{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CRKJRYSZOUD4JJVD636DPM3XXH","short_pith_number":"pith:CRKJRYSZ","canonical_record":{"source":{"id":"2303.06583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-12T05:28:55Z","cross_cats_sorted":[],"title_canon_sha256":"faa025cb44630f9a3dcd96f4114fb6e25e2d7f43a356fff9cceddf96e275824c","abstract_canon_sha256":"00d6e63b5b0da46762f0a961c089da68a10bd4013f74ff457be58f16d79d2fc5"},"schema_version":"1.0"},"canonical_sha256":"145498e2597507c4a6a3f6fc37b377b9e92e6ef34ced2b84689e75b4c5e02e42","source":{"kind":"arxiv","id":"2303.06583","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06583","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06583v2","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06583","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"pith_short_12","alias_value":"CRKJRYSZOUD4","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"pith_short_16","alias_value":"CRKJRYSZOUD4JJVD","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"pith_short_8","alias_value":"CRKJRYSZ","created_at":"2026-07-05T07:30:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CRKJRYSZOUD4JJVD636DPM3XXH","target":"record","payload":{"canonical_record":{"source":{"id":"2303.06583","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-12T05:28:55Z","cross_cats_sorted":[],"title_canon_sha256":"faa025cb44630f9a3dcd96f4114fb6e25e2d7f43a356fff9cceddf96e275824c","abstract_canon_sha256":"00d6e63b5b0da46762f0a961c089da68a10bd4013f74ff457be58f16d79d2fc5"},"schema_version":"1.0"},"canonical_sha256":"145498e2597507c4a6a3f6fc37b377b9e92e6ef34ced2b84689e75b4c5e02e42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:47.306599Z","signature_b64":"blG2HE9fxnItNMM5hJ2HHX0rgbOfDfgmKWByV3w7z1jnCCBnzWv4pHWBkR0X82pyY7BzwWE38nWgYPcq0hImDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"145498e2597507c4a6a3f6fc37b377b9e92e6ef34ced2b84689e75b4c5e02e42","last_reissued_at":"2026-07-05T07:30:47.306075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:47.306075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.06583","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":"2026-07-05T07:30:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Rj6NYjSY/N4foZoyFXL5cFPw7f9XigyLo1SLV8nY/PI6NL+i6G7t66ae3NAgNocjJOgGhLDent0e+Rn2FQLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:14:36.386481Z"},"content_sha256":"78e7b951c9cee54c5fa8bf7c4555d254f4adcee3c8596c72d3c845eac3f883ab","schema_version":"1.0","event_id":"sha256:78e7b951c9cee54c5fa8bf7c4555d254f4adcee3c8596c72d3c845eac3f883ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CRKJRYSZOUD4JJVD636DPM3XXH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Masked Autoencoders by Learning Where to Mask","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haijian Chen, Wendong Zhang, Xiaokang Yang, Yunbo Wang","submitted_at":"2023-03-12T05:28:55Z","abstract_excerpt":"Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is there a better masking strategy than random sampling and how can we learn it? We empirically study this problem and initially find that introducing object-centric priors in mask sampling can significantly improve the learned representations. Inspired by this observation, we present AutoMAE, a fully differentiable framework that uses Gumbel-Softmax to interlin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06583","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/2303.06583/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":"2026-07-05T07:30:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ocMtmCthTiR5WPQS0i8+oTWrJvTqVQc0A7yQ43IzzzSr5QZ3jlc/We+E7u4EjzVxzq9KtqZ6ro/q9d46uV1tDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T10:14:36.386979Z"},"content_sha256":"b0588a8ea8688077f882af2e49abadcb495b6a972f5f89e12388cc36d26529b9","schema_version":"1.0","event_id":"sha256:b0588a8ea8688077f882af2e49abadcb495b6a972f5f89e12388cc36d26529b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRKJRYSZOUD4JJVD636DPM3XXH/bundle.json","state