{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GFBVMHOLOZ2VFWZS2B72FWWJ66","short_pith_number":"pith:GFBVMHOL","canonical_record":{"source":{"id":"2304.12314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-24T17:59:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"23deee2d6a4cdc903202ec2d6d9e01d649c3b136cd233eec2f52f12f85927a5f","abstract_canon_sha256":"f6c3179269a55a6d52f9be50207ab4fbfae7843b970a5a3eda5823da7af8aec5"},"schema_version":"1.0"},"canonical_sha256":"3143561dcb767552db32d07fa2dac9f7becdd40fe40a302c81412196e15041a2","source":{"kind":"arxiv","id":"2304.12314","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12314","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12314v1","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12314","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"GFBVMHOLOZ2V","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"GFBVMHOLOZ2VFWZS","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"GFBVMHOL","created_at":"2026-07-05T06:03:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GFBVMHOLOZ2VFWZS2B72FWWJ66","target":"record","payload":{"canonical_record":{"source":{"id":"2304.12314","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-24T17:59:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"23deee2d6a4cdc903202ec2d6d9e01d649c3b136cd233eec2f52f12f85927a5f","abstract_canon_sha256":"f6c3179269a55a6d52f9be50207ab4fbfae7843b970a5a3eda5823da7af8aec5"},"schema_version":"1.0"},"canonical_sha256":"3143561dcb767552db32d07fa2dac9f7becdd40fe40a302c81412196e15041a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:50.347330Z","signature_b64":"B69rOlVHiRCCDFc01JBl7o+IvMg+JmDacVvqiiXlUmvX4KIC5Qgsho4Okx3ge0h1pziJFy7OzuXe0SIUwZitCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3143561dcb767552db32d07fa2dac9f7becdd40fe40a302c81412196e15041a2","last_reissued_at":"2026-07-05T06:03:50.346913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:50.346913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.12314","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":"2026-07-05T06:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2eyVGjv143mOZxPt4Lf79Y2SsPWFHqCayhp/M2pjr8bFD+llHmUCF9Riid6QqDbiVzA7XPCAwqC0AaHRBh2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:40:29.539898Z"},"content_sha256":"c79c57496a361f7506fe91ae88c2e46b6d9ef012b71e8e1adc059bbefe6792b9","schema_version":"1.0","event_id":"sha256:c79c57496a361f7506fe91ae88c2e46b6d9ef012b71e8e1adc059bbefe6792b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GFBVMHOLOZ2VFWZS2B72FWWJ66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling from Similar Tasks for Transfer Learning on a Budget","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Bharath Hariharan, Cheng Perng Phoo, Kenneth Borup","submitted_at":"2023-04-24T17:59:01Z","abstract_excerpt":"We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource constraints both during training and inference. Transfer learning is an effective solution for training with few labels, however often at the expense of a computationally costly fine-tuning of large base models. We propose to mitigate this unpleasant trade-off between compute and accuracy via semi-supervised cross-domain distillation from a set of diverse sou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12314","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/2304.12314/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":"2026-07-05T06:03:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k7aPC5Q1vpC5Ku0knpOL7/f5us7HNFsSGKldtzLxojUmpWYPSx/0prz2FxTfp+Tt9xHrXCpnrOUgV8jlwwcyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:40:29.540283Z"},"content_sha256":"e59019034d89e6f9db3bc24a0e00388dbe70acf235c90befb8548f3e24c17479","schema_version":"1.0","event_id":"sha256:e59019034d89e6f9db3bc24a0e00388dbe70acf235c90befb8548f3e24c17479"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66/bundle.json","state_url":"https://pith.science/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66/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":"2026-07-06T18:40:29Z","links":{"resolver":"https://pith.science/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66","bundle":"https://pith.science/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66/bundle.json","state":"https://pith.science/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GFBVMHOLOZ2VFWZS2B72FWWJ66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GFBVMHOLOZ2VFWZS2B72FWWJ66","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":"f6c3179269a55a6d52f9be50207ab4fbfae7843b970a5a3eda5823da7af8aec5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-24T17:59:01Z","title_canon_sha256":"23deee2d6a4cdc903202ec2d6d9e01d649c3b136cd233eec2f52f12f85927a5f"},"schema_version":"1.0","source":{"id":"2304.12314","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12314","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12314v1","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12314","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"GFBVMHOLOZ2V","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"GFBVMHOLOZ2VFWZS","created_at":"2026-07-05T06:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"GFBVMHOL","created_at":"2026-07-05T06:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:e59019034d89e6f9db3bc24a0e00388dbe70acf235c90befb8548f3e24c17479","target":"graph","created_at":"2026-07-05T06:03:50Z","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/2304.12314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource constraints both during training and inference. Transfer learning is an effective solution for training with few labels, however often at the expense of a computationally costly fine-tuning of large base models. We propose to mitigate this unpleasant trade-off between compute and accuracy via semi-supervised cross-domain distillation from a set of diverse sou","authors_text":"Bharath Hariharan, Cheng Perng Phoo, Kenneth Borup","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-24T17:59:01Z","title":"Distilling from Similar Tasks for Transfer Learning on a Budget"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12314","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:c79c57496a361f7506fe91ae88c2e46b6d9ef012b71e8e1adc059bbefe6792b9","target":"record","created_at":"2026-07-05T06:03:50Z","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":"f6c3179269a55a6d52f9be50207ab4fbfae7843b970a5a3eda5823da7af8aec5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-24T17:59:01Z","title_canon_sha256":"23deee2d6a4cdc903202ec2d6d9e01d649c3b136cd233eec2f52f12f85927a5f"},"schema_version":"1.0","source":{"id":"2304.12314","kind":"arxiv","version":1}},"canonical_sha256":"3143561dcb767552db32d07fa2dac9f7becdd40fe40a302c81412196e15041a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3143561dcb767552db32d07fa2dac9f7becdd40fe40a302c81412196e15041a2","first_computed_at":"2026-07-05T06:03:50.346913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:50.346913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B69rOlVHiRCCDFc01JBl7o+IvMg+JmDacVvqiiXlUmvX4KIC5Qgsho4Okx3ge0h1pziJFy7OzuXe0SIUwZitCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:50.347330Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12314","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c79c57496a361f7506fe91ae88c2e46b6d9ef012b71e8e1adc059bbefe6792b9","sha256:e59019034d89e6f9db3bc24a0e00388dbe70acf235c90befb8548f3e24c17479"],"state_sha256":"eed6210507cafd6bc2619f24f97d320429daced7908a0b776fa7ef6a9230b038"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lbap+WsBsscM/cV1dc4WYhpQx6cOBfW0mIwor0LDSV1rNwlUi7WrGi+y4tLNi05uJ7eaGJzDuzTVpwGjA7ewBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:40:29.542349Z","bundle_sha256":"f78c12a4f4904efa20022e2229e29fde818380eaeef5d6127e64170b6a99d978"}}