{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H5UD2MYYJTLDACWEQ3AKHTQ4EA","short_pith_number":"pith:H5UD2MYY","schema_version":"1.0","canonical_sha256":"3f683d33184cd6300ac486c0a3ce1c2011df30c308fcf9840002876bed17b18e","source":{"kind":"arxiv","id":"2601.15133","version":3},"attestation_state":"computed","paper":{"title":"Building Deep Graph Predictors with Graph Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andr\\'e Eberhard, Gerhard Neumann, Pascal Friederich","submitted_at":"2026-01-21T16:07:17Z","abstract_excerpt":"Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the effectiveness of training neural networks with backpropagation and gradient descent. We argue that representing graphs on a fixed-size Euclidean grid, as is common in recently proposed models for supervised graph prediction, may not be the optimal choice in these settings"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.15133","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-21T16:07:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"458952ebacd03cc1ea31b827154736592b86a3a588c1bfae798c5960323c08bf","abstract_canon_sha256":"17ce9ef8ca5c2d87b837ca63934ad3678a00183f74b3b0f099aaab17c899d113"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:04:57.341986Z","signature_b64":"VimzDMCXevMKg2R6UfVqzC5fINAR4cL0L/0qQC1DQ8kD5fDjwrM4aBbBmlQdqyzP2yhoyzJYfR+Fu/wCqadeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f683d33184cd6300ac486c0a3ce1c2011df30c308fcf9840002876bed17b18e","last_reissued_at":"2026-05-21T02:04:57.341070Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:04:57.341070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building Deep Graph Predictors with Graph Imitation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Andr\\'e Eberhard, Gerhard Neumann, Pascal Friederich","submitted_at":"2026-01-21T16:07:17Z","abstract_excerpt":"Recent years have seen substantial progress in neural generation of text, images, and audio, supported by mature training pipelines and large-scale optimization. For graphs, however, comparable progress has been more limited. We attribute this gap to graph-specific optimization and representation challenges that undermine the effectiveness of training neural networks with backpropagation and gradient descent. We argue that representing graphs on a fixed-size Euclidean grid, as is common in recently proposed models for supervised graph prediction, may not be the optimal choice in these settings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.15133","kind":"arxiv","version":3},"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/2601.15133/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.15133","created_at":"2026-05-21T02:04:57.341232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.15133v3","created_at":"2026-05-21T02:04:57.341232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.15133","created_at":"2026-05-21T02:04:57.341232+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5UD2MYYJTLD","created_at":"2026-05-21T02:04:57.341232+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5UD2MYYJTLDACWE","created_at":"2026-05-21T02:04:57.341232+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5UD2MYY","created_at":"2026-05-21T02:04:57.341232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA","json":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA.json","graph_json":"https://pith.science/api/pith-number/H5UD2MYYJTLDACWEQ3AKHTQ4EA/graph.json","events_json":"https://pith.science/api/pith-number/H5UD2MYYJTLDACWEQ3AKHTQ4EA/events.json","paper":"https://pith.science/paper/H5UD2MYY"},"agent_actions":{"view_html":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA","download_json":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA.json","view_paper":"https://pith.science/paper/H5UD2MYY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.15133&json=true","fetch_graph":"https://pith.science/api/pith-number/H5UD2MYYJTLDACWEQ3AKHTQ4EA/graph.json","fetch_events":"https://pith.science/api/pith-number/H5UD2MYYJTLDACWEQ3AKHTQ4EA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA/action/storage_attestation","attest_author":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA/action/author_attestation","sign_citation":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA/action/citation_signature","submit_replication":"https://pith.science/pith/H5UD2MYYJTLDACWEQ3AKHTQ4EA/action/replication_record"}},"created_at":"2026-05-21T02:04:57.341232+00:00","updated_at":"2026-05-21T02:04:57.341232+00:00"}