{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GVG62JL45FBHR6IJ6TTOFRNGWC","short_pith_number":"pith:GVG62JL4","canonical_record":{"source":{"id":"2103.16694","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T21:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"c6fde76648b7d5d8c979d79f3662fc14e9fdf3ee4eb3488689a50e525a8a1507","abstract_canon_sha256":"b9d3e3e10cda2843b1cdcbdcf7ce30894287a6c643b9a1dd03f79c4ad2ded66d"},"schema_version":"1.0"},"canonical_sha256":"354ded257ce94278f909f4e6e2c5a6b09b047ed07c78aa83d8f2a9b05f21f02f","source":{"kind":"arxiv","id":"2103.16694","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16694","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16694v2","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16694","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"GVG62JL45FBH","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"GVG62JL45FBHR6IJ","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"GVG62JL4","created_at":"2026-07-05T03:06:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GVG62JL45FBHR6IJ6TTOFRNGWC","target":"record","payload":{"canonical_record":{"source":{"id":"2103.16694","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T21:33:00Z","cross_cats_sorted":[],"title_canon_sha256":"c6fde76648b7d5d8c979d79f3662fc14e9fdf3ee4eb3488689a50e525a8a1507","abstract_canon_sha256":"b9d3e3e10cda2843b1cdcbdcf7ce30894287a6c643b9a1dd03f79c4ad2ded66d"},"schema_version":"1.0"},"canonical_sha256":"354ded257ce94278f909f4e6e2c5a6b09b047ed07c78aa83d8f2a9b05f21f02f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:46.454851Z","signature_b64":"nynuGVeBkk6BRhQge3ynDKxOqGxM2MmMjVBCjR+akrtNFq6orEmW6XHhWGeDj44pSW0BMqrkKKpoOhwJpUqkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"354ded257ce94278f909f4e6e2c5a6b09b047ed07c78aa83d8f2a9b05f21f02f","last_reissued_at":"2026-07-05T03:06:46.454428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:46.454428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.16694","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":"2026-07-05T03:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQDzceTHVjMjsRh8JGjNo3+xHoA9bBrRkMdZwfnAj6xw37zoyZdzOQZ9pj392gKf7fkhxUnKz2PeeKUi1sUBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:38:13.288356Z"},"content_sha256":"a52962d7035c226d1cb1b44d34676178976863497f7afa7d7724ebd5012d3cd7","schema_version":"1.0","event_id":"sha256:a52962d7035c226d1cb1b44d34676178976863497f7afa7d7724ebd5012d3cd7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GVG62JL45FBHR6IJ6TTOFRNGWC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adrien Gaidon, Jie Li, Rares Ambrus, Vitor Guizilini","submitted_at":"2021-03-30T21:33:00Z","abstract_excerpt":"Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). Our Geometric Unsupervised Domain Adaptation method (GUDA) learns a domain-invariant representation via a multi-task objective combining synthetic semantic supervision with real-world geometric constraints on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16694","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/2103.16694/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":"2026-07-05T03:06:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oMIno6OYIuuuCC4xSEgQw5Smjqg5qMt76bK67iBxm3HNNLCK+bQSUO3XkSF6Q0t2twaiIizM/65pY+A8NdBmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:38:13.288872Z"},"content_sha256":"3769900ba438c696acf0a2f1fd3abae66c529982f1567766bc383683281ff322","schema_version":"1.0","event_id":"sha256:3769900ba438c696acf0a2f1fd3abae66c529982f1567766bc383683281ff322"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVG62JL45FBHR6IJ6TTOFRNGWC/bundle.json","state_url":"https://pith.science/pith/GVG62JL45FBHR6IJ6TTOFRNGWC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVG62JL45FBHR6IJ6TTOFRNGWC/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":"2026-08-04T22:38:13Z","links":{"resolver":"https://pith.science/pith/GVG62JL45FBHR6IJ6TTOFRNGWC","bundle":"https://pith.science/pith/GVG62JL45FBHR6IJ6TTOFRNGWC/bundle.json","state":"https://pith.science/pith/GVG62JL45FBHR6IJ6TTOFRNGWC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVG62JL45FBHR6IJ6TTOFRNGWC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GVG62JL45FBHR6IJ6TTOFRNGWC","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":"b9d3e3e10cda2843b1cdcbdcf7ce30894287a6c643b9a1dd03f79c4ad2ded66d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T21:33:00Z","title_canon_sha256":"c6fde76648b7d5d8c979d79f3662fc14e9fdf3ee4eb3488689a50e525a8a1507"},"schema_version":"1.0","source":{"id":"2103.16694","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.16694","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"arxiv_version","alias_value":"2103.16694v2","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16694","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_12","alias_value":"GVG62JL45FBH","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_16","alias_value":"GVG62JL45FBHR6IJ","created_at":"2026-07-05T03:06:46Z"},{"alias_kind":"pith_short_8","alias_value":"GVG62JL4","created_at":"2026-07-05T03:06:46Z"}],"graph_snapshots":[{"event_id":"sha256:3769900ba438c696acf0a2f1fd3abae66c529982f1567766bc383683281ff322","target":"graph","created_at":"2026-07-05T03:06:46Z","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/2103.16694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). Our Geometric Unsupervised Domain Adaptation method (GUDA) learns a domain-invariant representation via a multi-task objective combining synthetic semantic supervision with real-world geometric constraints on","authors_text":"Adrien Gaidon, Jie Li, Rares Ambrus, Vitor Guizilini","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T21:33:00Z","title":"Geometric Unsupervised Domain Adaptation for Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16694","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:a52962d7035c226d1cb1b44d34676178976863497f7afa7d7724ebd5012d3cd7","target":"record","created_at":"2026-07-05T03:06:46Z","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":"b9d3e3e10cda2843b1cdcbdcf7ce30894287a6c643b9a1dd03f79c4ad2ded66d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T21:33:00Z","title_canon_sha256":"c6fde76648b7d5d8c979d79f3662fc14e9fdf3ee4eb3488689a50e525a8a1507"},"schema_version":"1.0","source":{"id":"2103.16694","kind":"arxiv","version":2}},"canonical_sha256":"354ded257ce94278f909f4e6e2c5a6b09b047ed07c78aa83d8f2a9b05f21f02f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"354ded257ce94278f909f4e6e2c5a6b09b047ed07c78aa83d8f2a9b05f21f02f","first_computed_at":"2026-07-05T03:06:46.454428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:06:46.454428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nynuGVeBkk6BRhQge3ynDKxOqGxM2MmMjVBCjR+akrtNFq6orEmW6XHhWGeDj44pSW0BMqrkKKpoOhwJpUqkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:06:46.454851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.16694","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a52962d7035c226d1cb1b44d34676178976863497f7afa7d7724ebd5012d3cd7","sha256:3769900ba438c696acf0a2f1fd3abae66c529982f1567766bc383683281ff322"],"state_sha256":"050f5d2f761db0db97df2a68fa8cc8bb16129588e89f560666a93e3a22946a51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Omx5xOAwd+YVGz3KRgkAFextgPdBfhaLmm/8ucZ0ken3JxB6urMq4M/bz45rbPvGJU6CQCsTRyjZQ5r4jhEFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:38:13.292902Z","bundle_sha256":"ca0b704bfc67b0f23cdc7ed803a5193c83d1d9b61b067c3440b4f367a654c504"}}