{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QPEHR5MM7RJGBRVVBHGCOJ2BNL","short_pith_number":"pith:QPEHR5MM","canonical_record":{"source":{"id":"1910.08845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-10-19T21:07:33Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c210c55839164236def06f4aeec307c0e56d713916f3c3d9b0d294d2515650db","abstract_canon_sha256":"19d632a90eb23a5502bf9eb50cf9d80e7c1d5923562db17bb4eca949e271cfea"},"schema_version":"1.0"},"canonical_sha256":"83c878f58cfc5260c6b509cc2727416ac3882896defb4d341ede11336bb5d1ac","source":{"kind":"arxiv","id":"1910.08845","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08845","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08845v2","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08845","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"pith_short_12","alias_value":"QPEHR5MM7RJG","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"pith_short_16","alias_value":"QPEHR5MM7RJGBRVV","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"pith_short_8","alias_value":"QPEHR5MM","created_at":"2026-07-05T01:51:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QPEHR5MM7RJGBRVVBHGCOJ2BNL","target":"record","payload":{"canonical_record":{"source":{"id":"1910.08845","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-10-19T21:07:33Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"c210c55839164236def06f4aeec307c0e56d713916f3c3d9b0d294d2515650db","abstract_canon_sha256":"19d632a90eb23a5502bf9eb50cf9d80e7c1d5923562db17bb4eca949e271cfea"},"schema_version":"1.0"},"canonical_sha256":"83c878f58cfc5260c6b509cc2727416ac3882896defb4d341ede11336bb5d1ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:59.426261Z","signature_b64":"35UiK8QJ82KrU4mr+0Vs36TXdJMs2cBWnseLv3XZW6yLH37TPzSI4BtclBc8LnJaua6930Bg3MkMkjiwZQ7SBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83c878f58cfc5260c6b509cc2727416ac3882896defb4d341ede11336bb5d1ac","last_reissued_at":"2026-07-05T01:51:59.425755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:59.425755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.08845","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":"2026-07-05T01:51:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6HS+IK2LsgoHK2OYdkRPwD8qQBGlolmQBN7r3QH9BHFcFZxIbUJIJYz+VmdWVZem24NdPDLTxZ3IrBi4KI/sCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:09:45.797706Z"},"content_sha256":"c527dbdc5d8b60a086f4d9e6252c209f657ff2c80dd7d67213b2418cd93e4875","schema_version":"1.0","event_id":"sha256:c527dbdc5d8b60a086f4d9e6252c209f657ff2c80dd7d67213b2418cd93e4875"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QPEHR5MM7RJGBRVVBHGCOJ2BNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Alan C. Bovik, Andrey Norkin, Christos G. Bampis, Li-Heng Chen, Zhi Li","submitted_at":"2019-10-19T21:07:33Z","abstract_excerpt":"The use of $\\ell_p$ $(p=1,2)$ norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different \"proximal\" approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08845","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/1910.08845/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":"2026-07-05T01:51:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEecA/1on46kYSCQP7uFXXj2a8dtyQb9eahJU3iVmTSfiBc9ByDe75wPniUDq67F6ObpzBB3TYZHuCZo4luaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:09:45.798269Z"},"content_sha256":"e484788b1a48f5d86127d9a53e23508027c59b266e86e0d785b4220079c588aa","schema_version":"1.0","event_id":"sha256:e484788b1a48f5d86127d9a53e23508027c59b266e86e0d785b4220079c588aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL/bundle.json","state_url":"https://pith.science/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL/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":"2026-08-06T01:09:45Z","links":{"resolver":"https://pith.science/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL","bundle":"https://pith.science/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL/bundle.json","state":"https://pith.science/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPEHR5MM7RJGBRVVBHGCOJ2BNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QPEHR5MM7RJGBRVVBHGCOJ2BNL","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":"19d632a90eb23a5502bf9eb50cf9d80e7c1d5923562db17bb4eca949e271cfea","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-10-19T21:07:33Z","title_canon_sha256":"c210c55839164236def06f4aeec307c0e56d713916f3c3d9b0d294d2515650db"},"schema_version":"1.0","source":{"id":"1910.08845","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.08845","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"arxiv_version","alias_value":"1910.08845v2","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.08845","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"pith_short_12","alias_value":"QPEHR5MM7RJG","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"pith_short_16","alias_value":"QPEHR5MM7RJGBRVV","created_at":"2026-07-05T01:51:59Z"},{"alias_kind":"pith_short_8","alias_value":"QPEHR5MM","created_at":"2026-07-05T01:51:59Z"}],"graph_snapshots":[{"event_id":"sha256:e484788b1a48f5d86127d9a53e23508027c59b266e86e0d785b4220079c588aa","target":"graph","created_at":"2026-07-05T01:51:59Z","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/1910.08845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of $\\ell_p$ $(p=1,2)$ norms has largely dominated the measurement of loss in neural networks due to their simplicity and analytical properties. However, when used to assess the loss of visual information, these simple norms are not very consistent with human perception. Here, we describe a different \"proximal\" approach to optimize image analysis networks against quantitative perceptual models. Specifically, we construct a proxy network, broadly termed ProxIQA, which mimics the perceptual model while serving as a loss layer of the network. We experimentally demonstrate how this optimiza","authors_text":"Alan C. Bovik, Andrey Norkin, Christos G. Bampis, Li-Heng Chen, Zhi Li","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-10-19T21:07:33Z","title":"ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.08845","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:c527dbdc5d8b60a086f4d9e6252c209f657ff2c80dd7d67213b2418cd93e4875","target":"record","created_at":"2026-07-05T01:51:59Z","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":"19d632a90eb23a5502bf9eb50cf9d80e7c1d5923562db17bb4eca949e271cfea","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2019-10-19T21:07:33Z","title_canon_sha256":"c210c55839164236def06f4aeec307c0e56d713916f3c3d9b0d294d2515650db"},"schema_version":"1.0","source":{"id":"1910.08845","kind":"arxiv","version":2}},"canonical_sha256":"83c878f58cfc5260c6b509cc2727416ac3882896defb4d341ede11336bb5d1ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83c878f58cfc5260c6b509cc2727416ac3882896defb4d341ede11336bb5d1ac","first_computed_at":"2026-07-05T01:51:59.425755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:59.425755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35UiK8QJ82KrU4mr+0Vs36TXdJMs2cBWnseLv3XZW6yLH37TPzSI4BtclBc8LnJaua6930Bg3MkMkjiwZQ7SBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:59.426261Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.08845","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c527dbdc5d8b60a086f4d9e6252c209f657ff2c80dd7d67213b2418cd93e4875","sha256:e484788b1a48f5d86127d9a53e23508027c59b266e86e0d785b4220079c588aa"],"state_sha256":"65b5f0df88854ceacde66bbc2ff3abc900b21709341d542ee225ad5000bede8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"goNajCRvE1UdsBghdtR2JypFK9NxgXCpG5qoxZ4unt7IYy2rZ8Yd1livM+XdYha+/jii9Hxg4dJdoi+JldpUDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:09:45.803142Z","bundle_sha256":"aaf3e6220c4af7edc9b56a7364e86ab7bbcf12a446f341418946f22072754b01"}}