{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MXUXGK2GIOFPSNGKXIYQK6J323","short_pith_number":"pith:MXUXGK2G","canonical_record":{"source":{"id":"2408.04961","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T09:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"f1a584e3f40cc330235c36e44ec994f37b618f912b815324fd18d294fe04958c","abstract_canon_sha256":"0bfac01af60f029bf27248cd80d7f8e21f4692f20f44391bce18fd4141239311"},"schema_version":"1.0"},"canonical_sha256":"65e9732b46438af934caba3105793bd6cd6968dcb3902333342f074526f56b5d","source":{"kind":"arxiv","id":"2408.04961","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04961","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04961v1","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04961","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"MXUXGK2GIOFP","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"pith_short_16","alias_value":"MXUXGK2GIOFPSNGK","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"pith_short_8","alias_value":"MXUXGK2G","created_at":"2026-07-05T08:53:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MXUXGK2GIOFPSNGKXIYQK6J323","target":"record","payload":{"canonical_record":{"source":{"id":"2408.04961","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T09:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"f1a584e3f40cc330235c36e44ec994f37b618f912b815324fd18d294fe04958c","abstract_canon_sha256":"0bfac01af60f029bf27248cd80d7f8e21f4692f20f44391bce18fd4141239311"},"schema_version":"1.0"},"canonical_sha256":"65e9732b46438af934caba3105793bd6cd6968dcb3902333342f074526f56b5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:46.445272Z","signature_b64":"QrYb9UpW5nKYoBoYco7Yu2JlOdXQ5TiY/mK6+JGIl4MTDgC/2jVLF1JZuZWwLOG8aTELiBSv4B6mRnfxlRUaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65e9732b46438af934caba3105793bd6cd6968dcb3902333342f074526f56b5d","last_reissued_at":"2026-07-05T08:53:46.444782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:46.444782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.04961","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:53:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Y0aKBZ49J/j8WIdBwKRBTcl4p806Jhg+zzEd6c87hZ78dFPHL3HA+dWfQo/oKHHWpOkwFPKIM0JbYm8sUcvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:28:39.932253Z"},"content_sha256":"c83f440b7df992c787b872d2527aae2e8548a869d97c3b251dcb52fc9c98ba58","schema_version":"1.0","event_id":"sha256:c83f440b7df992c787b872d2527aae2e8548a869d97c3b251dcb52fc9c98ba58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MXUXGK2GIOFPSNGKXIYQK6J323","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dahyun Kang, Minsu Cho","submitted_at":"2024-08-09T09:28:35Z","abstract_excerpt":"We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification without object-level comprehension, leveraging the image-to-text classification capability of pretrained vision-and-language models. We argue that visual objects are distinguishable without the prior text information as segmentation is essentially a vision task. Lazy visual grounding first discovers object masks covering an image with iterative Normalized c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04961","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/2408.04961/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":"2026-07-05T08:53:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6x3lEvMHLxUQvDUUI5QXlcVeTq/fv912fzLh1RJm7OXOfu3azJkgDqpuAxAsmb1azaDJW6serEGN2d17wayDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T19:28:39.932868Z"},"content_sha256":"dc5ce455a74684f5f95fe554eb5ec50d68923aba7699d2158df928c81b645d02","schema_version":"1.0","event_id":"sha256:dc5ce455a74684f5f95fe554eb5ec50d68923aba7699d2158df928c81b645d02"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXUXGK2GIOFPSNGKXIYQK6J323/bundle.json","state_url":"https://pith.science/pith/MXUXGK2GIOFPSNGKXIYQK6J323/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXUXGK2GIOFPSNGKXIYQK6J323/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":"2026-08-16T19:28:39Z","links":{"resolver":"https://pith.science/pith/MXUXGK2GIOFPSNGKXIYQK6J323","bundle":"https://pith.science/pith/MXUXGK2GIOFPSNGKXIYQK6J323/bundle.json","state":"https://pith.science/pith/MXUXGK2GIOFPSNGKXIYQK6J323/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXUXGK2GIOFPSNGKXIYQK6J323/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MXUXGK2GIOFPSNGKXIYQK6J323","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":"0bfac01af60f029bf27248cd80d7f8e21f4692f20f44391bce18fd4141239311","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T09:28:35Z","title_canon_sha256":"f1a584e3f40cc330235c36e44ec994f37b618f912b815324fd18d294fe04958c"},"schema_version":"1.0","source":{"id":"2408.04961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.04961","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"2408.04961v1","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04961","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"MXUXGK2GIOFP","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"pith_short_16","alias_value":"MXUXGK2GIOFPSNGK","created_at":"2026-07-05T08:53:46Z"},{"alias_kind":"pith_short_8","alias_value":"MXUXGK2G","created_at":"2026-07-05T08:53:46Z"}],"graph_snapshots":[{"event_id":"sha256:dc5ce455a74684f5f95fe554eb5ec50d68923aba7699d2158df928c81b645d02","target":"graph","created_at":"2026-07-05T08:53:46Z","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/2408.04961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification without object-level comprehension, leveraging the image-to-text classification capability of pretrained vision-and-language models. We argue that visual objects are distinguishable without the prior text information as segmentation is essentially a vision task. Lazy visual grounding first discovers object masks covering an image with iterative Normalized c","authors_text":"Dahyun Kang, Minsu Cho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T09:28:35Z","title":"In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04961","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:c83f440b7df992c787b872d2527aae2e8548a869d97c3b251dcb52fc9c98ba58","target":"record","created_at":"2026-07-05T08:53:46Z","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":"0bfac01af60f029bf27248cd80d7f8e21f4692f20f44391bce18fd4141239311","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-09T09:28:35Z","title_canon_sha256":"f1a584e3f40cc330235c36e44ec994f37b618f912b815324fd18d294fe04958c"},"schema_version":"1.0","source":{"id":"2408.04961","kind":"arxiv","version":1}},"canonical_sha256":"65e9732b46438af934caba3105793bd6cd6968dcb3902333342f074526f56b5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65e9732b46438af934caba3105793bd6cd6968dcb3902333342f074526f56b5d","first_computed_at":"2026-07-05T08:53:46.444782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:46.444782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QrYb9UpW5nKYoBoYco7Yu2JlOdXQ5TiY/mK6+JGIl4MTDgC/2jVLF1JZuZWwLOG8aTELiBSv4B6mRnfxlRUaBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:46.445272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.04961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c83f440b7df992c787b872d2527aae2e8548a869d97c3b251dcb52fc9c98ba58","sha256:dc5ce455a74684f5f95fe554eb5ec50d68923aba7699d2158df928c81b645d02"],"state_sha256":"7eb51ffff62fc08d0549ab8b492e35f1a78a0af070bc9fd60071b087566fd6da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QrMVedvMLpqK2wB/twDoLScwgD3aZZXC+nGRr+xxryJNwn6egoFOi4EE0Zz+oAaiZ2os3mHUZ7xU74RstcKLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T19:28:39.937745Z","bundle_sha256":"458a4f1a5ce2909c649c62ca9eaef176a1d707d13358f744c52f4269574eb7ca"}}