{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LMQ23CD5TAX4N22YV4GDRRPA7H","short_pith_number":"pith:LMQ23CD5","canonical_record":{"source":{"id":"2608.01077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-02T08:21:48Z","cross_cats_sorted":[],"title_canon_sha256":"b2263bbb1fcd2e500a9bc03581590ac11b6292f5717c1062a4197c2348f66656","abstract_canon_sha256":"837e8095443529f3f64a6deb9709f9704ec4c059bd5c90fdbe6afd3c5dd2ba3d"},"schema_version":"1.0"},"canonical_sha256":"5b21ad887d982fc6eb58af0c38c5e0f9e0870b3ca14a504c81960c8e521057c6","source":{"kind":"arxiv","id":"2608.01077","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01077","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01077v1","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01077","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"LMQ23CD5TAX4","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"pith_short_16","alias_value":"LMQ23CD5TAX4N22Y","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"pith_short_8","alias_value":"LMQ23CD5","created_at":"2026-08-04T01:56:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LMQ23CD5TAX4N22YV4GDRRPA7H","target":"record","payload":{"canonical_record":{"source":{"id":"2608.01077","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-02T08:21:48Z","cross_cats_sorted":[],"title_canon_sha256":"b2263bbb1fcd2e500a9bc03581590ac11b6292f5717c1062a4197c2348f66656","abstract_canon_sha256":"837e8095443529f3f64a6deb9709f9704ec4c059bd5c90fdbe6afd3c5dd2ba3d"},"schema_version":"1.0"},"canonical_sha256":"5b21ad887d982fc6eb58af0c38c5e0f9e0870b3ca14a504c81960c8e521057c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:56:29.155547Z","signature_b64":"K4jfl82V40xhQxv8BDzqPoBf6PMKEM+HSzkVMMnwTVaGZYA1L9tx3zOPIzcWnl5pnDuJba9Org9aTB9Mo49EAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b21ad887d982fc6eb58af0c38c5e0f9e0870b3ca14a504c81960c8e521057c6","last_reissued_at":"2026-08-04T01:56:29.153757Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:56:29.153757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.01077","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":"2026-08-04T01:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OZKcU1L5nmhMa5hgM685+d+Iy+gPX4P1DMOjVYbs3QLKYq7mNFhF09qG0zSmvAqeBG0QrBMonheUzMpCibAJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:17:36.858642Z"},"content_sha256":"e055870eeb8ebdefa52f944a83b716719941d1e5cb9673ccb3f8ef588d4c7cad","schema_version":"1.0","event_id":"sha256:e055870eeb8ebdefa52f944a83b716719941d1e5cb9673ccb3f8ef588d4c7cad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LMQ23CD5TAX4N22YV4GDRRPA7H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VespaSeg: A Resource-Aware Ground-then-Segment Pipeline for Referring Expression Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Savindu Dilshan Wickramasinghe (University of Moratuwa)","submitted_at":"2026-08-02T08:21:48Z","abstract_excerpt":"Referring expression segmentation requires language conditioned localization and pixel-accurate masks, but monolithic models can be costly to deploy. We present VespaSeg, a modular pipeline that grounds a text query with a compact vision-language model and converts the predicted box to a mask with MobileSAM. We study Florence-2-base, Florence-2-large, and Moondream2 grounders together with targeted adaptation of the grounding and segmentation stages. Under a repository-specific RefCOCO validation protocol containing the first expression for each of 3,811 referenced-object records, the adapted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01077","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/2608.01077/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":"2026-08-04T01:56:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1sSDoxayT3XIyjs5Uf0X5hIAyJii5IPR+akiSIdKNPCDq6AAmz9yYGT6SLYZ7bo+5pSCi3d67sULBoqT8jI5CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:17:36.859256Z"},"content_sha256":"5bd46ce94f42a8d1cde705b8e8d4d7b18cbe67a104313800b62183dbf78e09a0","schema_version":"1.0","event_id":"sha256:5bd46ce94f42a8d1cde705b8e8d4d7b18cbe67a104313800b62183dbf78e09a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LMQ23CD5TAX4N22YV4GDRRPA7H/bundle.json","state_url":"https://pith.science/pith/LMQ23