{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T4GNDF6CD24YXSKZ4FNMQTN65D","short_pith_number":"pith:T4GNDF6C","canonical_record":{"source":{"id":"2301.05221","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:08Z","cross_cats_sorted":[],"title_canon_sha256":"0f6d7cca9433c8a80c6cd1d8779edf9d119679d5d1126adb9e7e080410202f12","abstract_canon_sha256":"d8634673cb806017ff75041407c582dde4c7f82eb9d6aad179ed23cd3a5ccd51"},"schema_version":"1.0"},"canonical_sha256":"9f0cd197c21eb98bc959e15ac84dbee8c7735d96f3e6ad1d54cd12fec7f10522","source":{"kind":"arxiv","id":"2301.05221","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05221","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05221v2","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05221","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"T4GNDF6CD24Y","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"pith_short_16","alias_value":"T4GNDF6CD24YXSKZ","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"pith_short_8","alias_value":"T4GNDF6C","created_at":"2026-07-05T06:39:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T4GNDF6CD24YXSKZ4FNMQTN65D","target":"record","payload":{"canonical_record":{"source":{"id":"2301.05221","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:08Z","cross_cats_sorted":[],"title_canon_sha256":"0f6d7cca9433c8a80c6cd1d8779edf9d119679d5d1126adb9e7e080410202f12","abstract_canon_sha256":"d8634673cb806017ff75041407c582dde4c7f82eb9d6aad179ed23cd3a5ccd51"},"schema_version":"1.0"},"canonical_sha256":"9f0cd197c21eb98bc959e15ac84dbee8c7735d96f3e6ad1d54cd12fec7f10522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:51.351659Z","signature_b64":"baJiCtCW0GfMBOcgaIpI6C2oWBNgvXedE9W6cxpYhnMwqKoXJhMvEBpOfPt/x5IFNQAhBOzxlowKF2urfVNFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0cd197c21eb98bc959e15ac84dbee8c7735d96f3e6ad1d54cd12fec7f10522","last_reissued_at":"2026-07-05T06:39:51.351232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:51.351232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.05221","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":"2026-07-05T06:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M03qGa0WNLcgn9ShFb2X0EnJca2GZMeAOErDPQOPCOjjNR0+/SesAGUZda+qJYn2bfHy98fJsdrMYZCOtC2dBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:20:56.365542Z"},"content_sha256":"823512d09a6fa28662613cbcd21cc99733e9076050f7ad403afe7fea30e29de4","schema_version":"1.0","event_id":"sha256:823512d09a6fa28662613cbcd21cc99733e9076050f7ad403afe7fea30e29de4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T4GNDF6CD24YXSKZ4FNMQTN65D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Open-vocabulary Object Segmentation with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qinye Zhou, Weidi Xie, Xiaoyun Zhang, Yanfeng Wang, Ya Zhang, Ziyi Li","submitted_at":"2023-01-12T18:59:08Z","abstract_excerpt":"The goal of this paper is to extract the visual-language correspondence from a pre-trained text-to-image diffusion model, in the form of segmentation map, i.e., simultaneously generating images and segmentation masks for the corresponding visual entities described in the text prompt. We make the following contributions: (i) we pair the existing Stable Diffusion model with a novel grounding module, that can be trained to align the visual and textual embedding space of the diffusion model with only a small number of object categories; (ii) we establish an automatic pipeline for constructing a da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05221","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.05221/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:39:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"udps6YJzhtLTsE25F92GJMXfeCgrmHNSzxKw8+AtD+s1+wIk+oGgoRnzolGIg7n8QGWOLANDCnFbX9ECzQjfCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:20:56.366186Z"},"content_sha256":"9894fb62f637870a274b4561ab61973b9bd62a23227a4b7d62e5d19f5fb5cc69","schema_version":"1.0","event_id":"sha256:9894fb62f637870a274b4561ab61973b9bd62a23227a4b7d62e5d19f5fb5cc69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4GNDF6CD24YXSKZ4FNMQTN65D/bundle.json","state_url":"https://pith.science/pith/T4GNDF6CD24YXSKZ4FNMQTN65D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4GNDF6CD24YXSKZ4FNMQTN65D/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":"2026-08-03T16:20:56Z","links":{"resolver":"https://pith.science/pith/T4GNDF6CD24YXSKZ4FNMQTN65D","bundle":"https://pith.science/pith/T4GNDF6CD24YXSKZ4FNMQTN65D/bundle.json","state":"https://pith.science/pith/T4GNDF6CD24YXSKZ4FNMQTN65D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4GNDF6CD24YXSKZ4FNMQTN65D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T4GNDF6CD24YXSKZ4FNMQTN65D","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":"d8634673cb806017ff75041407c582dde4c7f82eb9d6aad179ed23cd3a5ccd51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:08Z","title_canon_sha256":"0f6d7cca9433c8a80c6cd1d8779edf9d119679d5d1126adb9e7e080410202f12"},"schema_version":"1.0","source":{"id":"2301.05221","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.05221","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"arxiv_version","alias_value":"2301.05221v2","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.05221","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"pith_short_12","alias_value":"T4GNDF6CD24Y","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"pith_short_16","alias_value":"T4GNDF6CD24YXSKZ","created_at":"2026-07-05T06:39:51Z"},{"alias_kind":"pith_short_8","alias_value":"T4GNDF6C","created_at":"2026-07-05T06:39:51Z"}],"graph_snapshots":[{"event_id":"sha256:9894fb62f637870a274b4561ab61973b9bd62a23227a4b7d62e5d19f5fb5cc69","target":"graph","created_at":"2026-07-05T06:39:51Z","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/2301.05221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to extract the visual-language correspondence from a pre-trained text-to-image diffusion model, in the form of segmentation map, i.e., simultaneously generating images and segmentation masks for the corresponding visual entities described in the text prompt. We make the following contributions: (i) we pair the existing Stable Diffusion model with a novel grounding module, that can be trained to align the visual and textual embedding space of the diffusion model with only a small number of object categories; (ii) we establish an automatic pipeline for constructing a da","authors_text":"Qinye Zhou, Weidi Xie, Xiaoyun Zhang, Yanfeng Wang, Ya Zhang, Ziyi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:08Z","title":"Open-vocabulary Object Segmentation with Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.05221","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":"sha256:823512d09a6fa28662613cbcd21cc99733e9076050f7ad403afe7fea30e29de4","target":"record","created_at":"2026-07-05T06:39:51Z","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":"d8634673cb806017ff75041407c582dde4c7f82eb9d6aad179ed23cd3a5ccd51","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-01-12T18:59:08Z","title_canon_sha256":"0f6d7cca9433c8a80c6cd1d8779edf9d119679d5d1126adb9e7e080410202f12"},"schema_version":"1.0","source":{"id":"2301.05221","kind":"arxiv","version":2}},"canonical_sha256":"9f0cd197c21eb98bc959e15ac84dbee8c7735d96f3e6ad1d54cd12fec7f10522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f0cd197c21eb98bc959e15ac84dbee8c7735d96f3e6ad1d54cd12fec7f10522","first_computed_at":"2026-07-05T06:39:51.351232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:51.351232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"baJiCtCW0GfMBOcgaIpI6C2oWBNgvXedE9W6cxpYhnMwqKoXJhMvEBpOfPt/x5IFNQAhBOzxlowKF2urfVNFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:51.351659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.05221","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:823512d09a6fa28662613cbcd21cc99733e9076050f7ad403afe7fea30e29de4","sha256:9894fb62f637870a274b4561ab61973b9bd62a23227a4b7d62e5d19f5fb5cc69"],"state_sha256":"c45fe485ebb1cb2f542a12b4b8e32a376e8f3827990ea8d680480c16247c1bed"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KnQDqpcZJGNkZD7KuXW2/Jg1w2eACA9FvZ9F8UhbaRw0CHFMTvmwvlZX7dzq/tkQCCHN1kV9Mb7Jz52dkK55AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:20:56.370678Z","bundle_sha256":"ca6339369d071b7bc7d66decc1194f00409f49fbc4ccc6ca847cd624a9efbc61"}}