrF4c2hbt6Szwc+t7EkEHgRHi3WolcrqZDqy+TgzCZLClMIMHRKQTmE+EPvYRvdut0UjfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:50:07.902834Z","bundle_sha256":"5e326bae6bdee847c97792d405c20cbb26fa37dbd93d05a90c57260ccae4c3d3"}}