{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VWWFOB74JWPLUX2USCYKN2CM6N","short_pith_number":"pith:VWWFOB74","canonical_record":{"source":{"id":"2605.19410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T06:04:23Z","cross_cats_sorted":[],"title_canon_sha256":"9d268afcc7592a74e07ac41151074388fac2992360cd60b5cc3a5e06706ebc49","abstract_canon_sha256":"e0ff8788ab5d7381270372873bc92b0bdf0b575d2712db9b9c2ec3e2c68f6098"},"schema_version":"1.0"},"canonical_sha256":"adac5707fc4d9eba5f5490b0a6e84cf37ba85bfa6afe079d4b5ec1d4597bbeda","source":{"kind":"arxiv","id":"2605.19410","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19410","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19410v1","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19410","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"VWWFOB74JWPL","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"VWWFOB74JWPLUX2U","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"VWWFOB74","created_at":"2026-05-20T01:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VWWFOB74JWPLUX2USCYKN2CM6N","target":"record","payload":{"canonical_record":{"source":{"id":"2605.19410","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T06:04:23Z","cross_cats_sorted":[],"title_canon_sha256":"9d268afcc7592a74e07ac41151074388fac2992360cd60b5cc3a5e06706ebc49","abstract_canon_sha256":"e0ff8788ab5d7381270372873bc92b0bdf0b575d2712db9b9c2ec3e2c68f6098"},"schema_version":"1.0"},"canonical_sha256":"adac5707fc4d9eba5f5490b0a6e84cf37ba85bfa6afe079d4b5ec1d4597bbeda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:05:44.219752Z","signature_b64":"1NEeUyYTQRmVCAzYp5ksfzxBFcwHbj8uJ9a6TJh7xdaKGx/ftX97zyN+K+8HkH26Cm1VDB1oQfUOrf3FkV36Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adac5707fc4d9eba5f5490b0a6e84cf37ba85bfa6afe079d4b5ec1d4597bbeda","last_reissued_at":"2026-05-20T01:05:44.219051Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:05:44.219051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.19410","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":"2026-05-20T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sk4TBnbOwWFMdE7zCk++fnK6zgRPAfFIwXHmqB+a6iOB3k49mvN8oq5mrlfA7d6jm6d6WZ65Q5ro84TeDskSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T21:07:45.697724Z"},"content_sha256":"58e47d66d4166a19f72393a4a59f3273f3e5a0464fb4242c44bba8a7902cd995","schema_version":"1.0","event_id":"sha256:58e47d66d4166a19f72393a4a59f3273f3e5a0464fb4242c44bba8a7902cd995"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VWWFOB74JWPLUX2USCYKN2CM6N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision Harnessing Agent for Open Ad-hoc Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Stella X. Yu, Zilin Wang","submitted_at":"2026-05-19T06:04:23Z","abstract_excerpt":"Segmentation has become easy when the concept is known, requiring retrieval of a learned visual grounding from text. It remains hard for open ad-hoc concepts, where the grounding may not exist as one learned mask and must often be constructed from image evidence through parts, relations, exclusions, and collections. We propose a Vision-guided Ad-hoc Segmentation Agent (VASA), the first vision harnessing agent for open ad-hoc segmentation. VASA is training-free and couples a VLM agent, a segmentation foundation model, and a visually grounded workflow. Rather than revising text prompts alone, VA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19410","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/2605.19410/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":"2026-05-20T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pk6XBm6dBQvNeewCGpE+6Kx2G2ubiq18Z5osYIKl4zEWEtVcBmg5oJ1gc8EWnZ696BiTtGIchwFcmSfvRakdAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T21:07:45.698291Z"},"content_sha256":"6e60d5741ce37427bfff1bf1cd50e95d531bb2d8976504c345b370675a800f96","schema_version":"1.0","event_id":"sha256:6e60d5741ce37427bfff1bf1cd50e95d531bb2d8976504c345b370675a800f96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VWWFOB74JWPLUX2USCYKN2CM6N/bundle.json","state_url":"https://pith.science/pith/VWWFOB74