{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TFGK3J3NJ6XOFG6O7CI6R6SKCB","short_pith_number":"pith:TFGK3J3N","canonical_record":{"source":{"id":"2106.12920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T16:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"79e657980bf76ff5faf71d7d0471e00201783cdc903010f801c9835829bb89c2","abstract_canon_sha256":"5bbc8a63b7ed8bd68cc70cb3c23e095f7705e68c559973cb3af1221aa31bc973"},"schema_version":"1.0"},"canonical_sha256":"994cada76d4faee29bcef891e8fa4a105b90ba4e1f9966f769dcf1c0aed0601b","source":{"kind":"arxiv","id":"2106.12920","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12920","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12920v1","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12920","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"pith_short_12","alias_value":"TFGK3J3NJ6XO","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"pith_short_16","alias_value":"TFGK3J3NJ6XOFG6O","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"pith_short_8","alias_value":"TFGK3J3N","created_at":"2026-07-05T02:52:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TFGK3J3NJ6XOFG6O7CI6R6SKCB","target":"record","payload":{"canonical_record":{"source":{"id":"2106.12920","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T16:04:25Z","cross_cats_sorted":[],"title_canon_sha256":"79e657980bf76ff5faf71d7d0471e00201783cdc903010f801c9835829bb89c2","abstract_canon_sha256":"5bbc8a63b7ed8bd68cc70cb3c23e095f7705e68c559973cb3af1221aa31bc973"},"schema_version":"1.0"},"canonical_sha256":"994cada76d4faee29bcef891e8fa4a105b90ba4e1f9966f769dcf1c0aed0601b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:07.488627Z","signature_b64":"eLxlDVSDOQ/PJppEcAy7526VtpKSe5JIP5VcB1E0PY1m7pdt0CiYKYCSpuss+JUVsBJaX0hchVCAOdlIeT49DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994cada76d4faee29bcef891e8fa4a105b90ba4e1f9966f769dcf1c0aed0601b","last_reissued_at":"2026-07-05T02:52:07.488137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:07.488137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.12920","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":"2026-07-05T02:52:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dE8QUp1UcIecRKFpdpN671yFFBWIL943Xg63RyMU+zu6I0nMYSekw00sdfeP0KiKArCcJm7AazKzk0Sk4AvtDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:40:01.191658Z"},"content_sha256":"1cfe840edcc7a4c732a784f4bb6201415171c2eaeac552b7515cebd06da49b2b","schema_version":"1.0","event_id":"sha256:1cfe840edcc7a4c732a784f4bb6201415171c2eaeac552b7515cebd06da49b2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TFGK3J3NJ6XOFG6O7CI6R6SKCB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learnt Sparsification for Interpretable Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Avishek Anand, Mandeep Rathee, Megha Khosla, Thorben Funke, Zijian Zhang","submitted_at":"2021-06-23T16:04:25Z","abstract_excerpt":"Graph neural networks (GNNs) have achieved great success on various tasks and fields that require relational modeling. GNNs aggregate node features using the graph structure as inductive biases resulting in flexible and powerful models. However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned. In this paper, we propose a novel method called Kedge for explicitly sparsifying the underlying graph by removing unnecessary neighbors. Our key idea is based on a tractable method for sparsification using the Hard Kumaraswamy distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12920","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/2106.12920/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K6NwCW5jRc2IQmWbU209+h8V+lHOAV6fwo6L8H/st+mRkld4xEkjj5CMwXsAPbb26u7JmwO4OOvfgOQqyLwzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:40:01.192248Z"},"content_sha256":"9388137e35af2c52c6c9d3c49a2fa4ee53e0827f953d4b5bc80b7e92c51004da","schema_version":"1.0","event_id":"sha256:9388137e35af2c52c6c9d3c49a2fa4ee53e0827f953d4b5bc80b7e92c51004da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB/bundle.json","state_url":"https://pith.science/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB/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":"2026-08-03T15:40:01Z","links":{"resolver":"https://pith.science/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB","bundle":"https://pith.science/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB/bundle.json","state":"https://pith.science/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TFGK3J3NJ6XOFG6O7CI6R6SKCB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TFGK3J3NJ6XOFG6O7CI6R6SKCB","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":"5bbc8a63b7ed8bd68cc70cb3c23e095f7705e68c559973cb3af1221aa31bc973","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T16:04:25Z","title_canon_sha256":"79e657980bf76ff5faf71d7d0471e00201783cdc903010f801c9835829bb89c2"},"schema_version":"1.0","source":{"id":"2106.12920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12920","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12920v1","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12920","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"pith_short_12","alias_value":"TFGK3J3NJ6XO","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"pith_short_16","alias_value":"TFGK3J3NJ6XOFG6O","created_at":"2026-07-05T02:52:07Z"},{"alias_kind":"pith_short_8","alias_value":"TFGK3J3N","created_at":"2026-07-05T02:52:07Z"}],"graph_snapshots":[{"event_id":"sha256:9388137e35af2c52c6c9d3c49a2fa4ee53e0827f953d4b5bc80b7e92c51004da","target":"graph","created_at":"2026-07-05T02:52:07Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.12920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph neural networks (GNNs) have achieved great success on various tasks and fields that require relational modeling. GNNs aggregate node features using the graph structure as inductive biases resulting in flexible and powerful models. However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned. In this paper, we propose a novel method called Kedge for explicitly sparsifying the underlying graph by removing unnecessary neighbors. Our key idea is based on a tractable method for sparsification using the Hard Kumaraswamy distributi","authors_text":"Avishek Anand, Mandeep Rathee, Megha Khosla, Thorben Funke, Zijian Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T16:04:25Z","title":"Learnt Sparsification for Interpretable Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12920","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":"sha256:1cfe840edcc7a4c732a784f4bb6201415171c2eaeac552b7515cebd06da49b2b","target":"record","created_at":"2026-07-05T02:52:07Z","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":"5bbc8a63b7ed8bd68cc70cb3c23e095f7705e68c559973cb3af1221aa31bc973","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T16:04:25Z","title_canon_sha256":"79e657980bf76ff5faf71d7d0471e00201783cdc903010f801c9835829bb89c2"},"schema_version":"1.0","source":{"id":"2106.12920","kind":"arxiv","version":1}},"canonical_sha256":"994cada76d4faee29bcef891e8fa4a105b90ba4e1f9966f769dcf1c0aed0601b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"994cada76d4faee29bcef891e8fa4a105b90ba4e1f9966f769dcf1c0aed0601b","first_computed_at":"2026-07-05T02:52:07.488137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:07.488137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eLxlDVSDOQ/PJppEcAy7526VtpKSe5JIP5VcB1E0PY1m7pdt0CiYKYCSpuss+JUVsBJaX0hchVCAOdlIeT49DA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:07.488627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.12920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cfe840edcc7a4c732a784f4bb6201415171c2eaeac552b7515cebd06da49b2b","sha256:9388137e35af2c52c6c9d3c49a2fa4ee53e0827f953d4b5bc80b7e92c51004da"],"state_sha256":"4bd8501506570c583f7835571edde8043ad387eea16ecc5bf1206dd31df43287"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+S0hGl48dlclt1spWZJMGtmJnPDKp1kzwrBgIAekKcQVDVdvrhfQKRt26p9uF4sj/6nzxWtV2yJk8xbzVfivCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:40:01.196345Z","bundle_sha256":"aa02f667142bbf64af610dc55a4c4ea0411811606c5231b16a892274850fe92b"}}