{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QMK47YLD6MW7SH2DYQWXQQIWPG","short_pith_number":"pith:QMK47YLD","canonical_record":{"source":{"id":"1904.06587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-13T19:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"a5c775cfc55f9b51cdbc847f140e31ab265587f570708fea411bac3b4d067241","abstract_canon_sha256":"f407f27440dd5b004b5845fe7d085d753b695e7d4eba372880ae9849becefb83"},"schema_version":"1.0"},"canonical_sha256":"8315cfe163f32df91f43c42d784116798ab0d8cf13a4f70c2ea9878731d585e4","source":{"kind":"arxiv","id":"1904.06587","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06587","created_at":"2026-05-17T23:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06587v1","created_at":"2026-05-17T23:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06587","created_at":"2026-05-17T23:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"QMK47YLD6MW7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QMK47YLD6MW7SH2D","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QMK47YLD","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QMK47YLD6MW7SH2DYQWXQQIWPG","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-13T19:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"a5c775cfc55f9b51cdbc847f140e31ab265587f570708fea411bac3b4d067241","abstract_canon_sha256":"f407f27440dd5b004b5845fe7d085d753b695e7d4eba372880ae9849becefb83"},"schema_version":"1.0"},"canonical_sha256":"8315cfe163f32df91f43c42d784116798ab0d8cf13a4f70c2ea9878731d585e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:38.754430Z","signature_b64":"WuAgAm7IRGKo+9yIiQd+QHVysU9JNAY0ClgFG9hRVjJj6GttOPdVmDb3Ob+Jf423L+qmfYy+BAmhhuPvGzEYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8315cfe163f32df91f43c42d784116798ab0d8cf13a4f70c2ea9878731d585e4","last_reissued_at":"2026-05-17T23:48:38.753825Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:38.753825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06587","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":"2026-05-17T23:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kvz1DtFXSMs710mLokduFX7QkVySb4Jcpo/K5NPNcgarUbFAo22bb67XodfJxUCgKFpQS5EM0epO3IHkgUhzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:03:55.440815Z"},"content_sha256":"6c60f58a2ce8b9a90b1848d57de4a73f643f6136565a4d6a5992f6bdd6cf5beb","schema_version":"1.0","event_id":"sha256:6c60f58a2ce8b9a90b1848d57de4a73f643f6136565a4d6a5992f6bdd6cf5beb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QMK47YLD6MW7SH2DYQWXQQIWPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feihu Zhang, Philip H.S. Torr, Ruigang Yang, Victor Prisacariu","submitted_at":"2019-04-13T19:30:13Z","abstract_excerpt":"In the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06587","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":""},"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":"2026-05-17T23:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h1st+3iYZHlplZVh58dt9yLOYcOn31YuwBMD+Ml0ihYiXZiHGHimil+gsSdag6Fy72+IJYw8I0x27E8qeoDVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:03:55.441466Z"},"content_sha256":"3fb100457717e105434fbe4cffe16205299b60fe5ee3a76f42000b1b1ad1c030","schema_version":"1.0","event_id":"sha256:3fb100457717e105434fbe4cffe16205299b60fe5ee3a76f42000b1b1ad1c030"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QMK47YLD6MW7SH2DYQWXQQIWPG/bundle.json","state_url":"https://pith.science/pith/QMK47YLD6MW7SH2DYQWXQQIWPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QMK47YLD6MW7SH2DYQWXQQIWPG/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":"2026-05-29T16:03:55Z","links":{"resolver":"https://pith.science/pith/QMK47YLD6MW7SH2DYQWXQQIWPG","bundle":"https://pith.science/pith/QMK47YLD6MW7SH2DYQWXQQIWPG/bundle.json","state":"https://pith.science/pith/QMK47YLD6MW7SH2DYQWXQQIWPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QMK47YLD6MW7SH2DYQWXQQIWPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QMK47YLD6MW7SH2DYQWXQQIWPG","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":"f407f27440dd5b004b5845fe7d085d753b695e7d4eba372880ae9849becefb83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-13T19:30:13Z","title_canon_sha256":"a5c775cfc55f9b51cdbc847f140e31ab265587f570708fea411bac3b4d067241"},"schema_version":"1.0","source":{"id":"1904.06587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06587","created_at":"2026-05-17T23:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06587v1","created_at":"2026-05-17T23:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06587","created_at":"2026-05-17T23:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"QMK47YLD6MW7","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QMK47YLD6MW7SH2D","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QMK47YLD","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:3fb100457717e105434fbe4cffe16205299b60fe5ee3a76f42000b1b1ad1c030","target":"graph","created_at":"2026-05-17T23:48:38Z","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"},"paper":{"abstract_excerpt":"In the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutiona","authors_text":"Feihu Zhang, Philip H.S. Torr, Ruigang Yang, Victor Prisacariu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-13T19:30:13Z","title":"GA-Net: Guided Aggregation Net for End-to-end Stereo Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06587","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":"sha256:6c60f58a2ce8b9a90b1848d57de4a73f643f6136565a4d6a5992f6bdd6cf5beb","target":"record","created_at":"2026-05-17T23:48:38Z","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":"f407f27440dd5b004b5845fe7d085d753b695e7d4eba372880ae9849becefb83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-13T19:30:13Z","title_canon_sha256":"a5c775cfc55f9b51cdbc847f140e31ab265587f570708fea411bac3b4d067241"},"schema_version":"1.0","source":{"id":"1904.06587","kind":"arxiv","version":1}},"canonical_sha256":"8315cfe163f32df91f43c42d784116798ab0d8cf13a4f70c2ea9878731d585e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8315cfe163f32df91f43c42d784116798ab0d8cf13a4f70c2ea9878731d585e4","first_computed_at":"2026-05-17T23:48:38.753825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:38.753825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WuAgAm7IRGKo+9yIiQd+QHVysU9JNAY0ClgFG9hRVjJj6GttOPdVmDb3Ob+Jf423L+qmfYy+BAmhhuPvGzEYAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:38.754430Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c60f58a2ce8b9a90b1848d57de4a73f643f6136565a4d6a5992f6bdd6cf5beb","sha256:3fb100457717e105434fbe4cffe16205299b60fe5ee3a76f42000b1b1ad1c030"],"state_sha256":"ae8a5cba7d89a0e500dfa6261b09941cff3dcb6922973ab8efbbc56cc5f09de6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z/xmRVEt8L8AIg1BKMLiAo1wElnzkESkAiDDVP74Dj8rtbfS3T9dhWKQsRxDedgKL/mPEqohn8HCE9iZ3v5zDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:03:55.444469Z","bundle_sha256":"8578469e70c1c66053c416a17e341f05895c1cc3dd007b54d77218536019d9d9"}}