{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:NTC5DP7QT3ZTNMRV7G2H2ICHRK","short_pith_number":"pith:NTC5DP7Q","canonical_record":{"source":{"id":"1412.5903","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-18T15:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"7fae54224d32bfa3cb1a68553a00516fd5d2744306dd18e8df58d5c034a6de7b","abstract_canon_sha256":"56569c91ce1a42395acd32f2e38b747a9aef541a0604fc63295353f3fbcad11e"},"schema_version":"1.0"},"canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","source":{"kind":"arxiv","id":"1412.5903","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.5903","created_at":"2026-05-18T02:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"1412.5903v5","created_at":"2026-05-18T02:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.5903","created_at":"2026-05-18T02:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"NTC5DP7QT3ZT","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"NTC5DP7QT3ZTNMRV","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"NTC5DP7Q","created_at":"2026-05-18T12:28:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:NTC5DP7QT3ZTNMRV7G2H2ICHRK","target":"record","payload":{"canonical_record":{"source":{"id":"1412.5903","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-18T15:49:46Z","cross_cats_sorted":[],"title_canon_sha256":"7fae54224d32bfa3cb1a68553a00516fd5d2744306dd18e8df58d5c034a6de7b","abstract_canon_sha256":"56569c91ce1a42395acd32f2e38b747a9aef541a0604fc63295353f3fbcad11e"},"schema_version":"1.0"},"canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:07.986892Z","signature_b64":"Jp21ImN+c6M5lNtrdBe5ljxk1+LaS3JoU7/vdfHbQawfWFZqWPnyJFNgaCO+jTTTxEAFnEjXfGGEqPRWPCirBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","last_reissued_at":"2026-05-18T02:19:07.986412Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:07.986412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.5903","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lpDyX1vKoSJbZcpFz68bX+bJrn5egTdeb661CFKyssq6ptfcv8WAQZfInNWafhYpbzorGQKE4B7+josAhbwzDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:04:32.980778Z"},"content_sha256":"68d78c99043fcc24e1bc45bf86a43f53a6a8f44e6306750fb1e61bd38278e59e","schema_version":"1.0","event_id":"sha256:68d78c99043fcc24e1bc45bf86a43f53a6a8f44e6306750fb1e61bd38278e59e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:NTC5DP7QT3ZTNMRV7G2H2ICHRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Structured Output Learning for Unconstrained Text Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Max Jaderberg","submitted_at":"2014-12-18T15:49:46Z","abstract_excerpt":"We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length.\n  To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical model, taking the whole word image as a single input. The unaries of the CRF are provided by a CNN that predicts characters at each position of the output, while higher order terms are provided by another CNN that detects the presence of N-grams. We show that this entire model (CRF, character predict"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.5903","kind":"arxiv","version":5},"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":"2026-05-18T02:19:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hechD4qb7P4zoJyMuZy4XPJuATp6GZShKggbz/6UKl7LyBO7pxBh5+M8JICJoJJkXNmeFz2EO+urukXSpFtAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:04:32.981481Z"},"content_sha256":"06d41710416e3a28fb22a8355bc50c4d20219ebed66ccabc35e78934b33764d0","schema_version":"1.0","event_id":"sha256:06d41710416e3a28fb22a8355bc50c4d20219ebed66ccabc35e78934b33764d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/bundle.json","state_url":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/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":"2026-05-25T08:04:32Z","links":{"resolver":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK","bundle":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/bundle.json","state":"https://pith.science/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NTC5DP7QT3ZTNMRV7G2H2ICHRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:NTC5DP7QT3ZTNMRV7G2H2ICHRK","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":"56569c91ce1a42395acd32f2e38b747a9aef541a0604fc63295353f3fbcad11e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-18T15:49:46Z","title_canon_sha256":"7fae54224d32bfa3cb1a68553a00516fd5d2744306dd18e8df58d5c034a6de7b"},"schema_version":"1.0","source":{"id":"1412.5903","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.5903","created_at":"2026-05-18T02:19:07Z"},{"alias_kind":"arxiv_version","alias_value":"1412.5903v5","created_at":"2026-05-18T02:19:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.5903","created_at":"2026-05-18T02:19:07Z"},{"alias_kind":"pith_short_12","alias_value":"NTC5DP7QT3ZT","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_16","alias_value":"NTC5DP7QT3ZTNMRV","created_at":"2026-05-18T12:28:41Z"},{"alias_kind":"pith_short_8","alias_value":"NTC5DP7Q","created_at":"2026-05-18T12:28:41Z"}],"graph_snapshots":[{"event_id":"sha256:06d41710416e3a28fb22a8355bc50c4d20219ebed66ccabc35e78934b33764d0","target":"graph","created_at":"2026-05-18T02:19:07Z","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":"We develop a representation suitable for the unconstrained recognition of words in natural images: the general case of no fixed lexicon and unknown length.\n  To this end we propose a convolutional neural network (CNN) based architecture which incorporates a Conditional Random Field (CRF) graphical model, taking the whole word image as a single input. The unaries of the CRF are provided by a CNN that predicts characters at each position of the output, while higher order terms are provided by another CNN that detects the presence of N-grams. We show that this entire model (CRF, character predict","authors_text":"Andrea Vedaldi, Andrew Zisserman, Karen Simonyan, Max Jaderberg","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-18T15:49:46Z","title":"Deep Structured Output Learning for Unconstrained Text Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.5903","kind":"arxiv","version":5},"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":"sha256:68d78c99043fcc24e1bc45bf86a43f53a6a8f44e6306750fb1e61bd38278e59e","target":"record","created_at":"2026-05-18T02:19:07Z","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":"56569c91ce1a42395acd32f2e38b747a9aef541a0604fc63295353f3fbcad11e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-12-18T15:49:46Z","title_canon_sha256":"7fae54224d32bfa3cb1a68553a00516fd5d2744306dd18e8df58d5c034a6de7b"},"schema_version":"1.0","source":{"id":"1412.5903","kind":"arxiv","version":5}},"canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6cc5d1bff09ef336b235f9b47d20478abaa1e588681c0fac77b8e8ab67751366","first_computed_at":"2026-05-18T02:19:07.986412Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:19:07.986412Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jp21ImN+c6M5lNtrdBe5ljxk1+LaS3JoU7/vdfHbQawfWFZqWPnyJFNgaCO+jTTTxEAFnEjXfGGEqPRWPCirBA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:19:07.986892Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.5903","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68d78c99043fcc24e1bc45bf86a43f53a6a8f44e6306750fb1e61bd38278e59e","sha256:06d41710416e3a28fb22a8355bc50c4d20219ebed66ccabc35e78934b33764d0"],"state_sha256":"18cbca1b77b0181c406441d4bec222a20ab8c8cd51ca7fc21451a0f122362539"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pwjby41BuXFnEjlU12pEF/ST81wjPSO4X8UxkZR9HllKk1GbAqvmT1i2ftTSf2NjTlZ5F/mnPju5C5DYvmuvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:04:32.985203Z","bundle_sha256":"0883acf8f2ddf123bbb73908acb414fcb8fd2c9e715074c8595753d2b319df66"}}