{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:I5JQDH6EQ36OLE7QHNMAWCTXWV","short_pith_number":"pith:I5JQDH6E","canonical_record":{"source":{"id":"1811.03542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T16:44:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90707f79bc9b55ac9185ba51d9c3aa7eea1c4fab9ec25906d83a224463595659","abstract_canon_sha256":"aaa242ddee7f66b787ca9cb3814811a61bd3de065942e78b810dd7c662177202"},"schema_version":"1.0"},"canonical_sha256":"4753019fc486fce593f03b580b0a77b551ddcbb0f44ba88fbee2c769ce98cd70","source":{"kind":"arxiv","id":"1811.03542","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03542","created_at":"2026-05-18T00:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03542v1","created_at":"2026-05-18T00:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03542","created_at":"2026-05-18T00:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"I5JQDH6EQ36O","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I5JQDH6EQ36OLE7Q","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I5JQDH6E","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:I5JQDH6EQ36OLE7QHNMAWCTXWV","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T16:44:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"90707f79bc9b55ac9185ba51d9c3aa7eea1c4fab9ec25906d83a224463595659","abstract_canon_sha256":"aaa242ddee7f66b787ca9cb3814811a61bd3de065942e78b810dd7c662177202"},"schema_version":"1.0"},"canonical_sha256":"4753019fc486fce593f03b580b0a77b551ddcbb0f44ba88fbee2c769ce98cd70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:15.794631Z","signature_b64":"RSJvxvF+P8UbUW+y0BGXv5EjyYjf8brA/8fNze4oa8DfIyM+EwLDO8vkIX9vJhQCDyn/GLgFOcfJiZE7TFkYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4753019fc486fce593f03b580b0a77b551ddcbb0f44ba88fbee2c769ce98cd70","last_reissued_at":"2026-05-18T00:01:15.794192Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:15.794192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03542","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":"2026-05-18T00:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+zgKTzrvBhd7t52ag3fkPfyipoq9kddwYGEASDauO94Mz1DR4uY66z7KBpX/ngFGkIvYUY/4ICK7VARTAQxoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:26:26.161908Z"},"content_sha256":"14868c0bc6081f69e761e25e568c2bb03c4365827d119672f88ccce07d64e2ea","schema_version":"1.0","event_id":"sha256:14868c0bc6081f69e761e25e568c2bb03c4365827d119672f88ccce07d64e2ea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:I5JQDH6EQ36OLE7QHNMAWCTXWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianwei Feng, Kashyap Chitta, Martial Hebert","submitted_at":"2018-11-08T16:44:59Z","abstract_excerpt":"Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent with the training data. In this paper, we show that by carefully presenting a mixture of labeled source domain and proxy-labeled target domain data to a network, we can achieve state-of-the-art unsupervised domain adaptation results. With our design, the network progressively learns features specific to the target domain using annotation from only the source d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03542","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":"2026-05-18T00:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0PZ9lmchFA2rl2ssuDv7gh/WjezFyM4rHGQhji0to+cenne3/rihlsmyjoLUp+kUAcM/4fW6+X9P4cc6AtRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:26:26.162642Z"},"content_sha256":"cd1f96aae1ac1447fd88ae7c52e283c8fc4a91b33ddfca9eb5a0289d3f6f6094","schema_version":"1.0","event_id":"sha256:cd1f96aae1ac1447fd88ae7c52e283c8fc4a91b33ddfca9eb5a0289d3f6f6094"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV/bundle.json","state_url":"https://pith.science/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV/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":"2026-06-09T05:26:26Z","links":{"resolver":"https://pith.science/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV","bundle":"https://pith.science/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV/bundle.json","state":"https://pith.science/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5JQDH6EQ36OLE7QHNMAWCTXWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I5JQDH6EQ36OLE7QHNMAWCTXWV","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":"aaa242ddee7f66b787ca9cb3814811a61bd3de065942e78b810dd7c662177202","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T16:44:59Z","title_canon_sha256":"90707f79bc9b55ac9185ba51d9c3aa7eea1c4fab9ec25906d83a224463595659"},"schema_version":"1.0","source":{"id":"1811.03542","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03542","created_at":"2026-05-18T00:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03542v1","created_at":"2026-05-18T00:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03542","created_at":"2026-05-18T00:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"I5JQDH6EQ36O","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I5JQDH6EQ36OLE7Q","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I5JQDH6E","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:cd1f96aae1ac1447fd88ae7c52e283c8fc4a91b33ddfca9eb5a0289d3f6f6094","target":"graph","created_at":"2026-05-18T00:01:15Z","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":"Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent with the training data. In this paper, we show that by carefully presenting a mixture of labeled source domain and proxy-labeled target domain data to a network, we can achieve state-of-the-art unsupervised domain adaptation results. With our design, the network progressively learns features specific to the target domain using annotation from only the source d","authors_text":"Jianwei Feng, Kashyap Chitta, Martial Hebert","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T16:44:59Z","title":"Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03542","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":"sha256:14868c0bc6081f69e761e25e568c2bb03c4365827d119672f88ccce07d64e2ea","target":"record","created_at":"2026-05-18T00:01:15Z","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":"aaa242ddee7f66b787ca9cb3814811a61bd3de065942e78b810dd7c662177202","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-08T16:44:59Z","title_canon_sha256":"90707f79bc9b55ac9185ba51d9c3aa7eea1c4fab9ec25906d83a224463595659"},"schema_version":"1.0","source":{"id":"1811.03542","kind":"arxiv","version":1}},"canonical_sha256":"4753019fc486fce593f03b580b0a77b551ddcbb0f44ba88fbee2c769ce98cd70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4753019fc486fce593f03b580b0a77b551ddcbb0f44ba88fbee2c769ce98cd70","first_computed_at":"2026-05-18T00:01:15.794192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:15.794192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RSJvxvF+P8UbUW+y0BGXv5EjyYjf8brA/8fNze4oa8DfIyM+EwLDO8vkIX9vJhQCDyn/GLgFOcfJiZE7TFkYDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:15.794631Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03542","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14868c0bc6081f69e761e25e568c2bb03c4365827d119672f88ccce07d64e2ea","sha256:cd1f96aae1ac1447fd88ae7c52e283c8fc4a91b33ddfca9eb5a0289d3f6f6094"],"state_sha256":"dee68bdff0936ec6b6d01fb911d6b02464ff0f5c65d1065a16eb579ef16714f3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HpXQlz8bxV/WGug93zbxkFEWZQMRFBqEOiEOJPGffFuOUpIAwXN24p/nLPs0/0BloqYXXo9v+mRj5P+5q2MdDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T05:26:26.166913Z","bundle_sha256":"463866c2f0c00e80399911976a79152abf6ee53b713ac9c19b08d989d3bd22fb"}}