{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:EWWU2KN7THL5J4JSFN3J5V44N3","short_pith_number":"pith:EWWU2KN7","canonical_record":{"source":{"id":"1605.00366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-02T06:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"05792251f9c7a1c17703aa70022ffd80591da9a45d98e1326935a742c5757dc5","abstract_canon_sha256":"57c48dc772a2d9e350f14714cb756ec03da799492c7cf5e23db525edee78e424"},"schema_version":"1.0"},"canonical_sha256":"25ad4d29bf99d7d4f1322b769ed79c6ed7ad6d0827712e4b46981e0900affdc9","source":{"kind":"arxiv","id":"1605.00366","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.00366","created_at":"2026-05-18T01:15:56Z"},{"alias_kind":"arxiv_version","alias_value":"1605.00366v1","created_at":"2026-05-18T01:15:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00366","created_at":"2026-05-18T01:15:56Z"},{"alias_kind":"pith_short_12","alias_value":"EWWU2KN7THL5","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"EWWU2KN7THL5J4JS","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"EWWU2KN7","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:EWWU2KN7THL5J4JSFN3J5V44N3","target":"record","payload":{"canonical_record":{"source":{"id":"1605.00366","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-02T06:40:08Z","cross_cats_sorted":[],"title_canon_sha256":"05792251f9c7a1c17703aa70022ffd80591da9a45d98e1326935a742c5757dc5","abstract_canon_sha256":"57c48dc772a2d9e350f14714cb756ec03da799492c7cf5e23db525edee78e424"},"schema_version":"1.0"},"canonical_sha256":"25ad4d29bf99d7d4f1322b769ed79c6ed7ad6d0827712e4b46981e0900affdc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:56.034894Z","signature_b64":"tCMYz6cUlmI7IbzeUkUgFhU9uueiyCgslPv7bXv+nxlqTHyIW76h8Vfg8wj46+YwJIq0ViOxQ1s8RGPPMporAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ad4d29bf99d7d4f1322b769ed79c6ed7ad6d0827712e4b46981e0900affdc9","last_reissued_at":"2026-05-18T01:15:56.034260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:56.034260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.00366","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":"2026-05-18T01:15:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LgO4Bfbrr4EbFD6tbqoGk54vuHOB5sxmeerUlZDLcObi0P3rLItopjTD/0+456niwy5OZtrPRaQJa+lgMa3gAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:48:00.356301Z"},"content_sha256":"5b1e3a342d3df8436e47de22b4a40871fd1785193cf62b3a33a47b9356b4ab79","schema_version":"1.0","event_id":"sha256:5b1e3a342d3df8436e47de22b4a40871fd1785193cf62b3a33a47b9356b4ab79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:EWWU2KN7THL5J4JSFN3J5V44N3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compression Artifacts Removal Using Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Barina, Michal Hradis, Pavel Svoboda, Pavel Zemcik","submitted_at":"2016-05-02T06:40:08Z","abstract_excerpt":"This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00366","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":""},"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":"2026-05-18T01:15:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aLvF65oAtlA1mJpDE7WHNe2MtVkyStg59cT/XCxKXxBSm7cwhexqGM1FgVnqLjX1TPyXa7v04pT8TDMpcIF3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:48:00.357026Z"},"content_sha256":"7a9c98e5abdefc55d2f58824cc87ce668906d5bbac67158a8d4a781ebfcc314f","schema_version":"1.0","event_id":"sha256:7a9c98e5abdefc55d2f58824cc87ce668906d5bbac67158a8d4a781ebfcc314f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWWU2KN7THL5J4JSFN3J5V44N3/bundle.json","state_url":"https://pith.science/pith/EWWU2KN7THL5J4JSFN3J5V44N3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWWU2KN7THL5J4JSFN3J5V44N3/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":"2026-05-31T20:48:00Z","links":{"resolver":"https://pith.science/pith/EWWU2KN7THL5J4JSFN3J5V44N3","bundle":"https://pith.science/pith/EWWU2KN7THL5J4JSFN3J5V44N3/bundle.json","state":"https://pith.science/pith/EWWU2KN7THL5J4JSFN3J5V44N3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWWU2KN7THL5J4JSFN3J5V44N3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EWWU2KN7THL5J4JSFN3J5V44N3","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":"57c48dc772a2d9e350f14714cb756ec03da799492c7cf5e23db525edee78e424","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-02T06:40:08Z","title_canon_sha256":"05792251f9c7a1c17703aa70022ffd80591da9a45d98e1326935a742c5757dc5"},"schema_version":"1.0","source":{"id":"1605.00366","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.00366","created_at":"2026-05-18T01:15:56Z"},{"alias_kind":"arxiv_version","alias_value":"1605.00366v1","created_at":"2026-05-18T01:15:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00366","created_at":"2026-05-18T01:15:56Z"},{"alias_kind":"pith_short_12","alias_value":"EWWU2KN7THL5","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"EWWU2KN7THL5J4JS","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"EWWU2KN7","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:7a9c98e5abdefc55d2f58824cc87ce668906d5bbac67158a8d4a781ebfcc314f","target":"graph","created_at":"2026-05-18T01:15:56Z","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"},"paper":{"abstract_excerpt":"This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three differ","authors_text":"David Barina, Michal Hradis, Pavel Svoboda, Pavel Zemcik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-02T06:40:08Z","title":"Compression Artifacts Removal Using Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00366","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":"sha256:5b1e3a342d3df8436e47de22b4a40871fd1785193cf62b3a33a47b9356b4ab79","target":"record","created_at":"2026-05-18T01:15:56Z","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":"57c48dc772a2d9e350f14714cb756ec03da799492c7cf5e23db525edee78e424","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-02T06:40:08Z","title_canon_sha256":"05792251f9c7a1c17703aa70022ffd80591da9a45d98e1326935a742c5757dc5"},"schema_version":"1.0","source":{"id":"1605.00366","kind":"arxiv","version":1}},"canonical_sha256":"25ad4d29bf99d7d4f1322b769ed79c6ed7ad6d0827712e4b46981e0900affdc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25ad4d29bf99d7d4f1322b769ed79c6ed7ad6d0827712e4b46981e0900affdc9","first_computed_at":"2026-05-18T01:15:56.034260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:56.034260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tCMYz6cUlmI7IbzeUkUgFhU9uueiyCgslPv7bXv+nxlqTHyIW76h8Vfg8wj46+YwJIq0ViOxQ1s8RGPPMporAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:56.034894Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.00366","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b1e3a342d3df8436e47de22b4a40871fd1785193cf62b3a33a47b9356b4ab79","sha256:7a9c98e5abdefc55d2f58824cc87ce668906d5bbac67158a8d4a781ebfcc314f"],"state_sha256":"8054c43c85722069e8e495dcfd5e0551a23f7e4f8367499d2747f1a57bd48d10"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q2xRMbU8AyuQrQLlLo8ch8d/qjnwToNxoym2UOY3YfKuJqD7FDkaTMMBL6nE7WHP+l2cCGH+l+nvd0wPjvDnDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:48:00.360825Z","bundle_sha256":"e3523ab6f7792a36c9508abc710ec8ee232314e78e3196da24808dc232c38476"}}