{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:X7P66NL4MV33HQKVJEOLLCIVXJ","short_pith_number":"pith:X7P66NL4","canonical_record":{"source":{"id":"2302.05441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T18:58:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"acdb74eaccf18bf64f640e87754f846f39db73c2d439830bda898daec0f05867","abstract_canon_sha256":"5e4811040118a39f6a2a45a944c15d47d9fb9698de24e1d1ff0f3b4b136afb2c"},"schema_version":"1.0"},"canonical_sha256":"bfdfef357c6577b3c155491cb58915ba67f5d6d4fe53786ef37d719f632282a6","source":{"kind":"arxiv","id":"2302.05441","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05441","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05441v2","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05441","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"X7P66NL4MV33","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"X7P66NL4MV33HQKV","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"X7P66NL4","created_at":"2026-07-05T06:13:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:X7P66NL4MV33HQKVJEOLLCIVXJ","target":"record","payload":{"canonical_record":{"source":{"id":"2302.05441","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T18:58:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"acdb74eaccf18bf64f640e87754f846f39db73c2d439830bda898daec0f05867","abstract_canon_sha256":"5e4811040118a39f6a2a45a944c15d47d9fb9698de24e1d1ff0f3b4b136afb2c"},"schema_version":"1.0"},"canonical_sha256":"bfdfef357c6577b3c155491cb58915ba67f5d6d4fe53786ef37d719f632282a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:38.393084Z","signature_b64":"JAeZhVp/0sFF4w1bwU9WYKtZIMfE9tiiAvBGOD53bLt12bPW28yw0caNeC7HvkErfSB/nJuSPugk/OBNMeikAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfdfef357c6577b3c155491cb58915ba67f5d6d4fe53786ef37d719f632282a6","last_reissued_at":"2026-07-05T06:13:38.392670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:38.392670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.05441","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":"2026-07-05T06:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3Nzij7715f0uPdoQZIX/9c1rJhYiNK5OJ9GDEq3Ldus+AYmXOqYEt+MMODYKLL5WLxlkGaqEMXROpkfz9B/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T18:18:29.044455Z"},"content_sha256":"147ad4eb71f7536ebbc47b20432b77f56edcd8d478acb1ac32c1fbe16f52e0f6","schema_version":"1.0","event_id":"sha256:147ad4eb71f7536ebbc47b20432b77f56edcd8d478acb1ac32c1fbe16f52e0f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:X7P66NL4MV33HQKVJEOLLCIVXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amrith Setlur, Annie S. Chen, Chelsea Finn, Sergey Levine, Yoonho Lee","submitted_at":"2023-02-10T18:58:03Z","abstract_excerpt":"Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts. In some situations, target data labels may be expensive to obtain, so we may only have access to a limited number of target data points. To make the most of a very small target dataset, we propose a lightweight, sample-efficient approach that learns a diverse set of features and adapts to a target distribution by interpolating these features. Our approach, Project and Probe (Pro$^2$), first learns a linear projection that maps a pre-trained embedding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05441","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/2302.05441/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":"2026-07-05T06:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GeE+P6NiT07AyFP6aXO2/UfFOCuRHTY93waJARzwNOIgDalGWU96mFxObPVIZhTsjty1efXEUtH6NFuRo8zzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T18:18:29.044821Z"},"content_sha256":"47f492100f750eb3c0e178e0c8dd159e82be54f15569e7a216d30d170ee181ac","schema_version":"1.0","event_id":"sha256:47f492100f750eb3c0e178e0c8dd159e82be54f15569e7a216d30d170ee181ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7P66NL4MV33HQKVJEOLLCIVXJ/bundle.json","state_url":"https://pith.science/pith/X7P66NL4MV33HQKVJEOLLCIVXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7P66NL4MV33HQKVJEOLLCIVXJ/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":"2026-07-24T18:18:29Z","links":{"resolver":"https://pith.science/pith/X7P66NL4MV33HQKVJEOLLCIVXJ","bundle":"https://pith.science/pith/X7P66NL4MV33HQKVJEOLLCIVXJ/bundle.json","state":"https://pith.science/pith/X7P66NL4MV33HQKVJEOLLCIVXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7P66NL4MV33HQKVJEOLLCIVXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:X7P66NL4MV33HQKVJEOLLCIVXJ","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":"5e4811040118a39f6a2a45a944c15d47d9fb9698de24e1d1ff0f3b4b136afb2c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T18:58:03Z","title_canon_sha256":"acdb74eaccf18bf64f640e87754f846f39db73c2d439830bda898daec0f05867"},"schema_version":"1.0","source":{"id":"2302.05441","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.05441","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2302.05441v2","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05441","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"X7P66NL4MV33","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"X7P66NL4MV33HQKV","created_at":"2026-07-05T06:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"X7P66NL4","created_at":"2026-07-05T06:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:47f492100f750eb3c0e178e0c8dd159e82be54f15569e7a216d30d170ee181ac","target":"graph","created_at":"2026-07-05T06:13:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.05441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning with a small amount of target data is an effective and common approach to adapting a pre-trained model to distribution shifts. In some situations, target data labels may be expensive to obtain, so we may only have access to a limited number of target data points. To make the most of a very small target dataset, we propose a lightweight, sample-efficient approach that learns a diverse set of features and adapts to a target distribution by interpolating these features. Our approach, Project and Probe (Pro$^2$), first learns a linear projection that maps a pre-trained embedding ","authors_text":"Amrith Setlur, Annie S. Chen, Chelsea Finn, Sergey Levine, Yoonho Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T18:58:03Z","title":"Project and Probe: Sample-Efficient Domain Adaptation by Interpolating Orthogonal Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05441","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":"sha256:147ad4eb71f7536ebbc47b20432b77f56edcd8d478acb1ac32c1fbe16f52e0f6","target":"record","created_at":"2026-07-05T06:13:38Z","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":"5e4811040118a39f6a2a45a944c15d47d9fb9698de24e1d1ff0f3b4b136afb2c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-10T18:58:03Z","title_canon_sha256":"acdb74eaccf18bf64f640e87754f846f39db73c2d439830bda898daec0f05867"},"schema_version":"1.0","source":{"id":"2302.05441","kind":"arxiv","version":2}},"canonical_sha256":"bfdfef357c6577b3c155491cb58915ba67f5d6d4fe53786ef37d719f632282a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfdfef357c6577b3c155491cb58915ba67f5d6d4fe53786ef37d719f632282a6","first_computed_at":"2026-07-05T06:13:38.392670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:38.392670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JAeZhVp/0sFF4w1bwU9WYKtZIMfE9tiiAvBGOD53bLt12bPW28yw0caNeC7HvkErfSB/nJuSPugk/OBNMeikAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:38.393084Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.05441","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:147ad4eb71f7536ebbc47b20432b77f56edcd8d478acb1ac32c1fbe16f52e0f6","sha256:47f492100f750eb3c0e178e0c8dd159e82be54f15569e7a216d30d170ee181ac"],"state_sha256":"a8f9ce97e1dedf4d25d2d33d52d5d257490569ce63b18f3a10ba7e6dba06dcbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LnX0NdxdT/C4v5EDepcy98d/kL7cQKWbrufoA42ogaxVjJc8fAGE1TQW338TidVW6Z00TqusVeXAmkYDbGttDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T18:18:29.047900Z","bundle_sha256":"31936f36c4a3cef9af9af06c64fb6915630b55f76e3db054984bcd2ef6c64383"}}