{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XNYQIUQVUJZUTL5EJGSR6L246Z","short_pith_number":"pith:XNYQIUQV","canonical_record":{"source":{"id":"2209.08788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-19T06:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"f44f8b7621c6dabb878c18efe776592664ec8e91a39734f46e376a3291ffc3ed","abstract_canon_sha256":"2a93e32eeaae6c403fbbccf08f902ee1485ca61ceb389dd523b6d57c968d5d77"},"schema_version":"1.0"},"canonical_sha256":"bb71045215a27349afa449a51f2f5cf64db7c517cc0460fc8edb742a374f1f7e","source":{"kind":"arxiv","id":"2209.08788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08788","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08788v1","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08788","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"XNYQIUQVUJZU","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"XNYQIUQVUJZUTL5E","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"XNYQIUQV","created_at":"2026-07-05T04:58:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XNYQIUQVUJZUTL5EJGSR6L246Z","target":"record","payload":{"canonical_record":{"source":{"id":"2209.08788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-19T06:35:04Z","cross_cats_sorted":[],"title_canon_sha256":"f44f8b7621c6dabb878c18efe776592664ec8e91a39734f46e376a3291ffc3ed","abstract_canon_sha256":"2a93e32eeaae6c403fbbccf08f902ee1485ca61ceb389dd523b6d57c968d5d77"},"schema_version":"1.0"},"canonical_sha256":"bb71045215a27349afa449a51f2f5cf64db7c517cc0460fc8edb742a374f1f7e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:45.999500Z","signature_b64":"u6cphDOeHn6s5UAJgWryi73mVIETN3znamjHkJtjAHdcVztEAHhIbBHnFeDgxvXloU6u1zf9dWphJmaPNolvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb71045215a27349afa449a51f2f5cf64db7c517cc0460fc8edb742a374f1f7e","last_reissued_at":"2026-07-05T04:58:45.999076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:45.999076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.08788","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":"2026-07-05T04:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcjxJNvwcgtChj17KUv4taqQ9PaehCBP3hHbWsJG/x7bqoY2lAWbNYlr40tU4+G+2nZcX4XVZoMZjptf8KtQCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:33:32.310987Z"},"content_sha256":"4b0bac76073e1378d7ee1435c9dd1edaaf923e914a3fdb920e150c48e546cef9","schema_version":"1.0","event_id":"sha256:4b0bac76073e1378d7ee1435c9dd1edaaf923e914a3fdb920e150c48e546cef9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XNYQIUQVUJZUTL5EJGSR6L246Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Zeng, Hailin Shi, Hang Du, Jun Wang, Ting Yao, Yibo Hu","submitted_at":"2022-09-19T06:35:04Z","abstract_excerpt":"Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such multi-shot scheme brings inference burden, and the predefined scales inevitably have gap from real data. Instead, learning scale parameters from data, and using them for one-shot feature inference, is a decent solution. To this end, we reform the conv layer by resorting to the scale-space theory, and achieve two-fold facilities: 1) the conv layer learns a set of scal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08788","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.08788/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":"2026-07-05T04:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84x8nrHAtR5aNo1RNSd6atRYm0eevvL4S2plfHui3/NMJ+3Mpuo0ASm/QQc755m8BmEMArrmqFILtQs1KXGADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T11:33:32.311581Z"},"content_sha256":"fdafc4da27f44be017e017881ff69a178fafe9e4ef1a2100dc62dc6082dd3c23","schema_version":"1.0","event_id":"sha256:fdafc4da27f44be017e017881ff69a178fafe9e4ef1a2100dc62dc6082dd3c23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNYQIUQVUJZUTL5EJGSR6L246Z/bundle.json","state_url":"https://pith.science/pith/XNYQIUQVUJZUTL5EJGSR6L246Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNYQIUQVUJZUTL5EJGSR6L246Z/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":"2026-08-16T11:33:32Z","links":{"resolver":"https://pith.science/pith/XNYQIUQVUJZUTL5EJGSR6L246Z","bundle":"https://pith.science/pith/XNYQIUQVUJZUTL5EJGSR6L246Z/bundle.json","state":"https://pith.science/pith/XNYQIUQVUJZUTL5EJGSR6L246Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNYQIUQVUJZUTL5EJGSR6L246Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XNYQIUQVUJZUTL5EJGSR6L246Z","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":"2a93e32eeaae6c403fbbccf08f902ee1485ca61ceb389dd523b6d57c968d5d77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-19T06:35:04Z","title_canon_sha256":"f44f8b7621c6dabb878c18efe776592664ec8e91a39734f46e376a3291ffc3ed"},"schema_version":"1.0","source":{"id":"2209.08788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.08788","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2209.08788v1","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.08788","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"XNYQIUQVUJZU","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"XNYQIUQVUJZUTL5E","created_at":"2026-07-05T04:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"XNYQIUQV","created_at":"2026-07-05T04:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:fdafc4da27f44be017e017881ff69a178fafe9e4ef1a2100dc62dc6082dd3c23","target":"graph","created_at":"2026-07-05T04:58:45Z","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/2209.08788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human face images usually appear with wide range of visual scales. The existing face representations pursue the bandwidth of handling scale variation via multi-scale scheme that assembles a finite series of predefined scales. Such multi-shot scheme brings inference burden, and the predefined scales inevitably have gap from real data. Instead, learning scale parameters from data, and using them for one-shot feature inference, is a decent solution. To this end, we reform the conv layer by resorting to the scale-space theory, and achieve two-fold facilities: 1) the conv layer learns a set of scal","authors_text":"Dan Zeng, Hailin Shi, Hang Du, Jun Wang, Ting Yao, Yibo Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-19T06:35:04Z","title":"Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.08788","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":"sha256:4b0bac76073e1378d7ee1435c9dd1edaaf923e914a3fdb920e150c48e546cef9","target":"record","created_at":"2026-07-05T04:58:45Z","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":"2a93e32eeaae6c403fbbccf08f902ee1485ca61ceb389dd523b6d57c968d5d77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-19T06:35:04Z","title_canon_sha256":"f44f8b7621c6dabb878c18efe776592664ec8e91a39734f46e376a3291ffc3ed"},"schema_version":"1.0","source":{"id":"2209.08788","kind":"arxiv","version":1}},"canonical_sha256":"bb71045215a27349afa449a51f2f5cf64db7c517cc0460fc8edb742a374f1f7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb71045215a27349afa449a51f2f5cf64db7c517cc0460fc8edb742a374f1f7e","first_computed_at":"2026-07-05T04:58:45.999076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:45.999076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u6cphDOeHn6s5UAJgWryi73mVIETN3znamjHkJtjAHdcVztEAHhIbBHnFeDgxvXloU6u1zf9dWphJmaPNolvAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:45.999500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.08788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b0bac76073e1378d7ee1435c9dd1edaaf923e914a3fdb920e150c48e546cef9","sha256:fdafc4da27f44be017e017881ff69a178fafe9e4ef1a2100dc62dc6082dd3c23"],"state_sha256":"b79435102d9a858f58e37ea9a8213376d455c7e41e734f52a0228f9a3e1f355a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hYmkK4Ft0FCcreRQVO9W9AGXkkOMb9EaLTulvrAEyiBNeWwSBo9MVzuoZNaq+5CadOBEK0y1NC1NCrNvs2xCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T11:33:32.317220Z","bundle_sha256":"b5aae0a033a7218b3e51eac02f943ec691336fc771724b9829623fdd381a02dc"}}