{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:GK4PYORHMG74YCA7CJESYCDXWQ","short_pith_number":"pith:GK4PYORH","canonical_record":{"source":{"id":"1711.05611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T15:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"66c940d563a82537bcd7cbc3bd4012700987c148c39239a2eff838ba5d2718a7","abstract_canon_sha256":"ef0580f32657bbb50a5d533bab92f696c8698e8e0cd2cef9e1c536aa8d3e90d6"},"schema_version":"1.0"},"canonical_sha256":"32b8fc3a2761bfcc081f12492c0877b415487cc62357fc1d1e97ffcc02ae0bc4","source":{"kind":"arxiv","id":"1711.05611","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.05611","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1711.05611v2","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05611","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"GK4PYORHMG74","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GK4PYORHMG74YCA7","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GK4PYORH","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:GK4PYORHMG74YCA7CJESYCDXWQ","target":"record","payload":{"canonical_record":{"source":{"id":"1711.05611","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T15:05:25Z","cross_cats_sorted":[],"title_canon_sha256":"66c940d563a82537bcd7cbc3bd4012700987c148c39239a2eff838ba5d2718a7","abstract_canon_sha256":"ef0580f32657bbb50a5d533bab92f696c8698e8e0cd2cef9e1c536aa8d3e90d6"},"schema_version":"1.0"},"canonical_sha256":"32b8fc3a2761bfcc081f12492c0877b415487cc62357fc1d1e97ffcc02ae0bc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:24.763031Z","signature_b64":"QdFhZHxZAZS81RlaBERUvQ/HWUqAgKd0Lx/AvAiPEDzkCfkTUKVbJc87dp9rpiNopv6a3C3XzchY0YHlRbiGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32b8fc3a2761bfcc081f12492c0877b415487cc62357fc1d1e97ffcc02ae0bc4","last_reissued_at":"2026-05-18T00:12:24.762520Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:24.762520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.05611","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":"2026-05-18T00:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Ju52GYz7yAUKbfHXmLRG+GtusqQ8AQj9BzlZcVpgGadBYWXzw+SGP2AcqZI7Ykw/6s4SR1jfFl5O6Giy0FJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:23:59.548756Z"},"content_sha256":"d9af565f57f64b2a344eb726f9cfb0e1564a3da35387388b941371c6c14edd20","schema_version":"1.0","event_id":"sha256:d9af565f57f64b2a344eb726f9cfb0e1564a3da35387388b941371c6c14edd20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:GK4PYORHMG74YCA7CJESYCDXWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpreting Deep Visual Representations via Network Dissection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Aude Oliva, Bolei Zhou, David Bau","submitted_at":"2017-11-15T15:05:25Z","abstract_excerpt":"The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack interpretability, since they have millions of unexplained model parameters. In this work, we describe Network Dissection, a method that interprets networks by providing labels for the units of their deep visual representations. The proposed method quantifies the interpretability of CNN representations by evaluating the alignment between individual hidden uni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05611","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":""},"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":"2026-05-18T00:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"apklcWcg/kP5EAlC+cO1WXsS1xr5Nx6EhlFxfL0Bd7sk80s1Zn0dORqvDkpG8o19E8q8SEAbjdM+79PdvLjIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T00:23:59.549399Z"},"content_sha256":"29ff25ab6ddd4e6e30ecb6c13036a63542c940c995638571f4dada30b1195ce1","schema_version":"1.0","event_id":"sha256:29ff25ab6ddd4e6e30ecb6c13036a63542c940c995638571f4dada30b1195ce1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GK4PYORHMG74YCA7CJESYCDXWQ/bundle.json","state_url":"https://pith.science/pith/GK4PYORHMG74YCA7CJESYCDXWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GK4PYORHMG74YCA7CJESYCDXWQ/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":"2026-05-26T00:23:59Z","links":{"resolver":"https://pith.science/pith/GK4PYORHMG74YCA7CJESYCDXWQ","bundle":"https://pith.science/pith/GK4PYORHMG74YCA7CJESYCDXWQ/bundle.json","state":"https://pith.science/pith/GK4PYORHMG74YCA7CJESYCDXWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GK4PYORHMG74YCA7CJESYCDXWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:GK4PYORHMG74YCA7CJESYCDXWQ","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":"ef0580f32657bbb50a5d533bab92f696c8698e8e0cd2cef9e1c536aa8d3e90d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T15:05:25Z","title_canon_sha256":"66c940d563a82537bcd7cbc3bd4012700987c148c39239a2eff838ba5d2718a7"},"schema_version":"1.0","source":{"id":"1711.05611","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.05611","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"1711.05611v2","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.05611","created_at":"2026-05-18T00:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"GK4PYORHMG74","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"GK4PYORHMG74YCA7","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"GK4PYORH","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:29ff25ab6ddd4e6e30ecb6c13036a63542c940c995638571f4dada30b1195ce1","target":"graph","created_at":"2026-05-18T00:12:24Z","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":"The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack interpretability, since they have millions of unexplained model parameters. In this work, we describe Network Dissection, a method that interprets networks by providing labels for the units of their deep visual representations. The proposed method quantifies the interpretability of CNN representations by evaluating the alignment between individual hidden uni","authors_text":"Antonio Torralba, Aude Oliva, Bolei Zhou, David Bau","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T15:05:25Z","title":"Interpreting Deep Visual Representations via Network Dissection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.05611","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:d9af565f57f64b2a344eb726f9cfb0e1564a3da35387388b941371c6c14edd20","target":"record","created_at":"2026-05-18T00:12:24Z","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":"ef0580f32657bbb50a5d533bab92f696c8698e8e0cd2cef9e1c536aa8d3e90d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-11-15T15:05:25Z","title_canon_sha256":"66c940d563a82537bcd7cbc3bd4012700987c148c39239a2eff838ba5d2718a7"},"schema_version":"1.0","source":{"id":"1711.05611","kind":"arxiv","version":2}},"canonical_sha256":"32b8fc3a2761bfcc081f12492c0877b415487cc62357fc1d1e97ffcc02ae0bc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32b8fc3a2761bfcc081f12492c0877b415487cc62357fc1d1e97ffcc02ae0bc4","first_computed_at":"2026-05-18T00:12:24.762520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:24.762520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QdFhZHxZAZS81RlaBERUvQ/HWUqAgKd0Lx/AvAiPEDzkCfkTUKVbJc87dp9rpiNopv6a3C3XzchY0YHlRbiGAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:24.763031Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.05611","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9af565f57f64b2a344eb726f9cfb0e1564a3da35387388b941371c6c14edd20","sha256:29ff25ab6ddd4e6e30ecb6c13036a63542c940c995638571f4dada30b1195ce1"],"state_sha256":"701778a63086e4c207239b40aafbf691799acd597e875dd8c5a80e5d9c696e5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3VDvg0p3lCD8juid1HwgeRE/XYGo2cuivXSdSXdOo5hLDER0qnBv5DGRp6ASblR6Fi1+FXV7ZC+il/n4HN7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T00:23:59.552860Z","bundle_sha256":"d744e0eeaaad76c630c3a605d7ae2dcd92b5a49dbedbb0bbc325cec3617ded48"}}