{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FHMEFOL53QQF6NPGATJ3TDDYI3","short_pith_number":"pith:FHMEFOL5","canonical_record":{"source":{"id":"2110.06014","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T13:57:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"82e2355cc20f897c2472c1a8e7f247f47a6504f3f9bcc1b8aa76cf5b664068b9","abstract_canon_sha256":"b3ba2a1fcd30c6a5ff8db821dccdf32d1a0e021b6e143aee49c39123f61da994"},"schema_version":"1.0"},"canonical_sha256":"29d842b97ddc205f35e604d3b98c7846c1849da8fff4b6c28ecedfed03d59ca1","source":{"kind":"arxiv","id":"2110.06014","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06014","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06014v2","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06014","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"FHMEFOL53QQF","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"FHMEFOL53QQF6NPG","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"FHMEFOL5","created_at":"2026-07-05T04:04:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FHMEFOL53QQF6NPGATJ3TDDYI3","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06014","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T13:57:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"82e2355cc20f897c2472c1a8e7f247f47a6504f3f9bcc1b8aa76cf5b664068b9","abstract_canon_sha256":"b3ba2a1fcd30c6a5ff8db821dccdf32d1a0e021b6e143aee49c39123f61da994"},"schema_version":"1.0"},"canonical_sha256":"29d842b97ddc205f35e604d3b98c7846c1849da8fff4b6c28ecedfed03d59ca1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:42.270634Z","signature_b64":"1EsUZZ/d0AvXmHWGttWlBLTK2BRxIORMx0dqLbpcCTotSGgOlU+9ZAWKEG/XnulyY6OFVT80mvD4uqB8SakAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29d842b97ddc205f35e604d3b98c7846c1849da8fff4b6c28ecedfed03d59ca1","last_reissued_at":"2026-07-05T04:04:42.270188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:42.270188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06014","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":"2026-07-05T04:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ud/5r76J73F0jkhvwYIqeZu6zVrcmUTjs39AsClrgSpam0xMmcveHYzwjFlLOXEnDrJY2wQuFhUbgqm4S5zFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:38:26.754807Z"},"content_sha256":"627a72c56f2ada8278ed0033daebed66b9cc1f19532182a4b68150ee5ca6907a","schema_version":"1.0","event_id":"sha256:627a72c56f2ada8278ed0033daebed66b9cc1f19532182a4b68150ee5ca6907a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FHMEFOL53QQF6NPGATJ3TDDYI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Supervised Pre-training for Better Downstream Transferring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Jianwen Jiang, Mingqian Tang, Rong Jin, Yue Gao, Yutong Feng","submitted_at":"2021-10-12T13:57:38Z","abstract_excerpt":"The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), and is then fine-tuned to different downstream tasks. Though for most cases, the pre-training stage is conducted based on supervised methods, recent works on self-supervised pre-training have shown powerful transferability and even outperform supervised pre-training on multiple downstream tasks. It thus remains an open question how to better generalize supervised pre-training model to downstream tasks. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06014","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/2110.06014/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":"2026-07-05T04:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8r9X5FXSPEHUiyKPXHOir4iq/0Iynd2d6eNs6uxmDkhI+HTowBAhdeOO1ztfelbhMWrqh0jKyXCT3k/uSj6Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T04:38:26.755330Z"},"content_sha256":"fb8acdd8d65c16b7d6633aeb5cc389735086c3547394db3e0e9bb1cc0271581a","schema_version":"1.0","event_id":"sha256:fb8acdd8d65c16b7d6633aeb5cc389735086c3547394db3e0e9bb1cc0271581a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FHMEFOL53QQF6NPGATJ3TDDYI3/bundle.json","state_url":"https://pith.science/pith/FHMEFOL53QQF6NPGATJ3TDDYI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FHMEFOL53QQF6NPGATJ3TDDYI3/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":"2026-08-11T04:38:26Z","links":{"resolver":"https://pith.science/pith/FHMEFOL53QQF6NPGATJ3TDDYI3","bundle":"https://pith.science/pith/FHMEFOL53QQF6NPGATJ3TDDYI3/bundle.json","state":"https://pith.science/pith/FHMEFOL53QQF6NPGATJ3TDDYI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FHMEFOL53QQF6NPGATJ3TDDYI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FHMEFOL53QQF6NPGATJ3TDDYI3","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":"b3ba2a1fcd30c6a5ff8db821dccdf32d1a0e021b6e143aee49c39123f61da994","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T13:57:38Z","title_canon_sha256":"82e2355cc20f897c2472c1a8e7f247f47a6504f3f9bcc1b8aa76cf5b664068b9"},"schema_version":"1.0","source":{"id":"2110.06014","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06014","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06014v2","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06014","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"FHMEFOL53QQF","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"FHMEFOL53QQF6NPG","created_at":"2026-07-05T04:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"FHMEFOL5","created_at":"2026-07-05T04:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:fb8acdd8d65c16b7d6633aeb5cc389735086c3547394db3e0e9bb1cc0271581a","target":"graph","created_at":"2026-07-05T04:04:42Z","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/2110.06014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), and is then fine-tuned to different downstream tasks. Though for most cases, the pre-training stage is conducted based on supervised methods, recent works on self-supervised pre-training have shown powerful transferability and even outperform supervised pre-training on multiple downstream tasks. It thus remains an open question how to better generalize supervised pre-training model to downstream tasks. In this paper, w","authors_text":"Jianwen Jiang, Mingqian Tang, Rong Jin, Yue Gao, Yutong Feng","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T13:57:38Z","title":"Rethinking Supervised Pre-training for Better Downstream Transferring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06014","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":"sha256:627a72c56f2ada8278ed0033daebed66b9cc1f19532182a4b68150ee5ca6907a","target":"record","created_at":"2026-07-05T04:04:42Z","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":"b3ba2a1fcd30c6a5ff8db821dccdf32d1a0e021b6e143aee49c39123f61da994","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T13:57:38Z","title_canon_sha256":"82e2355cc20f897c2472c1a8e7f247f47a6504f3f9bcc1b8aa76cf5b664068b9"},"schema_version":"1.0","source":{"id":"2110.06014","kind":"arxiv","version":2}},"canonical_sha256":"29d842b97ddc205f35e604d3b98c7846c1849da8fff4b6c28ecedfed03d59ca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"29d842b97ddc205f35e604d3b98c7846c1849da8fff4b6c28ecedfed03d59ca1","first_computed_at":"2026-07-05T04:04:42.270188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:42.270188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1EsUZZ/d0AvXmHWGttWlBLTK2BRxIORMx0dqLbpcCTotSGgOlU+9ZAWKEG/XnulyY6OFVT80mvD4uqB8SakAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:42.270634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06014","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:627a72c56f2ada8278ed0033daebed66b9cc1f19532182a4b68150ee5ca6907a","sha256:fb8acdd8d65c16b7d6633aeb5cc389735086c3547394db3e0e9bb1cc0271581a"],"state_sha256":"68b66bbda7768e4d5c8cb6601ff7ca83319a88574fedf2130e28da0357da7ef0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"120B2tQVtrANt8agR5QLt+US69syq6XH8r7aULmLVcCGrrpRwLOX/d4qliXG5qZR1DNvpQJJuN4heVclFRYEDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T04:38:26.761081Z","bundle_sha256":"df9939bbcf2a53adf29ad1d190e58060fd6c4282c2511982fc636140b554442b"}}