JWPLUX2USCYKN2CM6N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VWWFOB74JWPLUX2USCYKN2CM6N/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":"2026-05-20T21:07:45Z","links":{"resolver":"https://pith.science/pith/VWWFOB74JWPLUX2USCYKN2CM6N","bundle":"https://pith.science/pith/VWWFOB74JWPLUX2USCYKN2CM6N/bundle.json","state":"https://pith.science/pith/VWWFOB74JWPLUX2USCYKN2CM6N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VWWFOB74JWPLUX2USCYKN2CM6N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VWWFOB74JWPLUX2USCYKN2CM6N","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":"e0ff8788ab5d7381270372873bc92b0bdf0b575d2712db9b9c2ec3e2c68f6098","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T06:04:23Z","title_canon_sha256":"9d268afcc7592a74e07ac41151074388fac2992360cd60b5cc3a5e06706ebc49"},"schema_version":"1.0","source":{"id":"2605.19410","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19410","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19410v1","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19410","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"VWWFOB74JWPL","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"VWWFOB74JWPLUX2U","created_at":"2026-05-20T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"VWWFOB74","created_at":"2026-05-20T01:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:6e60d5741ce37427bfff1bf1cd50e95d531bb2d8976504c345b370675a800f96","target":"graph","created_at":"2026-05-20T01:05:44Z","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/2605.19410/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Segmentation has become easy when the concept is known, requiring retrieval of a learned visual grounding from text. It remains hard for open ad-hoc concepts, where the grounding may not exist as one learned mask and must often be constructed from image evidence through parts, relations, exclusions, and collections. We propose a Vision-guided Ad-hoc Segmentation Agent (VASA), the first vision harnessing agent for open ad-hoc segmentation. VASA is training-free and couples a VLM agent, a segmentation foundation model, and a visually grounded workflow. Rather than revising text prompts alone, VA","authors_text":"Stella X. Yu, Zilin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T06:04:23Z","title":"Vision Harnessing Agent for Open Ad-hoc Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19410","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":"sha256:58e47d66d4166a19f72393a4a59f3273f3e5a0464fb4242c44bba8a7902cd995","target":"record","created_at":"2026-05-20T01:05:44Z","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":"e0ff8788ab5d7381270372873bc92b0bdf0b575d2712db9b9c2ec3e2c68f6098","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-19T06:04:23Z","title_canon_sha256":"9d268afcc7592a74e07ac41151074388fac2992360cd60b5cc3a5e06706ebc49"},"schema_version":"1.0","source":{"id":"2605.19410","kind":"arxiv","version":1}},"canonical_sha256":"adac5707fc4d9eba5f5490b0a6e84cf37ba85bfa6afe079d4b5ec1d4597bbeda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adac5707fc4d9eba5f5490b0a6e84cf37ba85bfa6afe079d4b5ec1d4597bbeda","first_computed_at":"2026-05-20T01:05:44.219051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:44.219051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1NEeUyYTQRmVCAzYp5ksfzxBFcwHbj8uJ9a6TJh7xdaKGx/ftX97zyN+K+8HkH26Cm1VDB1oQfUOrf3FkV36Dw==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:44.219752Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19410","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58e47d66d4166a19f72393a4a59f3273f3e5a0464fb4242c44bba8a7902cd995","sha256:6e60d5741ce37427bfff1bf1cd50e95d531bb2d8976504c345b370675a800f96"],"state_sha256":"3104b46bab2ecb26a4d99f43fe9317bafc8926fd6559ee0e4672259b0727d9aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ry+SpZVntqNcMlU/ap+QBIe4OARhI8XdU30IwHJHo6ERieJVOp/iVLbryI5hIv0wJWLS6YPuGYF5gdA0o4kQBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T21:07:45.701371Z","bundle_sha256":"2af3067b833ee7f35da2b14d7d7680f52e74bbcd276834cec854c8e239bde4a4"}}