{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:PB4GFYSFTNYSER2XK2YMGPUKZO","short_pith_number":"pith:PB4GFYSF","canonical_record":{"source":{"id":"1301.3572","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-16T03:31:30Z","cross_cats_sorted":[],"title_canon_sha256":"09747cdcefeeada991389838f05ea4c51abe41e95481f2603917d16fe5ccff70","abstract_canon_sha256":"b13595b1b02f1876ff2ef18bdc921cb0a086027944b8337ee8403dd8bfc143ef"},"schema_version":"1.0"},"canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","source":{"kind":"arxiv","id":"1301.3572","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.3572","created_at":"2026-05-18T03:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"1301.3572v2","created_at":"2026-05-18T03:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3572","created_at":"2026-05-18T03:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"PB4GFYSFTNYS","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"PB4GFYSFTNYSER2X","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"PB4GFYSF","created_at":"2026-05-18T12:27:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:PB4GFYSFTNYSER2XK2YMGPUKZO","target":"record","payload":{"canonical_record":{"source":{"id":"1301.3572","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-16T03:31:30Z","cross_cats_sorted":[],"title_canon_sha256":"09747cdcefeeada991389838f05ea4c51abe41e95481f2603917d16fe5ccff70","abstract_canon_sha256":"b13595b1b02f1876ff2ef18bdc921cb0a086027944b8337ee8403dd8bfc143ef"},"schema_version":"1.0"},"canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:55.024122Z","signature_b64":"vRpmzoGdu6jkuidtJYVVy2j/df8DaguV9GLb+l9zz70YqShdfDVDwjmO5nkJY6ljsT+pN9ivDX2L710fsqO+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","last_reissued_at":"2026-05-18T03:30:55.023431Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:55.023431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1301.3572","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":"2026-05-18T03:30:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XlG6w4VSHJ8bpGGYAaOQZuD/o5iKMBIw5jxDllJXSQgrHE73fnD9fdM0CYP/bdtUNkx8oD8bxJ18Xno+XQ02AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:50:11.179872Z"},"content_sha256":"1296302fbd3d6b5b9c0c053723aff4ef4823d087c064f0560c014fb8bc5ee6e5","schema_version":"1.0","event_id":"sha256:1296302fbd3d6b5b9c0c053723aff4ef4823d087c064f0560c014fb8bc5ee6e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:PB4GFYSFTNYSER2XK2YMGPUKZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Indoor Semantic Segmentation using depth information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Camille Couprie, Cl\\'ement Farabet, Laurent Najman, Yann LeCun","submitted_at":"2013-01-16T03:31:30Z","abstract_excerpt":"This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale convolutional network to learn features directly from the images and the depth information. We obtain state-of-the-art on the NYU-v2 depth dataset with an accuracy of 64.5%. We illustrate the labeling of indoor scenes in videos sequences that could be processed in real-time using appropriate hardware such as an FPGA."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3572","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":"2026-05-18T03:30:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tn+hRAfhl0uxdCKnEnE41TAtVTLPMFxaABBv0mxp3STOafkCC03TSpJN4Q4Q8UvDc3ZAuOi++QadHYE+7lwYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T17:50:11.180269Z"},"content_sha256":"cb21326593bc2febf14499eb6f28f31e0515e2e0aab7b476c77fb8a67cd36c16","schema_version":"1.0","event_id":"sha256:cb21326593bc2febf14499eb6f28f31e0515e2e0aab7b476c77fb8a67cd36c16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/bundle.json","state_url":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/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":"2026-05-21T17:50:11Z","links":{"resolver":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO","bundle":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/bundle.json","state":"https://pith.science/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PB4GFYSFTNYSER2XK2YMGPUKZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:PB4GFYSFTNYSER2XK2YMGPUKZO","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":"b13595b1b02f1876ff2ef18bdc921cb0a086027944b8337ee8403dd8bfc143ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-16T03:31:30Z","title_canon_sha256":"09747cdcefeeada991389838f05ea4c51abe41e95481f2603917d16fe5ccff70"},"schema_version":"1.0","source":{"id":"1301.3572","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.3572","created_at":"2026-05-18T03:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"1301.3572v2","created_at":"2026-05-18T03:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3572","created_at":"2026-05-18T03:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"PB4GFYSFTNYS","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_16","alias_value":"PB4GFYSFTNYSER2X","created_at":"2026-05-18T12:27:54Z"},{"alias_kind":"pith_short_8","alias_value":"PB4GFYSF","created_at":"2026-05-18T12:27:54Z"}],"graph_snapshots":[{"event_id":"sha256:cb21326593bc2febf14499eb6f28f31e0515e2e0aab7b476c77fb8a67cd36c16","target":"graph","created_at":"2026-05-18T03:30:55Z","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":"This work addresses multi-class segmentation of indoor scenes with RGB-D inputs. While this area of research has gained much attention recently, most works still rely on hand-crafted features. In contrast, we apply a multiscale convolutional network to learn features directly from the images and the depth information. We obtain state-of-the-art on the NYU-v2 depth dataset with an accuracy of 64.5%. We illustrate the labeling of indoor scenes in videos sequences that could be processed in real-time using appropriate hardware such as an FPGA.","authors_text":"Camille Couprie, Cl\\'ement Farabet, Laurent Najman, Yann LeCun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-16T03:31:30Z","title":"Indoor Semantic Segmentation using depth information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3572","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":"sha256:1296302fbd3d6b5b9c0c053723aff4ef4823d087c064f0560c014fb8bc5ee6e5","target":"record","created_at":"2026-05-18T03:30:55Z","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":"b13595b1b02f1876ff2ef18bdc921cb0a086027944b8337ee8403dd8bfc143ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-01-16T03:31:30Z","title_canon_sha256":"09747cdcefeeada991389838f05ea4c51abe41e95481f2603917d16fe5ccff70"},"schema_version":"1.0","source":{"id":"1301.3572","kind":"arxiv","version":2}},"canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"787862e2459b7122475756b0c33e8acbbe920ea4191bf0eb6cbdea6c16ab67f2","first_computed_at":"2026-05-18T03:30:55.023431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:30:55.023431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vRpmzoGdu6jkuidtJYVVy2j/df8DaguV9GLb+l9zz70YqShdfDVDwjmO5nkJY6ljsT+pN9ivDX2L710fsqO+AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:30:55.024122Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.3572","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1296302fbd3d6b5b9c0c053723aff4ef4823d087c064f0560c014fb8bc5ee6e5","sha256:cb21326593bc2febf14499eb6f28f31e0515e2e0aab7b476c77fb8a67cd36c16"],"state_sha256":"7dffe2267767168e90e282a99b9a671f1869d30ae2c16c68ec0941a2e2d66190"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qtvhJOXPa3bRX1kH7qo13oa5HVCIMTDNlvbhcbdWtF/pgM0Bg8cX5b2UiuRealCVTYil98dFzKxQLZmQffnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T17:50:11.182543Z","bundle_sha256":"fc93fa904b66cc0661d78ff0a0ef535a13e8a27545573ce3f4b710045e95db59"}}