{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6WV75ZWPTTFTH2GKVECXQDHAEA","short_pith_number":"pith:6WV75ZWP","canonical_record":{"source":{"id":"2303.01573","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T20:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"79f84ac25b4251ce259be9bda3bbbe4c2d98bb570bc5de0f56a414cb33a20520","abstract_canon_sha256":"d07a7bbc97cabccb8cbd2720752dc34df37ed865ccbc44ffd3fb382f1798cfde"},"schema_version":"1.0"},"canonical_sha256":"f5abfee6cf9ccb33e8caa905780ce020306aac6addf3b392be0df1bee978f68a","source":{"kind":"arxiv","id":"2303.01573","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01573","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01573v2","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01573","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"6WV75ZWPTTFT","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"6WV75ZWPTTFTH2GK","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"6WV75ZWP","created_at":"2026-07-05T05:56:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6WV75ZWPTTFTH2GKVECXQDHAEA","target":"record","payload":{"canonical_record":{"source":{"id":"2303.01573","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T20:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"79f84ac25b4251ce259be9bda3bbbe4c2d98bb570bc5de0f56a414cb33a20520","abstract_canon_sha256":"d07a7bbc97cabccb8cbd2720752dc34df37ed865ccbc44ffd3fb382f1798cfde"},"schema_version":"1.0"},"canonical_sha256":"f5abfee6cf9ccb33e8caa905780ce020306aac6addf3b392be0df1bee978f68a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:16.209229Z","signature_b64":"F1KjmURfZJH0jbVuus89pjjLFwTDqBGsA3FEjdFETVq+O00tdIQWEJP21kYmXNXhorRjvogv4t5JfoJIbl3WCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5abfee6cf9ccb33e8caa905780ce020306aac6addf3b392be0df1bee978f68a","last_reissued_at":"2026-07-05T05:56:16.208722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:16.208722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.01573","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":"2026-07-05T05:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rDCooP6HG5siPd6AdMvYO1Z/IvBpPZngZTnK0BMXD9ULVdHzzQLTLvf1civ4vFVth4LQ/L/0LrSuYEQSju1lDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:57:18.404398Z"},"content_sha256":"b6f792069413190e13f47458c58aac2c3b07f14bd2df9dd13393cc4e38922568","schema_version":"1.0","event_id":"sha256:b6f792069413190e13f47458c58aac2c3b07f14bd2df9dd13393cc4e38922568"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6WV75ZWPTTFTH2GKVECXQDHAEA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Debasmit Das, Fatih Porikli, Hong Cai, Hyojin Park, Risheek Garrepalli, Shubhankar Borse","submitted_at":"2023-03-02T20:56:36Z","abstract_excerpt":"We present DejaVu, a novel framework which leverages conditional image regeneration as additional supervision during training to improve deep networks for dense prediction tasks such as segmentation, depth estimation, and surface normal prediction. First, we apply redaction to the input image, which removes certain structural information by sparse sampling or selective frequency removal. Next, we use a conditional regenerator, which takes the redacted image and the dense predictions as inputs, and reconstructs the original image by filling in the missing structural information. In the redacted"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01573","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/2303.01573/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":"2026-07-05T05:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QEJKjOXi4+JbMhPZU2u+RBefApfcGGWgdd829TYTCC2rMEPgnlT2Px7HmU1r3rTb6gihRuOApA1zNCItByFNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T05:57:18.404801Z"},"content_sha256":"ddb3630889d4825b52002fe9b860e8c968fc65255b97f08a33089d6c52df4aab","schema_version":"1.0","event_id":"sha256:ddb3630889d4825b52002fe9b860e8c968fc65255b97f08a33089d6c52df4aab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WV75ZWPTTFTH2GKVECXQDHAEA/bundle.json","state_url":"https://pith.science/pith/6WV75ZWPTTFTH2GKVECXQDHAEA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WV75ZWPTTFTH2GKVECXQDHAEA/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":"2026-07-07T05:57:18Z","links":{"resolver":"https://pith.science/pith/6WV75ZWPTTFTH2GKVECXQDHAEA","bundle":"https://pith.science/pith/6WV75ZWPTTFTH2GKVECXQDHAEA/bundle.json","state":"https://pith.science/pith/6WV75ZWPTTFTH2GKVECXQDHAEA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WV75ZWPTTFTH2GKVECXQDHAEA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6WV75ZWPTTFTH2GKVECXQDHAEA","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":"d07a7bbc97cabccb8cbd2720752dc34df37ed865ccbc44ffd3fb382f1798cfde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T20:56:36Z","title_canon_sha256":"79f84ac25b4251ce259be9bda3bbbe4c2d98bb570bc5de0f56a414cb33a20520"},"schema_version":"1.0","source":{"id":"2303.01573","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.01573","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2303.01573v2","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01573","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"6WV75ZWPTTFT","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"6WV75ZWPTTFTH2GK","created_at":"2026-07-05T05:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"6WV75ZWP","created_at":"2026-07-05T05:56:16Z"}],"graph_snapshots":[{"event_id":"sha256:ddb3630889d4825b52002fe9b860e8c968fc65255b97f08a33089d6c52df4aab","target":"graph","created_at":"2026-07-05T05:56:16Z","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/2303.01573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DejaVu, a novel framework which leverages conditional image regeneration as additional supervision during training to improve deep networks for dense prediction tasks such as segmentation, depth estimation, and surface normal prediction. First, we apply redaction to the input image, which removes certain structural information by sparse sampling or selective frequency removal. Next, we use a conditional regenerator, which takes the redacted image and the dense predictions as inputs, and reconstructs the original image by filling in the missing structural information. In the redacted","authors_text":"Debasmit Das, Fatih Porikli, Hong Cai, Hyojin Park, Risheek Garrepalli, Shubhankar Borse","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T20:56:36Z","title":"DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01573","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:b6f792069413190e13f47458c58aac2c3b07f14bd2df9dd13393cc4e38922568","target":"record","created_at":"2026-07-05T05:56:16Z","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":"d07a7bbc97cabccb8cbd2720752dc34df37ed865ccbc44ffd3fb382f1798cfde","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T20:56:36Z","title_canon_sha256":"79f84ac25b4251ce259be9bda3bbbe4c2d98bb570bc5de0f56a414cb33a20520"},"schema_version":"1.0","source":{"id":"2303.01573","kind":"arxiv","version":2}},"canonical_sha256":"f5abfee6cf9ccb33e8caa905780ce020306aac6addf3b392be0df1bee978f68a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5abfee6cf9ccb33e8caa905780ce020306aac6addf3b392be0df1bee978f68a","first_computed_at":"2026-07-05T05:56:16.208722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:16.208722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F1KjmURfZJH0jbVuus89pjjLFwTDqBGsA3FEjdFETVq+O00tdIQWEJP21kYmXNXhorRjvogv4t5JfoJIbl3WCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:16.209229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.01573","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6f792069413190e13f47458c58aac2c3b07f14bd2df9dd13393cc4e38922568","sha256:ddb3630889d4825b52002fe9b860e8c968fc65255b97f08a33089d6c52df4aab"],"state_sha256":"488f0e2a2ab8571546baa9f810b125f977966acac040df78e84b83df8aebe99a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6mCYCgF8tdYq9gMZVI/JAXt6Nx5HQvn5uUPSmdOr83bxTs9ISQVn+mcxuPcseFSuYB7rerwY4aRjK6dcPCUmDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T05:57:18.407084Z","bundle_sha256":"ceb5c82e4a8bceeeaab8527e9db954128d204f162c452a836c97be0087e576ab"}}