{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RZX4S56NRW7HHGKVZNPXZ2SJKR","short_pith_number":"pith:RZX4S56N","schema_version":"1.0","canonical_sha256":"8e6fc977cd8dbe739955cb5f7cea4954638c38f84f58fbf8d292a6194b5b608e","source":{"kind":"arxiv","id":"1912.08409","version":1},"attestation_state":"computed","paper":{"title":"CoulGAT: An Experiment on Interpretability of Graph Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Burc Gokden","submitted_at":"2019-12-18T06:46:39Z","abstract_excerpt":"We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework (CoulGAT) developed for this purpose. Using CoulGAT, a forest of plain and resnet models were trained and characterized using this attention mechanism against CHAMPS dataset. The learnable variables of the attention mechanism are used to extract node-node and node-feature interactions to define an empirical standard model for the graph structure and hidden l"},"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":"1912.08409","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-18T06:46:39Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0d37e13ee900075b87a50475827ac6e751fe1dce6267d026f4356a3933e53002","abstract_canon_sha256":"3e1bbd24037a5d9a5418e543b29d32e5ab27296fd460b4c30cb12f0ae81e8e0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:27:02.533861Z","signature_b64":"lOxRFpG0oUSYzJubHDQ72o0tHlSal9gOAMtSr7j39QFfZqEaCaV6x3L2SzgdG0mbgfiZZou1/MtpJ14PalKAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e6fc977cd8dbe739955cb5f7cea4954638c38f84f58fbf8d292a6194b5b608e","last_reissued_at":"2026-07-05T00:27:02.533374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:27:02.533374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoulGAT: An Experiment on Interpretability of Graph Attention Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Burc Gokden","submitted_at":"2019-12-18T06:46:39Z","abstract_excerpt":"We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by using a flexible and scalable framework (CoulGAT) developed for this purpose. Using CoulGAT, a forest of plain and resnet models were trained and characterized using this attention mechanism against CHAMPS dataset. The learnable variables of the attention mechanism are used to extract node-node and node-feature interactions to define an empirical standard model for the graph structure and hidden l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.08409","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/1912.08409/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":"1912.08409","created_at":"2026-07-05T00:27:02.533431+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.08409v1","created_at":"2026-07-05T00:27:02.533431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.08409","created_at":"2026-07-05T00:27:02.533431+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZX4S56NRW7H","created_at":"2026-07-05T00:27:02.533431+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZX4S56NRW7HHGKV","created_at":"2026-07-05T00:27:02.533431+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZX4S56N","created_at":"2026-07-05T00:27:02.533431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10288","citing_title":"Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR","json":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR.json","graph_json":"https://pith.science/api/pith-number/RZX4S56NRW7HHGKVZNPXZ2SJKR/graph.json","events_json":"https://pith.science/api/pith-number/RZX4S56NRW7HHGKVZNPXZ2SJKR/events.json","paper":"https://pith.science/paper/RZX4S56N"},"agent_actions":{"view_html":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR","download_json":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR.json","view_paper":"https://pith.science/paper/RZX4S56N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.08409&json=true","fetch_graph":"https://pith.science/api/pith-number/RZX4S56NRW7HHGKVZNPXZ2SJKR/graph.json","fetch_events":"https://pith.science/api/pith-number/RZX4S56NRW7HHGKVZNPXZ2SJKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR/action/storage_attestation","attest_author":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR/action/author_attestation","sign_citation":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR/action/citation_signature","submit_replication":"https://pith.science/pith/RZX4S56NRW7HHGKVZNPXZ2SJKR/action/replication_record"}},"created_at":"2026-07-05T00:27:02.533431+00:00","updated_at":"2026-07-05T00:27:02.533431+00:00"}