{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UECTSJ7NOKGYOMNCFO5LHJDZ4C","short_pith_number":"pith:UECTSJ7N","canonical_record":{"source":{"id":"2402.04964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T15:43:50Z","cross_cats_sorted":[],"title_canon_sha256":"12cbc2f5ed9b020904bd23c3e7828a6829f09abe940ecb3ddd507fdfd013d5e1","abstract_canon_sha256":"10be2c68311bbe13220a87d65af1b622afdabc69b6917a5a689e59feb7ad26e8"},"schema_version":"1.0"},"canonical_sha256":"a1053927ed728d8731a22bbab3a479e08e708a62dfd36a7bca379bb925af514b","source":{"kind":"arxiv","id":"2402.04964","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04964","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04964v1","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04964","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"pith_short_12","alias_value":"UECTSJ7NOKGY","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"pith_short_16","alias_value":"UECTSJ7NOKGYOMNC","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"pith_short_8","alias_value":"UECTSJ7N","created_at":"2026-07-05T07:42:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UECTSJ7NOKGYOMNCFO5LHJDZ4C","target":"record","payload":{"canonical_record":{"source":{"id":"2402.04964","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T15:43:50Z","cross_cats_sorted":[],"title_canon_sha256":"12cbc2f5ed9b020904bd23c3e7828a6829f09abe940ecb3ddd507fdfd013d5e1","abstract_canon_sha256":"10be2c68311bbe13220a87d65af1b622afdabc69b6917a5a689e59feb7ad26e8"},"schema_version":"1.0"},"canonical_sha256":"a1053927ed728d8731a22bbab3a479e08e708a62dfd36a7bca379bb925af514b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:42:34.487774Z","signature_b64":"Gjoj7r+826Ck7lM6sC3QZxB+kggo7yWuSnIiVWhEWm5hsBgYudC0spR+kNgJ7oQhQJ8qgSHGs+iH3mQpt+bVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1053927ed728d8731a22bbab3a479e08e708a62dfd36a7bca379bb925af514b","last_reissued_at":"2026-07-05T07:42:34.487363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:42:34.487363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.04964","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":"2026-07-05T07:42:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdwBCYFWiZpBBP4Jb/Q8ilcWMYsZK+gZpuWL7wecXS92xf1N5idzVPD3KQSZQlRtxLu+L8B7eLk4EKHAKVowDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:45:15.713583Z"},"content_sha256":"3895fb7dfe4ca515d1103139551b488d8ff2b5e510885c03879e41ff3942bb74","schema_version":"1.0","event_id":"sha256:3895fb7dfe4ca515d1103139551b488d8ff2b5e510885c03879e41ff3942bb74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UECTSJ7NOKGYOMNCFO5LHJDZ4C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ConvLoRA and AdaBN based Domain Adaptation via Self-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eric Arazo, Julia Dietlmeier, Sidra Aleem, Suzanne Little","submitted_at":"2024-02-07T15:43:50Z","abstract_excerpt":"Existing domain adaptation (DA) methods often involve pre-training on the source domain and fine-tuning on the target domain. For multi-target domain adaptation, having a dedicated/separate fine-tuned network for each target domain, that retain all the pre-trained model parameters, is prohibitively expensive. To address this limitation, we propose Convolutional Low-Rank Adaptation (ConvLoRA). ConvLoRA freezes pre-trained model weights, adds trainable low-rank decomposition matrices to convolutional layers, and backpropagates the gradient through these matrices thus greatly reducing the number "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04964","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.04964/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":"2026-07-05T07:42:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FZUiayRNfhkw2ZDkcYsiRfQAUvRbByxiOJ7PoUohUsrSXZn1upEYS8e0Xp8Pdhksn5qJPmMm1SLvRj9VVfXKDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:45:15.714537Z"},"content_sha256":"a5dc5a596044e213a1a3680d95d4568abf5e022ddb14c906a17a6ced88dfdf46","schema_version":"1.0","event_id":"sha256:a5dc5a596044e213a1a3680d95d4568abf5e022ddb14c906a17a6ced88dfdf46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