{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LT6ZQLVUYUSOKBGYEKF7Z2YM6M","short_pith_number":"pith:LT6ZQLVU","schema_version":"1.0","canonical_sha256":"5cfd982eb4c524e504d8228bfceb0cf30ed30665a5d940168eb9568d5361595d","source":{"kind":"arxiv","id":"1705.07450","version":2},"attestation_state":"computed","paper":{"title":"Image Segmentation by Iterative Inference from Conditional Score Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Romero, Akram Erraqabi, Michal Drozdzal, Simon J\\'egou, Yoshua Bengio","submitted_at":"2017-05-21T13:56:03Z","abstract_excerpt":"Inspired by the combination of feedforward and iterative computations in the virtual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of a joint distribution, we propose a novel approach to iterative inference for capturing and exploiting the complex joint distribution of output variables conditioned on some input variables. This approach is applied to image pixel-wise segmentation, with the estimated conditional score used to perform gradient ascent towards a mode of the estimated conditional distribution. This extends previous work on score estimati"},"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":"1705.07450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-21T13:56:03Z","cross_cats_sorted":[],"title_canon_sha256":"742f51df59042197c82db46a58a59830342fa026c24bb0a1047fcb5137530689","abstract_canon_sha256":"b6704741fd6d01ad7da23685f7cfc7b48b6bb93166ceab9d6ae9cf5d61ab7d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:47.344565Z","signature_b64":"kLJfcXs89yLIITVB2Z8qCHYG9VCxlW1IadCkBm58ldF+sn313RzMS1M2+s9RS19W3Y+cfQ2WeUGgXfw425FUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cfd982eb4c524e504d8228bfceb0cf30ed30665a5d940168eb9568d5361595d","last_reissued_at":"2026-05-18T00:37:47.343766Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:47.343766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Segmentation by Iterative Inference from Conditional Score Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adriana Romero, Akram Erraqabi, Michal Drozdzal, Simon J\\'egou, Yoshua Bengio","submitted_at":"2017-05-21T13:56:03Z","abstract_excerpt":"Inspired by the combination of feedforward and iterative computations in the virtual cortex, and taking advantage of the ability of denoising autoencoders to estimate the score of a joint distribution, we propose a novel approach to iterative inference for capturing and exploiting the complex joint distribution of output variables conditioned on some input variables. This approach is applied to image pixel-wise segmentation, with the estimated conditional score used to perform gradient ascent towards a mode of the estimated conditional distribution. This extends previous work on score estimati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07450","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":"1705.07450","created_at":"2026-05-18T00:37:47.343905+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07450v2","created_at":"2026-05-18T00:37:47.343905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07450","created_at":"2026-05-18T00:37:47.343905+00:00"},{"alias_kind":"pith_short_12","alias_value":"LT6ZQLVUYUSO","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LT6ZQLVUYUSOKBGY","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LT6ZQLVU","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19474","citing_title":"Harmonizing MR Images Across 100+ Scanners: Multi-site Validation with Traveling Subjects and Real-world Protocols","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M","json":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M.json","graph_json":"https://pith.science/api/pith-number/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/graph.json","events_json":"https://pith.science/api/pith-number/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/events.json","paper":"https://pith.science/paper/LT6ZQLVU"},"agent_actions":{"view_html":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M","download_json":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M.json","view_paper":"https://pith.science/paper/LT6ZQLVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07450&json=true","fetch_graph":"https://pith.science/api/pith-number/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/graph.json","fetch_events":"https://pith.science/api/pith-number/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/action/storage_attestation","attest_author":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/action/author_attestation","sign_citation":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/action/citation_signature","submit_replication":"https://pith.science/pith/LT6ZQLVUYUSOKBGYEKF7Z2YM6M/action/replication_record"}},"created_at":"2026-05-18T00:37:47.343905+00:00","updated_at":"2026-05-18T00:37:47.343905+00:00"}