{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ORJ2ITSEEBDD3WQQFYIDQMJM57","short_pith_number":"pith:ORJ2ITSE","schema_version":"1.0","canonical_sha256":"7453a44e4420463dda102e1038312cefe624848505393f58c20b96aec6361f19","source":{"kind":"arxiv","id":"2112.13528","version":1},"attestation_state":"computed","paper":{"title":"Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwen Xie, Jing Zhang, Nick Barnes, Ping Li","submitted_at":"2021-12-27T06:04:33Z","abstract_excerpt":"Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection. Both the vision transformer network and the energy-based prior model are jointly trained via Markov chain Monte Carlo-based maximum likelihood estimation, in which the sampling from the intractable posterior and prior distributions of the latent variables are performed by Langevin dynamics. Further, with the generative vision trans"},"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":"2112.13528","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-27T06:04:33Z","cross_cats_sorted":[],"title_canon_sha256":"e2bb5dfe4733ba630fafb14a02566d882d0bc8e2fe5083dceb61f44b50e3611b","abstract_canon_sha256":"25af97112fc4f48263d3d7e2963cc4d6e7dfabe39532d0f42a7472028f10b379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:54.506912Z","signature_b64":"kXIE57PtoPcqHp/z4BDmXb1EaulD/mOdkRDbm4+msjCLnqgYIZjdQmq86T6hPzMHocmu7dGETL8vADTTTqLMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7453a44e4420463dda102e1038312cefe624848505393f58c20b96aec6361f19","last_reissued_at":"2026-07-05T03:43:54.506502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:54.506502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwen Xie, Jing Zhang, Nick Barnes, Ping Li","submitted_at":"2021-12-27T06:04:33Z","abstract_excerpt":"Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for salient object detection. Both the vision transformer network and the energy-based prior model are jointly trained via Markov chain Monte Carlo-based maximum likelihood estimation, in which the sampling from the intractable posterior and prior distributions of the latent variables are performed by Langevin dynamics. Further, with the generative vision trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.13528","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.13528/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2112.13528","created_at":"2026-07-05T03:43:54.506565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.13528v1","created_at":"2026-07-05T03:43:54.506565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.13528","created_at":"2026-07-05T03:43:54.506565+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORJ2ITSEEBDD","created_at":"2026-07-05T03:43:54.506565+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORJ2ITSEEBDD3WQQ","created_at":"2026-07-05T03:43:54.506565+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORJ2ITSE","created_at":"2026-07-05T03:43:54.506565+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/ORJ2ITSEEBDD3WQQFYIDQMJM57","json":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57.json","graph_json":"https://pith.science/api/pith-number/ORJ2ITSEEBDD3WQQFYIDQMJM57/graph.json","events_json":"https://pith.science/api/pith-number/ORJ2ITSEEBDD3WQQFYIDQMJM57/events.json","paper":"https://pith.science/paper/ORJ2ITSE"},"agent_actions":{"view_html":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57","download_json":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57.json","view_paper":"https://pith.science/paper/ORJ2ITSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.13528&json=true","fetch_graph":"https://pith.science/api/pith-number/ORJ2ITSEEBDD3WQQFYIDQMJM57/graph.json","fetch_events":"https://pith.science/api/pith-number/ORJ2ITSEEBDD3WQQFYIDQMJM57/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57/action/storage_attestation","attest_author":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57/action/author_attestation","sign_citation":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57/action/citation_signature","submit_replication":"https://pith.science/pith/ORJ2ITSEEBDD3WQQFYIDQMJM57/action/replication_record"}},"created_at":"2026-07-05T03:43:54.506565+00:00","updated_at":"2026-07-05T03:43:54.506565+00:00"}