{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Z3ZIFGFVSRKMXWH46RDDGEUYUS","short_pith_number":"pith:Z3ZIFGFV","schema_version":"1.0","canonical_sha256":"cef28298b59454cbd8fcf446331298a4925a56af897bd9ca0d5d4097a808e6e5","source":{"kind":"arxiv","id":"1605.07078","version":2},"attestation_state":"computed","paper":{"title":"Learning Sensor Multiplexing Design through Back-propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayan Chakrabarti","submitted_at":"2016-05-23T16:26:59Z","abstract_excerpt":"Recent progress on many imaging and vision tasks has been driven by the use of deep feed-forward neural networks, which are trained by propagating gradients of a loss defined on the final output, back through the network up to the first layer that operates directly on the image. We propose back-propagating one step further---to learn camera sensor designs jointly with networks that carry out inference on the images they capture. In this paper, we specifically consider the design and inference problems in a typical color camera---where the sensor is able to measure only one color channel at eac"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1605.07078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-05-23T16:26:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4319f313c78f389ca6f9d5cbca860d7049a6f7d6753189d3c30daa9b43074543","abstract_canon_sha256":"e55439f498c5f89ea3b935bb226d5626a1f5de6d1fe049daae4b5c4a800d4537"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:35.050420Z","signature_b64":"GGgo6J3kprX9ZU7Q3nsz1S1djdh6CxlIFm3ehx3lNHhRO9rao1yyeSKL9bu4SDIxg//lC6L8wXFInAh4jzLIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cef28298b59454cbd8fcf446331298a4925a56af897bd9ca0d5d4097a808e6e5","last_reissued_at":"2026-05-18T01:00:35.049724Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:35.049724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Sensor Multiplexing Design through Back-propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ayan Chakrabarti","submitted_at":"2016-05-23T16:26:59Z","abstract_excerpt":"Recent progress on many imaging and vision tasks has been driven by the use of deep feed-forward neural networks, which are trained by propagating gradients of a loss defined on the final output, back through the network up to the first layer that operates directly on the image. We propose back-propagating one step further---to learn camera sensor designs jointly with networks that carry out inference on the images they capture. In this paper, we specifically consider the design and inference problems in a typical color camera---where the sensor is able to measure only one color channel at eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07078","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1605.07078","created_at":"2026-05-18T01:00:35.049834+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07078v2","created_at":"2026-05-18T01:00:35.049834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07078","created_at":"2026-05-18T01:00:35.049834+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z3ZIFGFVSRKM","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z3ZIFGFVSRKMXWH4","created_at":"2026-05-18T12:30:53.716459+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z3ZIFGFV","created_at":"2026-05-18T12:30:53.716459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS","json":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS.json","graph_json":"https://pith.science/api/pith-number/Z3ZIFGFVSRKMXWH46RDDGEUYUS/graph.json","events_json":"https://pith.science/api/pith-number/Z3ZIFGFVSRKMXWH46RDDGEUYUS/events.json","paper":"https://pith.science/paper/Z3ZIFGFV"},"agent_actions":{"view_html":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS","download_json":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS.json","view_paper":"https://pith.science/paper/Z3ZIFGFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07078&json=true","fetch_graph":"https://pith.science/api/pith-number/Z3ZIFGFVSRKMXWH46RDDGEUYUS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z3ZIFGFVSRKMXWH46RDDGEUYUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS/action/storage_attestation","attest_author":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS/action/author_attestation","sign_citation":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS/action/citation_signature","submit_replication":"https://pith.science/pith/Z3ZIFGFVSRKMXWH46RDDGEUYUS/action/replication_record"}},"created_at":"2026-05-18T01:00:35.049834+00:00","updated_at":"2026-05-18T01:00:35.049834+00:00"}