{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JB64KHCTTPL5Q7BJXYZ4QBZFAM","short_pith_number":"pith:JB64KHCT","canonical_record":{"source":{"id":"2103.04318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T10:46:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef567e7a8ffe0e692db2d0eafb83509dd46f54a66dd76278c62535e71c98d94a","abstract_canon_sha256":"58fe64215d7e33194bac615f4e04930230c9aaee44333bd0891418beee7a10b6"},"schema_version":"1.0"},"canonical_sha256":"487dc51c539bd7d87c29be33c80725033ef21ce9de40b9f2373aa19892c3dd5b","source":{"kind":"arxiv","id":"2103.04318","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04318","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04318v1","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04318","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"JB64KHCTTPL5","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"JB64KHCTTPL5Q7BJ","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"JB64KHCT","created_at":"2026-07-05T06:59:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JB64KHCTTPL5Q7BJXYZ4QBZFAM","target":"record","payload":{"canonical_record":{"source":{"id":"2103.04318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T10:46:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ef567e7a8ffe0e692db2d0eafb83509dd46f54a66dd76278c62535e71c98d94a","abstract_canon_sha256":"58fe64215d7e33194bac615f4e04930230c9aaee44333bd0891418beee7a10b6"},"schema_version":"1.0"},"canonical_sha256":"487dc51c539bd7d87c29be33c80725033ef21ce9de40b9f2373aa19892c3dd5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:26.315398Z","signature_b64":"6c8pQsvO99R3pOx/mZ2HCAiQM3OcfTwfU7mWposl85Erdtzau45FlXWjNOh0wndF+QvtzFcmLzIZm+y+sVN5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"487dc51c539bd7d87c29be33c80725033ef21ce9de40b9f2373aa19892c3dd5b","last_reissued_at":"2026-07-05T06:59:26.314883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:26.314883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.04318","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":"2026-07-05T06:59:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiyynEBJy0rwdjjjxUMXklH4bcTd7SyfyCSi57fPB1DvKrS2EZXWOUSPUop5GTxnRUUSvvELEUGWMczlC4aYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T22:00:37.088213Z"},"content_sha256":"a338f546a0f40cc5d571b6e61b6fc05e5a86f5b7324f078a83be3bf21aca7fa2","schema_version":"1.0","event_id":"sha256:a338f546a0f40cc5d571b6e61b6fc05e5a86f5b7324f078a83be3bf21aca7fa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JB64KHCTTPL5Q7BJXYZ4QBZFAM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implementing graph neural networks with TensorFlow-Keras","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andre Eberhard, Pascal Friederich, Patrick Reiser","submitted_at":"2021-03-07T10:46:02Z","abstract_excerpt":"Graph neural networks are a versatile machine learning architecture that received a lot of attention recently. In this technical report, we present an implementation of convolution and pooling layers for TensorFlow-Keras models, which allows a seamless and flexible integration into standard Keras layers to set up graph models in a functional way. This implies the usage of mini-batches as the first tensor dimension, which can be realized via the new RaggedTensor class of TensorFlow best suited for graphs. We developed the Keras Graph Convolutional Neural Network Python package kgcnn based on Te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04318","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/2103.04318/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":"2026-07-05T06:59:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SMSpW4cAOgb1fx1AzeplZ8YGGjEwdyGSfpzlcagw2hnXNMANe2Z4FLz/5YwIH/O43aXJ3UDMEb5d/eoMtegIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T22:00:37.088620Z"},"content_sha256":"a9a5790d88d84fddb62a730aab7c63a05fdaffbcaf65ba4b321f70b05a9a687e","schema_version":"1.0","event_id":"sha256:a9a5790d88d84fddb62a730aab7c63a05fdaffbcaf65ba4b321f70b05a9a687e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM/bundle.json","state_url":"https://pith.science/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM/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":"2026-07-12T22:00:37Z","links":{"resolver":"https://pith.science/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM","bundle":"https://pith.science/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM/bundle.json","state":"https://pith.science/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JB64KHCTTPL5Q7BJXYZ4QBZFAM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JB64KHCTTPL5Q7BJXYZ4QBZFAM","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":"58fe64215d7e33194bac615f4e04930230c9aaee44333bd0891418beee7a10b6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T10:46:02Z","title_canon_sha256":"ef567e7a8ffe0e692db2d0eafb83509dd46f54a66dd76278c62535e71c98d94a"},"schema_version":"1.0","source":{"id":"2103.04318","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.04318","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"arxiv_version","alias_value":"2103.04318v1","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.04318","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"pith_short_12","alias_value":"JB64KHCTTPL5","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"pith_short_16","alias_value":"JB64KHCTTPL5Q7BJ","created_at":"2026-07-05T06:59:26Z"},{"alias_kind":"pith_short_8","alias_value":"JB64KHCT","created_at":"2026-07-05T06:59:26Z"}],"graph_snapshots":[{"event_id":"sha256:a9a5790d88d84fddb62a730aab7c63a05fdaffbcaf65ba4b321f70b05a9a687e","target":"graph","created_at":"2026-07-05T06:59:26Z","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/2103.04318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks are a versatile machine learning architecture that received a lot of attention recently. In this technical report, we present an implementation of convolution and pooling layers for TensorFlow-Keras models, which allows a seamless and flexible integration into standard Keras layers to set up graph models in a functional way. This implies the usage of mini-batches as the first tensor dimension, which can be realized via the new RaggedTensor class of TensorFlow best suited for graphs. We developed the Keras Graph Convolutional Neural Network Python package kgcnn based on Te","authors_text":"Andre Eberhard, Pascal Friederich, Patrick Reiser","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T10:46:02Z","title":"Implementing graph neural networks with TensorFlow-Keras"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.04318","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:a338f546a0f40cc5d571b6e61b6fc05e5a86f5b7324f078a83be3bf21aca7fa2","target":"record","created_at":"2026-07-05T06:59:26Z","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":"58fe64215d7e33194bac615f4e04930230c9aaee44333bd0891418beee7a10b6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-07T10:46:02Z","title_canon_sha256":"ef567e7a8ffe0e692db2d0eafb83509dd46f54a66dd76278c62535e71c98d94a"},"schema_version":"1.0","source":{"id":"2103.04318","kind":"arxiv","version":1}},"canonical_sha256":"487dc51c539bd7d87c29be33c80725033ef21ce9de40b9f2373aa19892c3dd5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"487dc51c539bd7d87c29be33c80725033ef21ce9de40b9f2373aa19892c3dd5b","first_computed_at":"2026-07-05T06:59:26.314883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:26.314883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6c8pQsvO99R3pOx/mZ2HCAiQM3OcfTwfU7mWposl85Erdtzau45FlXWjNOh0wndF+QvtzFcmLzIZm+y+sVN5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:26.315398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.04318","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a338f546a0f40cc5d571b6e61b6fc05e5a86f5b7324f078a83be3bf21aca7fa2","sha256:a9a5790d88d84fddb62a730aab7c63a05fdaffbcaf65ba4b321f70b05a9a687e"],"state_sha256":"c66c46d4b1731c39d9e25f26667628ddc25514963f1c107af5d17ad176cd1f48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyvr3WSXN7ghJwA3usDUBYH27PV91RzhiSbIEZcd1BDAqP+7QU9vqWWEJbzIh8psuOIAXvq/tKOHeWPK2yjkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T22:00:37.091231Z","bundle_sha256":"c25874eaf839dedb68fa5497b59a8027b0c3407de9c1d9d54b2e7e21d10734b5"}}