{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:MAQHVBRTYTCSQ6JCWN5PKUFWBC","short_pith_number":"pith:MAQHVBRT","canonical_record":{"source":{"id":"1607.05851","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-20T07:58:57Z","cross_cats_sorted":[],"title_canon_sha256":"44555e75dca199a371d93e0bd88810e4931f4884dc47a131f58457542f6a4722","abstract_canon_sha256":"046eba11f2fa5735f2a5dee676312c60c63034398dfaf507cdf29fa8d79a641e"},"schema_version":"1.0"},"canonical_sha256":"60207a8633c4c5287922b37af550b608b385afe5e96bf7e479071c9a5ca0e325","source":{"kind":"arxiv","id":"1607.05851","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05851","created_at":"2026-05-18T00:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05851v3","created_at":"2026-05-18T00:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05851","created_at":"2026-05-18T00:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"MAQHVBRTYTCS","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MAQHVBRTYTCSQ6JC","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MAQHVBRT","created_at":"2026-05-18T12:30:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:MAQHVBRTYTCSQ6JCWN5PKUFWBC","target":"record","payload":{"canonical_record":{"source":{"id":"1607.05851","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-20T07:58:57Z","cross_cats_sorted":[],"title_canon_sha256":"44555e75dca199a371d93e0bd88810e4931f4884dc47a131f58457542f6a4722","abstract_canon_sha256":"046eba11f2fa5735f2a5dee676312c60c63034398dfaf507cdf29fa8d79a641e"},"schema_version":"1.0"},"canonical_sha256":"60207a8633c4c5287922b37af550b608b385afe5e96bf7e479071c9a5ca0e325","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:23.028134Z","signature_b64":"baHggWv7Jy3u1k5or1De5tkl2j+e5GkObDGglphovdzASwgohfk/ntMXhGR0gwlLN2t+shlYJDEorLUwLjmzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60207a8633c4c5287922b37af550b608b385afe5e96bf7e479071c9a5ca0e325","last_reissued_at":"2026-05-18T00:52:23.027546Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:23.027546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.05851","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k12jlFz/HfVCP3N1Pg/U3yheiV7c3IFiG0mldykyK+TVxcWzjW7tliKdHWIZOGcRdFzge1B4nHmkHel/tkq3Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:09:44.298291Z"},"content_sha256":"404592b0c5a3cf4d8c39fb2d3e0754d604991f39ac3f86933a1616b868190780","schema_version":"1.0","event_id":"sha256:404592b0c5a3cf4d8c39fb2d3e0754d604991f39ac3f86933a1616b868190780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:MAQHVBRTYTCSQ6JCWN5PKUFWBC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Recognize Objects by Retaining other Factors of Variation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chin-kai Chang, Jiaping Zhao, Laurent Itti","submitted_at":"2016-07-20T07:58:57Z","abstract_excerpt":"Natural images are generated under many factors, including shape, pose, illumination etc. Most existing ConvNets formulate object recognition from natural images as a single task classification problem, and attempt to learn features useful for object categories, but invariant to other factors of variation as much as possible. These architectures do not explicitly learn other factors, like pose and lighting, instead, they usually discard them by pooling and normalization. In this work, we take the opposite approach: we train ConvNets for object recognition by retaining other factors (pose in ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05851","kind":"arxiv","version":3},"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":"2026-05-18T00:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYGigld00xRH8jEh+EMHU3ZqM2zdi5Twf4/z8SxTAsG377GupE1TrvU6dk3j1AHaaVaDS2w2ti+Q7jgs43CTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:09:44.298934Z"},"content_sha256":"043fa77c669699061d432ae660b3741e289f572c7336fea049eaabdf39cbbb7d","schema_version":"1.0","event_id":"sha256:043fa77c669699061d432ae660b3741e289f572c7336fea049eaabdf39cbbb7d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC/bundle.json","state_url":"https://pith.science/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC/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":"2026-06-06T04:09:44Z","links":{"resolver":"https://pith.science/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC","bundle":"https://pith.science/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC/bundle.json","state":"https://pith.science/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAQHVBRTYTCSQ6JCWN5PKUFWBC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:MAQHVBRTYTCSQ6JCWN5PKUFWBC","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":"046eba11f2fa5735f2a5dee676312c60c63034398dfaf507cdf29fa8d79a641e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-20T07:58:57Z","title_canon_sha256":"44555e75dca199a371d93e0bd88810e4931f4884dc47a131f58457542f6a4722"},"schema_version":"1.0","source":{"id":"1607.05851","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05851","created_at":"2026-05-18T00:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05851v3","created_at":"2026-05-18T00:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05851","created_at":"2026-05-18T00:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"MAQHVBRTYTCS","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_16","alias_value":"MAQHVBRTYTCSQ6JC","created_at":"2026-05-18T12:30:32Z"},{"alias_kind":"pith_short_8","alias_value":"MAQHVBRT","created_at":"2026-05-18T12:30:32Z"}],"graph_snapshots":[{"event_id":"sha256:043fa77c669699061d432ae660b3741e289f572c7336fea049eaabdf39cbbb7d","target":"graph","created_at":"2026-05-18T00:52:23Z","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":"Natural images are generated under many factors, including shape, pose, illumination etc. Most existing ConvNets formulate object recognition from natural images as a single task classification problem, and attempt to learn features useful for object categories, but invariant to other factors of variation as much as possible. These architectures do not explicitly learn other factors, like pose and lighting, instead, they usually discard them by pooling and normalization. In this work, we take the opposite approach: we train ConvNets for object recognition by retaining other factors (pose in ou","authors_text":"Chin-kai Chang, Jiaping Zhao, Laurent Itti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-20T07:58:57Z","title":"Learning to Recognize Objects by Retaining other Factors of Variation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05851","kind":"arxiv","version":3},"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":"sha256:404592b0c5a3cf4d8c39fb2d3e0754d604991f39ac3f86933a1616b868190780","target":"record","created_at":"2026-05-18T00:52:23Z","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":"046eba11f2fa5735f2a5dee676312c60c63034398dfaf507cdf29fa8d79a641e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-07-20T07:58:57Z","title_canon_sha256":"44555e75dca199a371d93e0bd88810e4931f4884dc47a131f58457542f6a4722"},"schema_version":"1.0","source":{"id":"1607.05851","kind":"arxiv","version":3}},"canonical_sha256":"60207a8633c4c5287922b37af550b608b385afe5e96bf7e479071c9a5ca0e325","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60207a8633c4c5287922b37af550b608b385afe5e96bf7e479071c9a5ca0e325","first_computed_at":"2026-05-18T00:52:23.027546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:23.027546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"baHggWv7Jy3u1k5or1De5tkl2j+e5GkObDGglphovdzASwgohfk/ntMXhGR0gwlLN2t+shlYJDEorLUwLjmzAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:23.028134Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.05851","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:404592b0c5a3cf4d8c39fb2d3e0754d604991f39ac3f86933a1616b868190780","sha256:043fa77c669699061d432ae660b3741e289f572c7336fea049eaabdf39cbbb7d"],"state_sha256":"8fced26120ecc6a45e62658f79ce95ab79cb26bc6fbc78e243584857790c94b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7agbMAixVUROz6y25g7/i51e6iaY2qitBBvvg1y+1BUFni7xbYTZv3mHN4IdChkHTbftayn6Bq7wDhNt4A+cCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T04:09:44.301407Z","bundle_sha256":"1a8009512d97bdf712b9792cc51d31450799c4d326fd4b632bdb3665987316c2"}}