_url":"https://pith.science/pith/CRKJRYSZOUD4JJVD636DPM3XXH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRKJRYSZOUD4JJVD636DPM3XXH/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":"2026-08-14T10:14:36Z","links":{"resolver":"https://pith.science/pith/CRKJRYSZOUD4JJVD636DPM3XXH","bundle":"https://pith.science/pith/CRKJRYSZOUD4JJVD636DPM3XXH/bundle.json","state":"https://pith.science/pith/CRKJRYSZOUD4JJVD636DPM3XXH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRKJRYSZOUD4JJVD636DPM3XXH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CRKJRYSZOUD4JJVD636DPM3XXH","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":"00d6e63b5b0da46762f0a961c089da68a10bd4013f74ff457be58f16d79d2fc5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-12T05:28:55Z","title_canon_sha256":"faa025cb44630f9a3dcd96f4114fb6e25e2d7f43a356fff9cceddf96e275824c"},"schema_version":"1.0","source":{"id":"2303.06583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06583","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06583v2","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06583","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"pith_short_12","alias_value":"CRKJRYSZOUD4","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"pith_short_16","alias_value":"CRKJRYSZOUD4JJVD","created_at":"2026-07-05T07:30:47Z"},{"alias_kind":"pith_short_8","alias_value":"CRKJRYSZ","created_at":"2026-07-05T07:30:47Z"}],"graph_snapshots":[{"event_id":"sha256:b0588a8ea8688077f882af2e49abadcb495b6a972f5f89e12388cc36d26529b9","target":"graph","created_at":"2026-07-05T07:30:47Z","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/2303.06583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is there a better masking strategy than random sampling and how can we learn it? We empirically study this problem and initially find that introducing object-centric priors in mask sampling can significantly improve the learned representations. Inspired by this observation, we present AutoMAE, a fully differentiable framework that uses Gumbel-Softmax to interlin","authors_text":"Haijian Chen, Wendong Zhang, Xiaokang Yang, Yunbo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-12T05:28:55Z","title":"Improving Masked Autoencoders by Learning Where to Mask"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06583","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":"sha256:78e7b951c9cee54c5fa8bf7c4555d254f4adcee3c8596c72d3c845eac3f883ab","target":"record","created_at":"2026-07-05T07:30:47Z","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":"00d6e63b5b0da46762f0a961c089da68a10bd4013f74ff457be58f16d79d2fc5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-12T05:28:55Z","title_canon_sha256":"faa025cb44630f9a3dcd96f4114fb6e25e2d7f43a356fff9cceddf96e275824c"},"schema_version":"1.0","source":{"id":"2303.06583","kind":"arxiv","version":2}},"canonical_sha256":"145498e2597507c4a6a3f6fc37b377b9e92e6ef34ced2b84689e75b4c5e02e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"145498e2597507c4a6a3f6fc37b377b9e92e6ef34ced2b84689e75b4c5e02e42","first_computed_at":"2026-07-05T07:30:47.306075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:30:47.306075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"blG2HE9fxnItNMM5hJ2HHX0rgbOfDfgmKWByV3w7z1jnCCBnzWv4pHWBkR0X82pyY7BzwWE38nWgYPcq0hImDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:30:47.306599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.06583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78e7b951c9cee54c5fa8bf7c4555d254f4adcee3c8596c72d3c845eac3f883ab","sha256:b0588a8ea8688077f882af2e49abadcb495b6a972f5f89e12388cc36d26529b9"],"state_sha256":"f29be42fe394e0cc9515bbe188270b039c509258b4f574dd9e13de69a0572c29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tANQ3CBxG3a7h27gHJuod6+orZlRho1wcJ4NjC+957bNA3u4HITxnBQt2OHOuxlJbdEfbOlc1Q0Tv5GRsCreDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T10:14:36.392476Z","bundle_sha256":"b516d9ac215d337c94d6031fc6b598f56d1296da3fb8e5aa9350a9cb91150ae5"}}