{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MOZV2QWJU64WZWIVMMAT6NDWWK","short_pith_number":"pith:MOZV2QWJ","canonical_record":{"source":{"id":"1608.04374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-15T19:38:35Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"f001f5f822ce272f15050f3b8662202753ac312dcb528ee9f3ccf04740a06300","abstract_canon_sha256":"e7bf4b083e5bbe69c609c53c37211803ce58daa928c049523ba27679c07cd8ec"},"schema_version":"1.0"},"canonical_sha256":"63b35d42c9a7b96cd91563013f3476b2b33b39f90d5bc576e0dd0e3be078c985","source":{"kind":"arxiv","id":"1608.04374","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04374","created_at":"2026-05-18T01:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04374v2","created_at":"2026-05-18T01:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04374","created_at":"2026-05-18T01:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"MOZV2QWJU64W","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MOZV2QWJU64WZWIV","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MOZV2QWJ","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MOZV2QWJU64WZWIVMMAT6NDWWK","target":"record","payload":{"canonical_record":{"source":{"id":"1608.04374","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-15T19:38:35Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"f001f5f822ce272f15050f3b8662202753ac312dcb528ee9f3ccf04740a06300","abstract_canon_sha256":"e7bf4b083e5bbe69c609c53c37211803ce58daa928c049523ba27679c07cd8ec"},"schema_version":"1.0"},"canonical_sha256":"63b35d42c9a7b96cd91563013f3476b2b33b39f90d5bc576e0dd0e3be078c985","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:07.258771Z","signature_b64":"vNCBznUuL/pQaFGK2vE/fjhd0ZSxWiwFrUzuJ3XIBNpeOcnZQSHaqTbs85VFo9lo+u0O3EeKXZoUNIwGjENAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b35d42c9a7b96cd91563013f3476b2b33b39f90d5bc576e0dd0e3be078c985","last_reissued_at":"2026-05-18T01:03:07.258261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:07.258261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.04374","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":"2026-05-18T01:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDfwVwGULnOIJrTDh5sQ72I6FbrGLveYhEegkC3L/AXCL5oEFAN8et3o/wVCt6JLmGhv8ILzIMOR3f7ESCNMDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:52:57.760809Z"},"content_sha256":"30d535c01266c98549cb516f7fcc4dc72f0e9627a150e55fdf9d2d9c05ff0c33","schema_version":"1.0","event_id":"sha256:30d535c01266c98549cb516f7fcc4dc72f0e9627a150e55fdf9d2d9c05ff0c33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MOZV2QWJU64WZWIVMMAT6NDWWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Geometric Framework for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"stat.ML","authors_text":"Anthony L. Caterini, Dong Eui Chang","submitted_at":"2016-08-15T19:38:35Z","abstract_excerpt":"In this paper, a geometric framework for neural networks is proposed. This framework uses the inner product space structure underlying the parameter set to perform gradient descent not in a component-based form, but in a coordinate-free manner. Convolutional neural networks are described in this framework in a compact form, with the gradients of standard --- and higher-order --- loss functions calculated for each layer of the network. This approach can be applied to other network structures and provides a basis on which to create new networks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04374","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":""},"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":"2026-05-18T01:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kknYxMIt7Tfz1gw6nsLQlHvNZdbBF3KJb/C1exRwyTmY0fapeBKT1FZVEOAS1y/z9m8l5ydr6YPXpYQusJGLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:52:57.761508Z"},"content_sha256":"777139b7e05b6687aed22a63ec246ee31882c26c22f96e1142e9aec368554358","schema_version":"1.0","event_id":"sha256:777139b7e05b6687aed22a63ec246ee31882c26c22f96e1142e9aec368554358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MOZV2QWJU64WZWIVMMAT6NDWWK/bundle.json","state_url":"https://pith.science/pith/MOZV2QWJU64WZWIVMMAT6NDWWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MOZV2QWJU64WZWIVMMAT6NDWWK/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":"2026-06-09T10:52:57Z","links":{"resolver":"https://pith.science/pith/MOZV2QWJU64WZWIVMMAT6NDWWK","bundle":"https://pith.science/pith/MOZV2QWJU64WZWIVMMAT6NDWWK/bundle.json","state":"https://pith.science/pith/MOZV2QWJU64WZWIVMMAT6NDWWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MOZV2QWJU64WZWIVMMAT6NDWWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MOZV2QWJU64WZWIVMMAT6NDWWK","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":"e7bf4b083e5bbe69c609c53c37211803ce58daa928c049523ba27679c07cd8ec","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-15T19:38:35Z","title_canon_sha256":"f001f5f822ce272f15050f3b8662202753ac312dcb528ee9f3ccf04740a06300"},"schema_version":"1.0","source":{"id":"1608.04374","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04374","created_at":"2026-05-18T01:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04374v2","created_at":"2026-05-18T01:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04374","created_at":"2026-05-18T01:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"MOZV2QWJU64W","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MOZV2QWJU64WZWIV","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MOZV2QWJ","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:777139b7e05b6687aed22a63ec246ee31882c26c22f96e1142e9aec368554358","target":"graph","created_at":"2026-05-18T01:03:07Z","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"},"paper":{"abstract_excerpt":"In this paper, a geometric framework for neural networks is proposed. This framework uses the inner product space structure underlying the parameter set to perform gradient descent not in a component-based form, but in a coordinate-free manner. Convolutional neural networks are described in this framework in a compact form, with the gradients of standard --- and higher-order --- loss functions calculated for each layer of the network. This approach can be applied to other network structures and provides a basis on which to create new networks.","authors_text":"Anthony L. Caterini, Dong Eui Chang","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-15T19:38:35Z","title":"A Geometric Framework for Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04374","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":"sha256:30d535c01266c98549cb516f7fcc4dc72f0e9627a150e55fdf9d2d9c05ff0c33","target":"record","created_at":"2026-05-18T01:03:07Z","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":"e7bf4b083e5bbe69c609c53c37211803ce58daa928c049523ba27679c07cd8ec","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-08-15T19:38:35Z","title_canon_sha256":"f001f5f822ce272f15050f3b8662202753ac312dcb528ee9f3ccf04740a06300"},"schema_version":"1.0","source":{"id":"1608.04374","kind":"arxiv","version":2}},"canonical_sha256":"63b35d42c9a7b96cd91563013f3476b2b33b39f90d5bc576e0dd0e3be078c985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b35d42c9a7b96cd91563013f3476b2b33b39f90d5bc576e0dd0e3be078c985","first_computed_at":"2026-05-18T01:03:07.258261Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:07.258261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vNCBznUuL/pQaFGK2vE/fjhd0ZSxWiwFrUzuJ3XIBNpeOcnZQSHaqTbs85VFo9lo+u0O3EeKXZoUNIwGjENAAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:07.258771Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.04374","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30d535c01266c98549cb516f7fcc4dc72f0e9627a150e55fdf9d2d9c05ff0c33","sha256:777139b7e05b6687aed22a63ec246ee31882c26c22f96e1142e9aec368554358"],"state_sha256":"81486f1105fb09e9f2cb135d315243c6b40371b6a309edacaeb0d8469df6ba96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cag8HjZ70QhJsl2cj5z/PkXfCBNgEu5tR72DfOFwFz2kQMU+arkdbXyC3OzHaxc9RkqnVncfA8wNeyn7rGNvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T10:52:57.765328Z","bundle_sha256":"5eab338727065f0add04b91aa68a8c7364b9e3cfd47ffe922d8353ddf815e146"}}