{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SF7J6EAXEESYJAQJQKTXCFSJCH","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":"9be00c29c7dadac3693c6f8d3cb96db36d2c4518e592abf98d4703db1d20bbd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T17:22:50Z","title_canon_sha256":"fc84e2ebbe80c8c22890aaf611004ed3b66431d27a40bda4c08bee48e6b970b4"},"schema_version":"1.0","source":{"id":"2412.10292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10292","created_at":"2026-07-05T09:48:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10292v1","created_at":"2026-07-05T09:48:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10292","created_at":"2026-07-05T09:48:55Z"},{"alias_kind":"pith_short_12","alias_value":"SF7J6EAXEESY","created_at":"2026-07-05T09:48:55Z"},{"alias_kind":"pith_short_16","alias_value":"SF7J6EAXEESYJAQJ","created_at":"2026-07-05T09:48:55Z"},{"alias_kind":"pith_short_8","alias_value":"SF7J6EAX","created_at":"2026-07-05T09:48:55Z"}],"graph_snapshots":[{"event_id":"sha256:7d10aed857b990357f7eccea4447b7f41db5c0d4af974ab22774681f5cdc5628","target":"graph","created_at":"2026-07-05T09:48:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.10292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the challenge of open-vocabulary segmentation, where we need to identify objects from a wide range of categories in different environments, using text prompts as our input. To overcome this challenge, existing methods often use multi-modal models like CLIP, which combine image and text features in a shared embedding space to bridge the gap between limited and extensive vocabulary recognition, resulting in a two-stage approach: In the first stage, a mask generator takes an input image to generate mask proposals, and the in the second stage the target mask is picked based on the query.","authors_text":"Ajinkya Kale, Kun Wan, Lantao Yu, Xin Lu, Xinyang Zhang, Yu-Jhe Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T17:22:50Z","title":"Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10292","kind":"arxiv","version":1},"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":"sha256:70fca622d32a78f306d50e3a1e5a73d6ba4847ddf002eaf14a0755840022e363","target":"record","created_at":"2026-07-05T09:48:55Z","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":"9be00c29c7dadac3693c6f8d3cb96db36d2c4518e592abf98d4703db1d20bbd4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T17:22:50Z","title_canon_sha256":"fc84e2ebbe80c8c22890aaf611004ed3b66431d27a40bda4c08bee48e6b970b4"},"schema_version":"1.0","source":{"id":"2412.10292","kind":"arxiv","version":1}},"canonical_sha256":"917e9f1017212584820982a771164911fb0fb3836d77b24c947fa767312ec888","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"917e9f1017212584820982a771164911fb0fb3836d77b24c947fa767312ec888","first_computed_at":"2026-07-05T09:48:55.873750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:55.873750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hH4LecS+MLOr779TyFVLquqKSpGyF3zU7dlsqcUr6Ajln8YlJ2wm1OtS4PLk0K9i3q7l7FZZxVhPzAhe6NOVCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:55.874288Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70fca622d32a78f306d50e3a1e5a73d6ba4847ddf002eaf14a0755840022e363","sha256:7d10aed857b990357f7eccea4447b7f41db5c0d4af974ab22774681f5cdc5628"],"state_sha256":"75423b8650354a468d5a1969868f9e1f7be11fb303c9977862d6fe6427494ec2"}