{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FMJMSB7WEYNCFQL6OCMFIX37QF","short_pith_number":"pith:FMJMSB7W","schema_version":"1.0","canonical_sha256":"2b12c907f6261a22c17e7098545f7f81726718b9535b96120f213ee232300110","source":{"kind":"arxiv","id":"2407.05649","version":5},"attestation_state":"computed","paper":{"title":"Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Tongzhou Liao","submitted_at":"2024-07-08T06:21:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) have become important tools for machine learning on graph-structured data. In this paper, we explore the synergistic combination of graph encoding, graph rewiring, and graph attention, by introducing Graph Attention with Stochastic Structures (GRASS), a novel GNN architecture. GRASS utilizes relative random walk probabilities (RRWP) encoding and a novel decomposed variant (D-RRWP) to efficiently capture structural information. It rewires the input graph by superimposing a random regular graph to enhance long-range information propagation. It also employs a novel ad"},"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":"2407.05649","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-08T06:21:56Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"a790b0f00acfe0f8e1ebe3be272e52438c7daa71eea8ac83cef17305267ebc06","abstract_canon_sha256":"d369c4a8041bfb99ba336e5c962cf6602b9fe22dd396b191261d6dc0225c928e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:44.839183Z","signature_b64":"ScH6KEYTDJWCxum+GIUCJgsbHxguQYgtncj2KdXx+cVR3Iozjk7liDWNXgDcRcVNGFQ8AwrERij1FM2hKcvjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b12c907f6261a22c17e7098545f7f81726718b9535b96120f213ee232300110","last_reissued_at":"2026-07-05T10:31:44.838454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:44.838454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Tongzhou Liao","submitted_at":"2024-07-08T06:21:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) have become important tools for machine learning on graph-structured data. In this paper, we explore the synergistic combination of graph encoding, graph rewiring, and graph attention, by introducing Graph Attention with Stochastic Structures (GRASS), a novel GNN architecture. GRASS utilizes relative random walk probabilities (RRWP) encoding and a novel decomposed variant (D-RRWP) to efficiently capture structural information. It rewires the input graph by superimposing a random regular graph to enhance long-range information propagation. It also employs a novel ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05649","kind":"arxiv","version":5},"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/2407.05649/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":"2407.05649","created_at":"2026-07-05T10:31:44.838540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05649v5","created_at":"2026-07-05T10:31:44.838540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05649","created_at":"2026-07-05T10:31:44.838540+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMJMSB7WEYNC","created_at":"2026-07-05T10:31:44.838540+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMJMSB7WEYNCFQL6","created_at":"2026-07-05T10:31:44.838540+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMJMSB7W","created_at":"2026-07-05T10:31:44.838540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06751","citing_title":"What makes a good feedforward computational graph?","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF","json":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF.json","graph_json":"https://pith.science/api/pith-number/FMJMSB7WEYNCFQL6OCMFIX37QF/graph.json","events_json":"https://pith.science/api/pith-number/FMJMSB7WEYNCFQL6OCMFIX37QF/events.json","paper":"https://pith.science/paper/FMJMSB7W"},"agent_actions":{"view_html":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF","download_json":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF.json","view_paper":"https://pith.science/paper/FMJMSB7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05649&json=true","fetch_graph":"https://pith.science/api/pith-number/FMJMSB7WEYNCFQL6OCMFIX37QF/graph.json","fetch_events":"https://pith.science/api/pith-number/FMJMSB7WEYNCFQL6OCMFIX37QF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF/action/storage_attestation","attest_author":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF/action/author_attestation","sign_citation":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF/action/citation_signature","submit_replication":"https://pith.science/pith/FMJMSB7WEYNCFQL6OCMFIX37QF/action/replication_record"}},"created_at":"2026-07-05T10:31:44.838540+00:00","updated_at":"2026-07-05T10:31:44.838540+00:00"}