CD5TAX4N22YV4GDRRPA7H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LMQ23CD5TAX4N22YV4GDRRPA7H/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":"2026-08-17T20:17:36Z","links":{"resolver":"https://pith.science/pith/LMQ23CD5TAX4N22YV4GDRRPA7H","bundle":"https://pith.science/pith/LMQ23CD5TAX4N22YV4GDRRPA7H/bundle.json","state":"https://pith.science/pith/LMQ23CD5TAX4N22YV4GDRRPA7H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LMQ23CD5TAX4N22YV4GDRRPA7H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LMQ23CD5TAX4N22YV4GDRRPA7H","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":"837e8095443529f3f64a6deb9709f9704ec4c059bd5c90fdbe6afd3c5dd2ba3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-02T08:21:48Z","title_canon_sha256":"b2263bbb1fcd2e500a9bc03581590ac11b6292f5717c1062a4197c2348f66656"},"schema_version":"1.0","source":{"id":"2608.01077","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01077","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01077v1","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01077","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"pith_short_12","alias_value":"LMQ23CD5TAX4","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"pith_short_16","alias_value":"LMQ23CD5TAX4N22Y","created_at":"2026-08-04T01:56:29Z"},{"alias_kind":"pith_short_8","alias_value":"LMQ23CD5","created_at":"2026-08-04T01:56:29Z"}],"graph_snapshots":[{"event_id":"sha256:5bd46ce94f42a8d1cde705b8e8d4d7b18cbe67a104313800b62183dbf78e09a0","target":"graph","created_at":"2026-08-04T01:56:29Z","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/2608.01077/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring expression segmentation requires language conditioned localization and pixel-accurate masks, but monolithic models can be costly to deploy. We present VespaSeg, a modular pipeline that grounds a text query with a compact vision-language model and converts the predicted box to a mask with MobileSAM. We study Florence-2-base, Florence-2-large, and Moondream2 grounders together with targeted adaptation of the grounding and segmentation stages. Under a repository-specific RefCOCO validation protocol containing the first expression for each of 3,811 referenced-object records, the adapted ","authors_text":"Savindu Dilshan Wickramasinghe (University of Moratuwa)","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-02T08:21:48Z","title":"VespaSeg: A Resource-Aware Ground-then-Segment Pipeline for Referring Expression Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01077","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:e055870eeb8ebdefa52f944a83b716719941d1e5cb9673ccb3f8ef588d4c7cad","target":"record","created_at":"2026-08-04T01:56:29Z","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":"837e8095443529f3f64a6deb9709f9704ec4c059bd5c90fdbe6afd3c5dd2ba3d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-08-02T08:21:48Z","title_canon_sha256":"b2263bbb1fcd2e500a9bc03581590ac11b6292f5717c1062a4197c2348f66656"},"schema_version":"1.0","source":{"id":"2608.01077","kind":"arxiv","version":1}},"canonical_sha256":"5b21ad887d982fc6eb58af0c38c5e0f9e0870b3ca14a504c81960c8e521057c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b21ad887d982fc6eb58af0c38c5e0f9e0870b3ca14a504c81960c8e521057c6","first_computed_at":"2026-08-04T01:56:29.153757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:56:29.153757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K4jfl82V40xhQxv8BDzqPoBf6PMKEM+HSzkVMMnwTVaGZYA1L9tx3zOPIzcWnl5pnDuJba9Org9aTB9Mo49EAg==","signature_status":"signed_v1","signed_at":"2026-08-04T01:56:29.155547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01077","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e055870eeb8ebdefa52f944a83b716719941d1e5cb9673ccb3f8ef588d4c7cad","sha256:5bd46ce94f42a8d1cde705b8e8d4d7b18cbe67a104313800b62183dbf78e09a0"],"state_sha256":"1dedbf8e9c4c6799cd97d7b42bb766997a899efdb0b2fcf9e7077a3c4a2a3f5d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u5+8vmNnGA6YvWuRdUY9h+snrQ09vP+gSH0th2qgySTemZzu61aOIG2jBrbvM6NwiCT7BokorheZ2BI0wasiDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:17:36.866272Z","bundle_sha256":"980f83dd2e694ea77b6000bdb20f9a360919a49ecf37ebdc0beaa334fe1bc8aa"}}