{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QBWNLXDYYEO4P7G6HXAA3V4ZTM","short_pith_number":"pith:QBWNLXDY","schema_version":"1.0","canonical_sha256":"806cd5dc78c11dc7fcde3dc00dd7999b2544a620d189ea0ff306b45f26910e01","source":{"kind":"arxiv","id":"2310.09486","version":4},"attestation_state":"computed","paper":{"title":"Mirage: Model-Agnostic Graph Distillation for Graph Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hariprasad Kodamana, Mridul Gupta, Sahil Manchanda, Sayan Ranu","submitted_at":"2023-10-14T04:21:52Z","abstract_excerpt":"GNNs, like other deep learning models, are data and computation hungry. There is a pressing need to scale training of GNNs on large datasets to enable their usage on low-resource environments. Graph distillation is an effort in that direction with the aim to construct a smaller synthetic training set from the original training data without significantly compromising model performance. While initial efforts are promising, this work is motivated by two key observations: (1) Existing graph distillation algorithms themselves rely on training with the full dataset, which undermines the very premise"},"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":"2310.09486","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-14T04:21:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2e14e9c10069a877a9fade888e731903f7e3a55e0e1fac6c636d744c06a413e","abstract_canon_sha256":"cdd9b2dfce16a3d14eb9b6d8b2743fde5c55eff1f7cdbb5796337212aa2e019a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:46.861338Z","signature_b64":"IZiQSqvSqMilYRNdfxlkecOAPo2pgLT2J5C5KKqrYX5G+t8OOmO4dXXUZmOCOcVd5Nvs1kJnjfoHGrPBO5zwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"806cd5dc78c11dc7fcde3dc00dd7999b2544a620d189ea0ff306b45f26910e01","last_reissued_at":"2026-07-05T08:02:46.860767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:46.860767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirage: Model-Agnostic Graph Distillation for Graph Classification","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hariprasad Kodamana, Mridul Gupta, Sahil Manchanda, Sayan Ranu","submitted_at":"2023-10-14T04:21:52Z","abstract_excerpt":"GNNs, like other deep learning models, are data and computation hungry. There is a pressing need to scale training of GNNs on large datasets to enable their usage on low-resource environments. Graph distillation is an effort in that direction with the aim to construct a smaller synthetic training set from the original training data without significantly compromising model performance. While initial efforts are promising, this work is motivated by two key observations: (1) Existing graph distillation algorithms themselves rely on training with the full dataset, which undermines the very premise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09486","kind":"arxiv","version":4},"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/2310.09486/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":"2310.09486","created_at":"2026-07-05T08:02:46.860850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.09486v4","created_at":"2026-07-05T08:02:46.860850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09486","created_at":"2026-07-05T08:02:46.860850+00:00"},{"alias_kind":"pith_short_12","alias_value":"QBWNLXDYYEO4","created_at":"2026-07-05T08:02:46.860850+00:00"},{"alias_kind":"pith_short_16","alias_value":"QBWNLXDYYEO4P7G6","created_at":"2026-07-05T08:02:46.860850+00:00"},{"alias_kind":"pith_short_8","alias_value":"QBWNLXDY","created_at":"2026-07-05T08:02:46.860850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02854","citing_title":"TD3: Tucker Decomposition Based Dataset Distillation Method for Sequential Recommendation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM","json":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM.json","graph_json":"https://pith.science/api/pith-number/QBWNLXDYYEO4P7G6HXAA3V4ZTM/graph.json","events_json":"https://pith.science/api/pith-number/QBWNLXDYYEO4P7G6HXAA3V4ZTM/events.json","paper":"https://pith.science/paper/QBWNLXDY"},"agent_actions":{"view_html":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM","download_json":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM.json","view_paper":"https://pith.science/paper/QBWNLXDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.09486&json=true","fetch_graph":"https://pith.science/api/pith-number/QBWNLXDYYEO4P7G6HXAA3V4ZTM/graph.json","fetch_events":"https://pith.science/api/pith-number/QBWNLXDYYEO4P7G6HXAA3V4ZTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM/action/storage_attestation","attest_author":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM/action/author_attestation","sign_citation":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM/action/citation_signature","submit_replication":"https://pith.science/pith/QBWNLXDYYEO4P7G6HXAA3V4ZTM/action/replication_record"}},"created_at":"2026-07-05T08:02:46.860850+00:00","updated_at":"2026-07-05T08:02:46.860850+00:00"}