{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PR7FPNLJNHIPRRIBRFAXWX77PI","short_pith_number":"pith:PR7FPNLJ","canonical_record":{"source":{"id":"2208.05642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T05:08:55Z","cross_cats_sorted":[],"title_canon_sha256":"180b002ca3581316c73e359c39d262cb35df38a2d16ef7c10f1638871a017076","abstract_canon_sha256":"2aff8d3c364057f18c6157914c621afa247bcef76468f4da63d7f462fb1a7ee2"},"schema_version":"1.0"},"canonical_sha256":"7c7e57b56969d0f8c50189417b5fff7a23d3f8141c2df8bdf23c898b3ea577d8","source":{"kind":"arxiv","id":"2208.05642","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.05642","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2208.05642v1","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05642","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"PR7FPNLJNHIP","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"PR7FPNLJNHIPRRIB","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"PR7FPNLJ","created_at":"2026-07-05T04:47:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PR7FPNLJNHIPRRIBRFAXWX77PI","target":"record","payload":{"canonical_record":{"source":{"id":"2208.05642","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T05:08:55Z","cross_cats_sorted":[],"title_canon_sha256":"180b002ca3581316c73e359c39d262cb35df38a2d16ef7c10f1638871a017076","abstract_canon_sha256":"2aff8d3c364057f18c6157914c621afa247bcef76468f4da63d7f462fb1a7ee2"},"schema_version":"1.0"},"canonical_sha256":"7c7e57b56969d0f8c50189417b5fff7a23d3f8141c2df8bdf23c898b3ea577d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:44.803026Z","signature_b64":"S+VHxsrBgXa8jLBlj4y5a1evwGe49acMPh31agz+0KSkV1BLuFqB6joydOQ2EMPGJ+vrPtP0AZFZAx3m7n4rAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c7e57b56969d0f8c50189417b5fff7a23d3f8141c2df8bdf23c898b3ea577d8","last_reissued_at":"2026-07-05T04:47:44.802567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:44.802567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.05642","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":"2026-07-05T04:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gRyytcF2IL3W+tjvwBNHHz1RzPt/MZ+e7asHMemIqiJiBJN0FE26Sd1z53UdiOHcLruNEv85VQuFGAH//H45Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:46:15.814064Z"},"content_sha256":"a260563af230bb7636d226ee745ccd77c7b35db4cb0ac67e76ad1025f9764ef4","schema_version":"1.0","event_id":"sha256:a260563af230bb7636d226ee745ccd77c7b35db4cb0ac67e76ad1025f9764ef4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PR7FPNLJNHIPRRIBRFAXWX77PI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Knowledge Distillation via Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hyoje Lee, Hyun Seo, Myungjoo Kang, Yeachan Park","submitted_at":"2022-08-11T05:08:55Z","abstract_excerpt":"To boost the performance, deep neural networks require deeper or wider network structures that involve massive computational and memory costs. To alleviate this issue, the self-knowledge distillation method regularizes the model by distilling the internal knowledge of the model itself. Conventional self-knowledge distillation methods require additional trainable parameters or are dependent on the data. In this paper, we propose a simple and effective self-knowledge distillation method using a dropout (SD-Dropout). SD-Dropout distills the posterior distributions of multiple models through a dro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05642","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/2208.05642/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":"2026-07-05T04:47:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1LzxhTXn4cyGJCkBrIHdAkpC2E1Icci8KWpuBoYzsZb6Si/LQgwFlyhRyGgNtmQdh4pC0BWjkr6ThlR11a2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:46:15.814551Z"},"content_sha256":"1c2d9862cf24f15dcece52d88d4a036d120476e9513a49e987afdc62b5ae9739","schema_version":"1.0","event_id":"sha256:1c2d9862cf24f15dcece52d88d4a036d120476e9513a49e987afdc62b5ae9739"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PR7FPNLJNHIPRRIBRFAXWX77PI/bundle.json","state_url":"https://pith.science/pith/PR7FPNLJNHIPRRIBRFAXWX77PI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