{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XP5CG3DTKEYQPLD3ZGK2LHLLDE","short_pith_number":"pith:XP5CG3DT","canonical_record":{"source":{"id":"1905.07443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-17T19:05:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6850c1422a27278cb1585c0bc0ee7efb541329af9cf5a902dda2e1ab7188538e","abstract_canon_sha256":"6bc500ea4c4111529d2d2172a7364aea98a6ea8bd00c9f3724f86450e5baf38a"},"schema_version":"1.0"},"canonical_sha256":"bbfa236c73513107ac7bc995a59d6b1932c45a26bbeb0480b42a2039eeeab06f","source":{"kind":"arxiv","id":"1905.07443","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07443","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07443v2","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07443","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"XP5CG3DTKEYQ","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"XP5CG3DTKEYQPLD3","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"XP5CG3DT","created_at":"2026-07-05T00:10:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XP5CG3DTKEYQPLD3ZGK2LHLLDE","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-17T19:05:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6850c1422a27278cb1585c0bc0ee7efb541329af9cf5a902dda2e1ab7188538e","abstract_canon_sha256":"6bc500ea4c4111529d2d2172a7364aea98a6ea8bd00c9f3724f86450e5baf38a"},"schema_version":"1.0"},"canonical_sha256":"bbfa236c73513107ac7bc995a59d6b1932c45a26bbeb0480b42a2039eeeab06f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:01.473980Z","signature_b64":"qB3yICYVAqlvEybXNmLqNcY1EMx1sbq3d3fVsvbtLsOiRuJGz6YVi3O0zzWh48vn78hHJiTtCEcYStK/T5M5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbfa236c73513107ac7bc995a59d6b1932c45a26bbeb0480b42a2039eeeab06f","last_reissued_at":"2026-07-05T00:10:01.473572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:01.473572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07443","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vjFEzN+nqU4gbT4Q+8puvaf0k/648eeZPQiohD5IwaOkTjfHxBWOFzvYPhCj7wl2S0PR85HHEe+rWm85vWfuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T06:30:21.367478Z"},"content_sha256":"8965e8475468be0754a03e154557da180ce11406e8b599888560fc8f34f27f44","schema_version":"1.0","event_id":"sha256:8965e8475468be0754a03e154557da180ce11406e8b599888560fc8f34f27f44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XP5CG3DTKEYQPLD3ZGK2LHLLDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AutoDispNet: Improving Disparity Estimation With AutoML","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arber Zela, Frank Hutter, Thomas Brox, Tonmoy Saikia, Yassine Marrakchi","submitted_at":"2019-05-17T19:05:25Z","abstract_excerpt":"Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches promise to relieve us from this effort. However, they are mainly designed for comparatively small-scale classification tasks. In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures. In particular, we leverage gradient-based neural architecture search and Bayesian optimization for hyperparameter search. The resulting optimization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07443","kind":"arxiv","version":2},"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/1905.07443/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":"2026-07-05T00:10:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yiTbeTQQGUd05/OrOrzTTmubkRE0Znr/vF/6u6QCAGRBx1YdL7t91W9nur3yK6F7qmfzpCY+vyw+7CWQ/Ud+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T06:30:21.367864Z"},"content_sha256":"f8ff0b81fefd35fdcb3d9eb8de9bed730e04cc946433839c6c120d32f3c17253","schema_version":"1.0","event_id":"sha256:f8ff0b81fefd35fdcb3d9eb8de9bed730e04cc946433839c6c120d32f3c17253"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE/bundle.json","state_url":"https://pith.science/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE/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":"2026-07-16T06:30:21Z","links":{"resolver":"https://pith.science/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE","bundle":"https://pith.science/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE/bundle.json","state":"https://pith.science/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XP5CG3DTKEYQPLD3ZGK2LHLLDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XP5CG3DTKEYQPLD3ZGK2LHLLDE","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":"6bc500ea4c4111529d2d2172a7364aea98a6ea8bd00c9f3724f86450e5baf38a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-17T19:05:25Z","title_canon_sha256":"6850c1422a27278cb1585c0bc0ee7efb541329af9cf5a902dda2e1ab7188538e"},"schema_version":"1.0","source":{"id":"1905.07443","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07443","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07443v2","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07443","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_12","alias_value":"XP5CG3DTKEYQ","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_16","alias_value":"XP5CG3DTKEYQPLD3","created_at":"2026-07-05T00:10:01Z"},{"alias_kind":"pith_short_8","alias_value":"XP5CG3DT","created_at":"2026-07-05T00:10:01Z"}],"graph_snapshots":[{"event_id":"sha256:f8ff0b81fefd35fdcb3d9eb8de9bed730e04cc946433839c6c120d32f3c17253","target":"graph","created_at":"2026-07-05T00:10:01Z","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/1905.07443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches promise to relieve us from this effort. However, they are mainly designed for comparatively small-scale classification tasks. In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures. In particular, we leverage gradient-based neural architecture search and Bayesian optimization for hyperparameter search. The resulting optimization","authors_text":"Arber Zela, Frank Hutter, Thomas Brox, Tonmoy Saikia, Yassine Marrakchi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-17T19:05:25Z","title":"AutoDispNet: Improving Disparity Estimation With AutoML"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07443","kind":"arxiv","version":2},"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":"sha256:8965e8475468be0754a03e154557da180ce11406e8b599888560fc8f34f27f44","target":"record","created_at":"2026-07-05T00:10:01Z","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":"6bc500ea4c4111529d2d2172a7364aea98a6ea8bd00c9f3724f86450e5baf38a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-17T19:05:25Z","title_canon_sha256":"6850c1422a27278cb1585c0bc0ee7efb541329af9cf5a902dda2e1ab7188538e"},"schema_version":"1.0","source":{"id":"1905.07443","kind":"arxiv","version":2}},"canonical_sha256":"bbfa236c73513107ac7bc995a59d6b1932c45a26bbeb0480b42a2039eeeab06f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbfa236c73513107ac7bc995a59d6b1932c45a26bbeb0480b42a2039eeeab06f","first_computed_at":"2026-07-05T00:10:01.473572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:01.473572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qB3yICYVAqlvEybXNmLqNcY1EMx1sbq3d3fVsvbtLsOiRuJGz6YVi3O0zzWh48vn78hHJiTtCEcYStK/T5M5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:01.473980Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07443","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8965e8475468be0754a03e154557da180ce11406e8b599888560fc8f34f27f44","sha256:f8ff0b81fefd35fdcb3d9eb8de9bed730e04cc946433839c6c120d32f3c17253"],"state_sha256":"efba10adc08bccfe014325dce2595cb68db8e57adb6bf838689d3cf430c3623c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NIFR3ANNtmOMw/BCBjGkUIh2Ce0KZ7feM+wbF0F82pV4Sodj4PKE86Oeoh5NDWc1scs7h3n/GAu77ABwIPOSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T06:30:21.370075Z","bundle_sha256":"dfaddf7895a980c4ccdd7eb3585454c597167271de555c69490066c54017606a"}}