{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DWJJTQMO7ZCQXKXA5OZOYEICRL","short_pith_number":"pith:DWJJTQMO","canonical_record":{"source":{"id":"1804.10745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-28T05:20:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2c5d055b45e8e6c878c874c1a301b70920b6c911859de4b4b65a960078b69f61","abstract_canon_sha256":"953e3c2d9142b373eacc70bfe0b7fa07f6cb62946187b9e9c064db2da8f95168"},"schema_version":"1.0"},"canonical_sha256":"1d9299c18efe450baae0ebb2ec11028aee4a99982b77fd28c37a09008e2ad2b1","source":{"kind":"arxiv","id":"1804.10745","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10745","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10745v2","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10745","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"DWJJTQMO7ZCQ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DWJJTQMO7ZCQXKXA","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DWJJTQMO","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DWJJTQMO7ZCQXKXA5OZOYEICRL","target":"record","payload":{"canonical_record":{"source":{"id":"1804.10745","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-28T05:20:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2c5d055b45e8e6c878c874c1a301b70920b6c911859de4b4b65a960078b69f61","abstract_canon_sha256":"953e3c2d9142b373eacc70bfe0b7fa07f6cb62946187b9e9c064db2da8f95168"},"schema_version":"1.0"},"canonical_sha256":"1d9299c18efe450baae0ebb2ec11028aee4a99982b77fd28c37a09008e2ad2b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:10.791917Z","signature_b64":"u1MHVrRJU2Mi1Vy+nYpSW6pzLZCjVN4oLXqd8f1Cdm/t7Sl2eYZw2qrQUEanQSzROmBmGjAcr3foLL7n2uT4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d9299c18efe450baae0ebb2ec11028aee4a99982b77fd28c37a09008e2ad2b1","last_reissued_at":"2026-05-18T00:17:10.791362Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:10.791362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.10745","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":"2026-05-18T00:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrCURwuRgSFlAwcnfjUZZlRqt4LL1hbfbMPsV/ajTn+FLeFibrlprUgr3BuqNhEznNGqvw10q9vhMKmYo51sDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:24:56.841163Z"},"content_sha256":"c96e2cd2c406d3e195035f06d8d804a7c541209d849c388793d05aa5ec1171c3","schema_version":"1.0","event_id":"sha256:c96e2cd2c406d3e195035f06d8d804a7c541209d849c388793d05aa5ec1171c3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DWJJTQMO7ZCQXKXA5OZOYEICRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalizing Across Domains via Cross-Gradient Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Preethi Jyothi, Shiv Shankar, Siddhartha Chaudhuri, Soumen Chakrabarti, Sunita Sarawagi, Vihari Piratla","submitted_at":"2018-04-28T05:20:53Z","abstract_excerpt":"We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or unlabeled data, or domain features in the new domain. Most existing domain adaptation methods attempt to erase domain signals using techniques like domain adversarial training. In contrast, CROSSGRAD is free to use domain signals for predicting labels, if it can prevent overfitting on training domains. We conceptualize the task in a Bayesian setting, in which a sampling step is implemented as data augmentation, based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10745","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":""},"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":"2026-05-18T00:17:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ubHLa6z5sGrDTVR/4n3mmXUo2rZpwb2sLp6MzoDB5hqGs3/saRrR2QWsgzxyJrijyMLxIF3uxm3gYTtEl6LSBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T11:24:56.841692Z"},"content_sha256":"3a463eebbf75aba84f61b0e00e65e7d9b67b931c19fc58163b1487f1cf7dc15b","schema_version":"1.0","event_id":"sha256:3a463eebbf75aba84f61b0e00e65e7d9b67b931c19fc58163b1487f1cf7dc15b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL/bundle.json","state_url":"https://pith.science/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL/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":"2026-05-31T11:24:56Z","links":{"resolver":"https://pith.science/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL","bundle":"https://pith.science/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL/bundle.json","state":"https://pith.science/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DWJJTQMO7ZCQXKXA5OZOYEICRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DWJJTQMO7ZCQXKXA5OZOYEICRL","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":"953e3c2d9142b373eacc70bfe0b7fa07f6cb62946187b9e9c064db2da8f95168","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-28T05:20:53Z","title_canon_sha256":"2c5d055b45e8e6c878c874c1a301b70920b6c911859de4b4b65a960078b69f61"},"schema_version":"1.0","source":{"id":"1804.10745","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10745","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10745v2","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10745","created_at":"2026-05-18T00:17:10Z"},{"alias_kind":"pith_short_12","alias_value":"DWJJTQMO7ZCQ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DWJJTQMO7ZCQXKXA","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DWJJTQMO","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:3a463eebbf75aba84f61b0e00e65e7d9b67b931c19fc58163b1487f1cf7dc15b","target":"graph","created_at":"2026-05-18T00:17:10Z","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"},"paper":{"abstract_excerpt":"We present CROSSGRAD, a method to use multi-domain training data to learn a classifier that generalizes to new domains. CROSSGRAD does not need an adaptation phase via labeled or unlabeled data, or domain features in the new domain. Most existing domain adaptation methods attempt to erase domain signals using techniques like domain adversarial training. In contrast, CROSSGRAD is free to use domain signals for predicting labels, if it can prevent overfitting on training domains. We conceptualize the task in a Bayesian setting, in which a sampling step is implemented as data augmentation, based ","authors_text":"Preethi Jyothi, Shiv Shankar, Siddhartha Chaudhuri, Soumen Chakrabarti, Sunita Sarawagi, Vihari Piratla","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-28T05:20:53Z","title":"Generalizing Across Domains via Cross-Gradient Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10745","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:c96e2cd2c406d3e195035f06d8d804a7c541209d849c388793d05aa5ec1171c3","target":"record","created_at":"2026-05-18T00:17:10Z","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":"953e3c2d9142b373eacc70bfe0b7fa07f6cb62946187b9e9c064db2da8f95168","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-28T05:20:53Z","title_canon_sha256":"2c5d055b45e8e6c878c874c1a301b70920b6c911859de4b4b65a960078b69f61"},"schema_version":"1.0","source":{"id":"1804.10745","kind":"arxiv","version":2}},"canonical_sha256":"1d9299c18efe450baae0ebb2ec11028aee4a99982b77fd28c37a09008e2ad2b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d9299c18efe450baae0ebb2ec11028aee4a99982b77fd28c37a09008e2ad2b1","first_computed_at":"2026-05-18T00:17:10.791362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:10.791362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u1MHVrRJU2Mi1Vy+nYpSW6pzLZCjVN4oLXqd8f1Cdm/t7Sl2eYZw2qrQUEanQSzROmBmGjAcr3foLL7n2uT4Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:10.791917Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.10745","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c96e2cd2c406d3e195035f06d8d804a7c541209d849c388793d05aa5ec1171c3","sha256:3a463eebbf75aba84f61b0e00e65e7d9b67b931c19fc58163b1487f1cf7dc15b"],"state_sha256":"417fc2f759b60299140dc080f66aeb93f0e413797111ceb4b2264e9ab0f71c31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MpbQFgIwBTLo4/W+OTAORwauCYMNs9/wl270uPP0prBO0Ano6uQa4rpv3OsHrfcKWP0T8p9pevfmNxH2VaPTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T11:24:56.845030Z","bundle_sha256":"7c018259d26277aedd99003ce23446c1be068badd120e9cc355c4a5e8cf65ea5"}}