PR7FPNLJNHIPRRIBRFAXWX77PI/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":"2026-08-08T13:46:15Z","links":{"resolver":"https://pith.science/pith/PR7FPNLJNHIPRRIBRFAXWX77PI","bundle":"https://pith.science/pith/PR7FPNLJNHIPRRIBRFAXWX77PI/bundle.json","state":"https://pith.science/pith/PR7FPNLJNHIPRRIBRFAXWX77PI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PR7FPNLJNHIPRRIBRFAXWX77PI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PR7FPNLJNHIPRRIBRFAXWX77PI","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":"2aff8d3c364057f18c6157914c621afa247bcef76468f4da63d7f462fb1a7ee2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T05:08:55Z","title_canon_sha256":"180b002ca3581316c73e359c39d262cb35df38a2d16ef7c10f1638871a017076"},"schema_version":"1.0","source":{"id":"2208.05642","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.05642","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"arxiv_version","alias_value":"2208.05642v1","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05642","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"pith_short_12","alias_value":"PR7FPNLJNHIP","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"pith_short_16","alias_value":"PR7FPNLJNHIPRRIB","created_at":"2026-07-05T04:47:44Z"},{"alias_kind":"pith_short_8","alias_value":"PR7FPNLJ","created_at":"2026-07-05T04:47:44Z"}],"graph_snapshots":[{"event_id":"sha256:1c2d9862cf24f15dcece52d88d4a036d120476e9513a49e987afdc62b5ae9739","target":"graph","created_at":"2026-07-05T04:47:44Z","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/2208.05642/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To boost the performance, deep neural networks require deeper or wider network structures that involve massive computational and memory costs. To alleviate this issue, the self-knowledge distillation method regularizes the model by distilling the internal knowledge of the model itself. Conventional self-knowledge distillation methods require additional trainable parameters or are dependent on the data. In this paper, we propose a simple and effective self-knowledge distillation method using a dropout (SD-Dropout). SD-Dropout distills the posterior distributions of multiple models through a dro","authors_text":"Hyoje Lee, Hyun Seo, Myungjoo Kang, Yeachan Park","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T05:08:55Z","title":"Self-Knowledge Distillation via Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05642","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:a260563af230bb7636d226ee745ccd77c7b35db4cb0ac67e76ad1025f9764ef4","target":"record","created_at":"2026-07-05T04:47:44Z","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":"2aff8d3c364057f18c6157914c621afa247bcef76468f4da63d7f462fb1a7ee2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-08-11T05:08:55Z","title_canon_sha256":"180b002ca3581316c73e359c39d262cb35df38a2d16ef7c10f1638871a017076"},"schema_version":"1.0","source":{"id":"2208.05642","kind":"arxiv","version":1}},"canonical_sha256":"7c7e57b56969d0f8c50189417b5fff7a23d3f8141c2df8bdf23c898b3ea577d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c7e57b56969d0f8c50189417b5fff7a23d3f8141c2df8bdf23c898b3ea577d8","first_computed_at":"2026-07-05T04:47:44.802567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:47:44.802567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S+VHxsrBgXa8jLBlj4y5a1evwGe49acMPh31agz+0KSkV1BLuFqB6joydOQ2EMPGJ+vrPtP0AZFZAx3m7n4rAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:47:44.803026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.05642","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a260563af230bb7636d226ee745ccd77c7b35db4cb0ac67e76ad1025f9764ef4","sha256:1c2d9862cf24f15dcece52d88d4a036d120476e9513a49e987afdc62b5ae9739"],"state_sha256":"07505d54a092d80704f92dff81b190550cca6a4344a4a8d8dd5f8e149a8a165a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5WidLJiYikpRViTkYgChmNZ+FsvEiQZI89Ypeq0DaIyRYJl37/ckQYo4Slyuc8TbocZZek2VhPuXXqLio7pAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:46:15.817746Z","bundle_sha256":"a50b54f7bda535f099eab36f3270c5e99bab5139075016663fc9ad2b8bdd19fb"}}