{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3U53WMBUCPQK3WVTR5ZH375WID","short_pith_number":"pith:3U53WMBU","canonical_record":{"source":{"id":"1910.14388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-31T11:38:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"56e61aa2863d9c854706c6d7fda5e9e3f063a29cee4b314daf044b2114ff3c49","abstract_canon_sha256":"a815bb3a5014184e6ce5fd235b031c336da3f48a4b1de9abada019e6bc443013"},"schema_version":"1.0"},"canonical_sha256":"dd3bbb303413e0addab38f727dffb640df9b116db5d9cf127dfdeb738b04bd20","source":{"kind":"arxiv","id":"1910.14388","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.14388","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"1910.14388v1","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14388","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"3U53WMBUCPQK","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"3U53WMBUCPQK3WVT","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"3U53WMBU","created_at":"2026-07-05T00:16:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3U53WMBUCPQK3WVTR5ZH375WID","target":"record","payload":{"canonical_record":{"source":{"id":"1910.14388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-31T11:38:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"56e61aa2863d9c854706c6d7fda5e9e3f063a29cee4b314daf044b2114ff3c49","abstract_canon_sha256":"a815bb3a5014184e6ce5fd235b031c336da3f48a4b1de9abada019e6bc443013"},"schema_version":"1.0"},"canonical_sha256":"dd3bbb303413e0addab38f727dffb640df9b116db5d9cf127dfdeb738b04bd20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:10.194332Z","signature_b64":"2PBk/jHc4RgHfuXQewYWKrnfx60v7ujA7c06uir61JHsxqJSNEVUltx9Y/wYIqWgwosIEjXrylHzIWpzStVICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd3bbb303413e0addab38f727dffb640df9b116db5d9cf127dfdeb738b04bd20","last_reissued_at":"2026-07-05T00:16:10.193795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:10.193795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.14388","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":"2026-07-05T00:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2QDcMS/+azk5dW1lrZkeE8h0BfbgGgr3NqWJR9zqWuf/CAcMkw/sFy63N5WFxt3072Q3e+obCG571yRMC288Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:46:14.180913Z"},"content_sha256":"35eadef9b27384dbca39daca3325ebc61ff243aa597832cfd09788755a966773","schema_version":"1.0","event_id":"sha256:35eadef9b27384dbca39daca3325ebc61ff243aa597832cfd09788755a966773"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3U53WMBUCPQK3WVTR5ZH375WID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Image-Conditioned Graph Generation for Road Network Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Davide Belli, Thomas Kipf","submitted_at":"2019-10-31T11:38:13Z","abstract_excerpt":"Deep generative models for graphs have shown great promise in the area of drug design, but have so far found little application beyond generating graph-structured molecules. In this work, we demonstrate a proof of concept for the challenging task of road network extraction from image data. This task can be framed as image-conditioned graph generation, for which we develop the Generative Graph Transformer (GGT), a deep autoregressive model that makes use of attention mechanisms for image conditioning and the recurrent generation of graphs. We benchmark GGT on the application of road network ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14388","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/1910.14388/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":"2026-07-05T00:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A808utc8UFxIulSS/UxR2LTTtJA0lJoSVGlXxSdDOqOY23VpRXSrco4ESxSRJrH7mJopWrjwKcPobz+XHca6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T23:46:14.181527Z"},"content_sha256":"7685c20faa8e86cf05192d8758d12af046ef23cfe9b7839558876b28bd2c2322","schema_version":"1.0","event_id":"sha256:7685c20faa8e86cf05192d8758d12af046ef23cfe9b7839558876b28bd2c2322"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3U53WMBUCPQK3WVTR5ZH375WID/bundle.json","state_url":"https://pith.science/pith/3U53WMBUCPQK3WVTR5ZH375WID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3U53WMBUCPQK3WVTR5ZH375WID/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":"2026-08-21T23:46:14Z","links":{"resolver":"https://pith.science/pith/3U53WMBUCPQK3WVTR5ZH375WID","bundle":"https://pith.science/pith/3U53WMBUCPQK3WVTR5ZH375WID/bundle.json","state":"https://pith.science/pith/3U53WMBUCPQK3WVTR5ZH375WID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3U53WMBUCPQK3WVTR5ZH375WID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3U53WMBUCPQK3WVTR5ZH375WID","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":"a815bb3a5014184e6ce5fd235b031c336da3f48a4b1de9abada019e6bc443013","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-31T11:38:13Z","title_canon_sha256":"56e61aa2863d9c854706c6d7fda5e9e3f063a29cee4b314daf044b2114ff3c49"},"schema_version":"1.0","source":{"id":"1910.14388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.14388","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"1910.14388v1","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14388","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"3U53WMBUCPQK","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"pith_short_16","alias_value":"3U53WMBUCPQK3WVT","created_at":"2026-07-05T00:16:10Z"},{"alias_kind":"pith_short_8","alias_value":"3U53WMBU","created_at":"2026-07-05T00:16:10Z"}],"graph_snapshots":[{"event_id":"sha256:7685c20faa8e86cf05192d8758d12af046ef23cfe9b7839558876b28bd2c2322","target":"graph","created_at":"2026-07-05T00:16:10Z","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/1910.14388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep generative models for graphs have shown great promise in the area of drug design, but have so far found little application beyond generating graph-structured molecules. In this work, we demonstrate a proof of concept for the challenging task of road network extraction from image data. This task can be framed as image-conditioned graph generation, for which we develop the Generative Graph Transformer (GGT), a deep autoregressive model that makes use of attention mechanisms for image conditioning and the recurrent generation of graphs. We benchmark GGT on the application of road network ext","authors_text":"Davide Belli, Thomas Kipf","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-31T11:38:13Z","title":"Image-Conditioned Graph Generation for Road Network Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14388","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":"sha256:35eadef9b27384dbca39daca3325ebc61ff243aa597832cfd09788755a966773","target":"record","created_at":"2026-07-05T00:16:10Z","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":"a815bb3a5014184e6ce5fd235b031c336da3f48a4b1de9abada019e6bc443013","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-31T11:38:13Z","title_canon_sha256":"56e61aa2863d9c854706c6d7fda5e9e3f063a29cee4b314daf044b2114ff3c49"},"schema_version":"1.0","source":{"id":"1910.14388","kind":"arxiv","version":1}},"canonical_sha256":"dd3bbb303413e0addab38f727dffb640df9b116db5d9cf127dfdeb738b04bd20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd3bbb303413e0addab38f727dffb640df9b116db5d9cf127dfdeb738b04bd20","first_computed_at":"2026-07-05T00:16:10.193795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:16:10.193795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PBk/jHc4RgHfuXQewYWKrnfx60v7ujA7c06uir61JHsxqJSNEVUltx9Y/wYIqWgwosIEjXrylHzIWpzStVICA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:16:10.194332Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.14388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35eadef9b27384dbca39daca3325ebc61ff243aa597832cfd09788755a966773","sha256:7685c20faa8e86cf05192d8758d12af046ef23cfe9b7839558876b28bd2c2322"],"state_sha256":"4d8d8ab29656df119da33431b73053a64d95774d4702e3bce1fe65f463be4b0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mZJb9XPX7kWgjlNpkOuk+Oicv8rDBar9fK1g4caGCoPqxGqv42YFvLxFKqnPfECaRyEB6CXb8yjIh16j4XkpCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T23:46:14.185299Z","bundle_sha256":"2516c931854ddb4babfb990fdb7fb6c769b301390785276c75ae230d6b451f77"}}