{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YTFCICPYARNT4WIKFXR5HRFR4T","short_pith_number":"pith:YTFCICPY","canonical_record":{"source":{"id":"1704.06803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-22T14:02:01Z","cross_cats_sorted":["cs.IR","cs.NA","stat.ML"],"title_canon_sha256":"36a5e9fbae673f1f11698904a51c60a59f32fbe3558f02208659020cfcdfa3f6","abstract_canon_sha256":"3fa5bb2fb51c7a3194591a99282001df2137c233854d595debf30a7508c63e16"},"schema_version":"1.0"},"canonical_sha256":"c4ca2409f8045b3e590a2de3d3c4b1e4e81a2a2b55fd9b6d85c7d3858a4f5098","source":{"kind":"arxiv","id":"1704.06803","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06803","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06803v1","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06803","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"YTFCICPYARNT","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YTFCICPYARNT4WIK","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YTFCICPY","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YTFCICPYARNT4WIKFXR5HRFR4T","target":"record","payload":{"canonical_record":{"source":{"id":"1704.06803","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-22T14:02:01Z","cross_cats_sorted":["cs.IR","cs.NA","stat.ML"],"title_canon_sha256":"36a5e9fbae673f1f11698904a51c60a59f32fbe3558f02208659020cfcdfa3f6","abstract_canon_sha256":"3fa5bb2fb51c7a3194591a99282001df2137c233854d595debf30a7508c63e16"},"schema_version":"1.0"},"canonical_sha256":"c4ca2409f8045b3e590a2de3d3c4b1e4e81a2a2b55fd9b6d85c7d3858a4f5098","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:55.765181Z","signature_b64":"pmBxwWABetg1joIF4MNiMx95dndT2wbpU063SAaRCmi28ksVllabpSpc0rQdHB4Mm8BusyEqEfO7qTKLEtkGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4ca2409f8045b3e590a2de3d3c4b1e4e81a2a2b55fd9b6d85c7d3858a4f5098","last_reissued_at":"2026-05-18T00:45:55.764529Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:55.764529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.06803","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":"2026-05-18T00:45:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IVnd9Hq1nhT2g2IFOUOyapMBbNfVZ+r6h67xTO5Y4A6jJYppG5QSLv6xa1FahpTsNOws/A/eutpFIN5O752/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:51:26.809442Z"},"content_sha256":"d27041d2bb5d4cf1f5034c1df9a02e3bed80113100598d676e980fd81f4f9fbb","schema_version":"1.0","event_id":"sha256:d27041d2bb5d4cf1f5034c1df9a02e3bed80113100598d676e980fd81f4f9fbb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YTFCICPYARNT4WIKFXR5HRFR4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Federico Monti, Michael M. Bronstein, Xavier Bresson","submitted_at":"2017-04-22T14:02:01Z","abstract_excerpt":"Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of graphs, and imposing smoothness priors on these graphs. However, such techniques do not fully exploit the local stationarity structures of user/item graphs, and the number of parameters to learn is linear w.r.t. the number of users and items. We propose a novel approach to overcome these limitations by using geometric deep learning on graphs. Our matrix completio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06803","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":""},"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":"2026-05-18T00:45:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AyJIretA2JGjw7BtJHTtRYxD6fvcGZsKYwIh7awzhomEjLggR0+DXvb4UzpEZpZJEWxAD1Sy/xCJrh6pTPj0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:51:26.809866Z"},"content_sha256":"e3233a803232aeae68d22d35544cd0fbe3f69058e4006164e475f0c6f8b8982e","schema_version":"1.0","event_id":"sha256:e3233a803232aeae68d22d35544cd0fbe3f69058e4006164e475f0c6f8b8982e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YTFCICPYARNT4WIKFXR5HRFR4T/bundle.json","state_url":"https://pith.science/pith/YTFCICPYARNT4WIKFXR5HRFR4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YTFCICPYARNT4WIKFXR5HRFR4T/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":"2026-05-25T21:51:26Z","links":{"resolver":"https://pith.science/pith/YTFCICPYARNT4WIKFXR5HRFR4T","bundle":"https://pith.science/pith/YTFCICPYARNT4WIKFXR5HRFR4T/bundle.json","state":"https://pith.science/pith/YTFCICPYARNT4WIKFXR5HRFR4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YTFCICPYARNT4WIKFXR5HRFR4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YTFCICPYARNT4WIKFXR5HRFR4T","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":"3fa5bb2fb51c7a3194591a99282001df2137c233854d595debf30a7508c63e16","cross_cats_sorted":["cs.IR","cs.