C/bundle.json","state_url":"https://pith.science/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C/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":"2026-08-04T15:45:15Z","links":{"resolver":"https://pith.science/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C","bundle":"https://pith.science/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C/bundle.json","state":"https://pith.science/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UECTSJ7NOKGYOMNCFO5LHJDZ4C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UECTSJ7NOKGYOMNCFO5LHJDZ4C","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":"10be2c68311bbe13220a87d65af1b622afdabc69b6917a5a689e59feb7ad26e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T15:43:50Z","title_canon_sha256":"12cbc2f5ed9b020904bd23c3e7828a6829f09abe940ecb3ddd507fdfd013d5e1"},"schema_version":"1.0","source":{"id":"2402.04964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04964","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04964v1","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04964","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"pith_short_12","alias_value":"UECTSJ7NOKGY","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"pith_short_16","alias_value":"UECTSJ7NOKGYOMNC","created_at":"2026-07-05T07:42:34Z"},{"alias_kind":"pith_short_8","alias_value":"UECTSJ7N","created_at":"2026-07-05T07:42:34Z"}],"graph_snapshots":[{"event_id":"sha256:a5dc5a596044e213a1a3680d95d4568abf5e022ddb14c906a17a6ced88dfdf46","target":"graph","created_at":"2026-07-05T07:42:34Z","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/2402.04964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing domain adaptation (DA) methods often involve pre-training on the source domain and fine-tuning on the target domain. For multi-target domain adaptation, having a dedicated/separate fine-tuned network for each target domain, that retain all the pre-trained model parameters, is prohibitively expensive. To address this limitation, we propose Convolutional Low-Rank Adaptation (ConvLoRA). ConvLoRA freezes pre-trained model weights, adds trainable low-rank decomposition matrices to convolutional layers, and backpropagates the gradient through these matrices thus greatly reducing the number ","authors_text":"Eric Arazo, Julia Dietlmeier, Sidra Aleem, Suzanne Little","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T15:43:50Z","title":"ConvLoRA and AdaBN based Domain Adaptation via Self-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04964","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":"sha256:3895fb7dfe4ca515d1103139551b488d8ff2b5e510885c03879e41ff3942bb74","target":"record","created_at":"2026-07-05T07:42:34Z","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":"10be2c68311bbe13220a87d65af1b622afdabc69b6917a5a689e59feb7ad26e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-07T15:43:50Z","title_canon_sha256":"12cbc2f5ed9b020904bd23c3e7828a6829f09abe940ecb3ddd507fdfd013d5e1"},"schema_version":"1.0","source":{"id":"2402.04964","kind":"arxiv","version":1}},"canonical_sha256":"a1053927ed728d8731a22bbab3a479e08e708a62dfd36a7bca379bb925af514b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1053927ed728d8731a22bbab3a479e08e708a62dfd36a7bca379bb925af514b","first_computed_at":"2026-07-05T07:42:34.487363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:34.487363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gjoj7r+826Ck7lM6sC3QZxB+kggo7yWuSnIiVWhEWm5hsBgYudC0spR+kNgJ7oQhQJ8qgSHGs+iH3mQpt+bVCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:34.487774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3895fb7dfe4ca515d1103139551b488d8ff2b5e510885c03879e41ff3942bb74","sha256:a5dc5a596044e213a1a3680d95d4568abf5e022ddb14c906a17a6ced88dfdf46"],"state_sha256":"aed09701b658338f51c45faa6be949fcfacd6f6bc116ddf5e91541abe2fb7511"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+yfrB65PUwG6AQIi31ikkkUs+aIZpVHmmcZ9wxV1HJaZFfVCq7cS8LRjQX0PJVgQ4685gEeMfQQ/mCjwtovBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:45:15.720098Z","bundle_sha256":"f260f61b6523c7a6f1d80ddeba794b062be41f42c2ccc484eafe2d4147a794dd"}}