{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:MLEDZTL2PXAYTRW6WWS5VTGKIX","short_pith_number":"pith:MLEDZTL2","canonical_record":{"source":{"id":"2207.03172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T09:04:55Z","cross_cats_sorted":[],"title_canon_sha256":"766fa6974cb295543b0602823125279f38ce582f18edeb5a14bca2ee4f230f46","abstract_canon_sha256":"a3d609aac9b99ced0fc02c5f816a6f7a806876a2b79045280a8758ea6b07427f"},"schema_version":"1.0"},"canonical_sha256":"62c83ccd7a7dc189c6deb5a5daccca45de9c3ef788739782d45723791dc1d421","source":{"kind":"arxiv","id":"2207.03172","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.03172","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2207.03172v1","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03172","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"MLEDZTL2PXAY","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"MLEDZTL2PXAYTRW6","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"MLEDZTL2","created_at":"2026-07-05T04:38:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:MLEDZTL2PXAYTRW6WWS5VTGKIX","target":"record","payload":{"canonical_record":{"source":{"id":"2207.03172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T09:04:55Z","cross_cats_sorted":[],"title_canon_sha256":"766fa6974cb295543b0602823125279f38ce582f18edeb5a14bca2ee4f230f46","abstract_canon_sha256":"a3d609aac9b99ced0fc02c5f816a6f7a806876a2b79045280a8758ea6b07427f"},"schema_version":"1.0"},"canonical_sha256":"62c83ccd7a7dc189c6deb5a5daccca45de9c3ef788739782d45723791dc1d421","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:19.540191Z","signature_b64":"0Cjqopns+MS3WSFlqDSe8Lnfznjg8rad3uLSSyu2kIIZXiZ9KpFE4rkEGkVVkT9dbk5D+eigYWDdw9k4IFq1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c83ccd7a7dc189c6deb5a5daccca45de9c3ef788739782d45723791dc1d421","last_reissued_at":"2026-07-05T04:38:19.539849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:19.539849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.03172","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":"2026-07-05T04:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z0So1pq6GnGZw9PSnkRG0Z+Z2ih48qEdQms4/lODGv8Ycu2I7n7quTUmiIJp7hjQpnxoEWt6lGY2qBfv8S7bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:49:02.110750Z"},"content_sha256":"ca4e099cdb513eb065ad517c09665cd9f21fdbaa3a147eb489255b9b223fccd9","schema_version":"1.0","event_id":"sha256:ca4e099cdb513eb065ad517c09665cd9f21fdbaa3a147eb489255b9b223fccd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:MLEDZTL2PXAYTRW6WWS5VTGKIX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Level","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Claudio Gennaro, Gabriele Lagani, Giuseppe Amato, Hannes Fassold","submitted_at":"2022-07-07T09:04:55Z","abstract_excerpt":"Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop). Backprop algorithms require a large number of labelled training samples to achieve high performance. However, in many realistic applications, even if there is plenty of image samples, very few of them are labelled, and semi-supervised sample-efficient training strategies have to be used. Hebbian learning represents a possible approach towards sample efficient training; however, in current solutions, it does not scale well to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03172","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/2207.03172/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":"2026-07-05T04:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMV1McOuGbwfsP3fNlFSqkBXpZVrZCJ4neKkDbjjaLpKI12rHFPgv+wLgS1yzeRDdy6J96Bvc4STZhB8dNWIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:49:02.111117Z"},"content_sha256":"2c66a12afb30c9aa3afd2227d082cee2d4554d30d0f89715ca8eae30ee9366e9","schema_version":"1.0","event_id":"sha256:2c66a12afb30c9aa3afd2227d082cee2d4554d30d0f89715ca8eae30ee9366e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX/bundle.json","state_url":"https://pith.science/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX/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":"2026-08-06T15:49:02Z","links":{"resolver":"https://pith.science/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX","bundle":"https://pith.science/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX/bundle.json","state":"https://pith.science/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLEDZTL2PXAYTRW6WWS5VTGKIX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:MLEDZTL2PXAYTRW6WWS5VTGKIX","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":"a3d609aac9b99ced0fc02c5f816a6f7a806876a2b79045280a8758ea6b07427f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T09:04:55Z","title_canon_sha256":"766fa6974cb295543b0602823125279f38ce582f18edeb5a14bca2ee4f230f46"},"schema_version":"1.0","source":{"id":"2207.03172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.03172","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2207.03172v1","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03172","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"MLEDZTL2PXAY","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"MLEDZTL2PXAYTRW6","created_at":"2026-07-05T04:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"MLEDZTL2","created_at":"2026-07-05T04:38:19Z"}],"graph_snapshots":[{"event_id":"sha256:2c66a12afb30c9aa3afd2227d082cee2d4554d30d0f89715ca8eae30ee9366e9","target":"graph","created_at":"2026-07-05T04:38:19Z","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/2207.03172/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning algorithms for Deep Neural Networks are typically based on supervised end-to-end Stochastic Gradient Descent (SGD) training with error backpropagation (backprop). Backprop algorithms require a large number of labelled training samples to achieve high performance. However, in many realistic applications, even if there is plenty of image samples, very few of them are labelled, and semi-supervised sample-efficient training strategies have to be used. Hebbian learning represents a possible approach towards sample efficient training; however, in current solutions, it does not scale well to","authors_text":"Claudio Gennaro, Gabriele Lagani, Giuseppe Amato, Hannes Fassold","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T09:04:55Z","title":"FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Level"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03172","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:ca4e099cdb513eb065ad517c09665cd9f21fdbaa3a147eb489255b9b223fccd9","target":"record","created_at":"2026-07-05T04:38:19Z","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":"a3d609aac9b99ced0fc02c5f816a6f7a806876a2b79045280a8758ea6b07427f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-07T09:04:55Z","title_canon_sha256":"766fa6974cb295543b0602823125279f38ce582f18edeb5a14bca2ee4f230f46"},"schema_version":"1.0","source":{"id":"2207.03172","kind":"arxiv","version":1}},"canonical_sha256":"62c83ccd7a7dc189c6deb5a5daccca45de9c3ef788739782d45723791dc1d421","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62c83ccd7a7dc189c6deb5a5daccca45de9c3ef788739782d45723791dc1d421","first_computed_at":"2026-07-05T04:38:19.539849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:38:19.539849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Cjqopns+MS3WSFlqDSe8Lnfznjg8rad3uLSSyu2kIIZXiZ9KpFE4rkEGkVVkT9dbk5D+eigYWDdw9k4IFq1AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:38:19.540191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.03172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca4e099cdb513eb065ad517c09665cd9f21fdbaa3a147eb489255b9b223fccd9","sha256:2c66a12afb30c9aa3afd2227d082cee2d4554d30d0f89715ca8eae30ee9366e9"],"state_sha256":"7b078f2a2d61c85cf8a9eb64d7326b192d11ec29f65bc28c0b012b15e464e53e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"huHJdN9NBZOr8DEyaQVC16mCPKs4JTgZqB+lsA4Zg5MHKIJco0CKhfv4y3/fSLTf8Dvng6cdGUMi0TH/UTctDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:49:02.114065Z","bundle_sha256":"58c68eeef2cb2a8b2512eaff0d51b75254177a5b7a5baba57e96d9391a9bdcc5"}}