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-22T14:02:01Z","title_canon_sha256":"36a5e9fbae673f1f11698904a51c60a59f32fbe3558f02208659020cfcdfa3f6"},"schema_version":"1.0","source":{"id":"1704.06803","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.06803","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"arxiv_version","alias_value":"1704.06803v1","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.06803","created_at":"2026-05-18T00:45:55Z"},{"alias_kind":"pith_short_12","alias_value":"YTFCICPYARNT","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YTFCICPYARNT4WIK","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YTFCICPY","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:e3233a803232aeae68d22d35544cd0fbe3f69058e4006164e475f0c6f8b8982e","target":"graph","created_at":"2026-05-18T00:45:55Z","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":"Matrix completion models are among the most common formulations of recommender systems. Recent works have showed a boost of performance of these techniques when introducing the pairwise relationships between users/items in the form of graphs, and imposing smoothness priors on these graphs. However, such techniques do not fully exploit the local stationarity structures of user/item graphs, and the number of parameters to learn is linear w.r.t. the number of users and items. We propose a novel approach to overcome these limitations by using geometric deep learning on graphs. Our matrix completio","authors_text":"Federico Monti, Michael M. Bronstein, Xavier Bresson","cross_cats":["cs.IR","cs.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-22T14:02:01Z","title":"Geometric Matrix Completion with Recurrent Multi-Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.06803","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:d27041d2bb5d4cf1f5034c1df9a02e3bed80113100598d676e980fd81f4f9fbb","target":"record","created_at":"2026-05-18T00:45:55Z","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":"3fa5bb2fb51c7a3194591a99282001df2137c233854d595debf30a7508c63e16","cross_cats_sorted":["cs.IR","cs.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-22T14:02:01Z","title_canon_sha256":"36a5e9fbae673f1f11698904a51c60a59f32fbe3558f02208659020cfcdfa3f6"},"schema_version":"1.0","source":{"id":"1704.06803","kind":"arxiv","version":1}},"canonical_sha256":"c4ca2409f8045b3e590a2de3d3c4b1e4e81a2a2b55fd9b6d85c7d3858a4f5098","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4ca2409f8045b3e590a2de3d3c4b1e4e81a2a2b55fd9b6d85c7d3858a4f5098","first_computed_at":"2026-05-18T00:45:55.764529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:55.764529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pmBxwWABetg1joIF4MNiMx95dndT2wbpU063SAaRCmi28ksVllabpSpc0rQdHB4Mm8BusyEqEfO7qTKLEtkGBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:55.765181Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.06803","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d27041d2bb5d4cf1f5034c1df9a02e3bed80113100598d676e980fd81f4f9fbb","sha256:e3233a803232aeae68d22d35544cd0fbe3f69058e4006164e475f0c6f8b8982e"],"state_sha256":"ada834072d10d846511bbd7a9aa805fe4566a511a61114b532e2c3ab2039bff0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3ja7HHYmBWIcLLVylKxLN4d06vr56pwtIeKqRBsqOQUj2aC2ilb5rSSbLOMzIg3nTGsjaRoouzY7+Lnz0rwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:51:26.813338Z","bundle_sha256":"857c818198a96c8ca3c8c1c1854d31bcb12bb0a314df3afb3f3805a385eb9bb9"}}