{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R5SI7GGLYRWVEFT7RP6WHOYD3H","short_pith_number":"pith:R5SI7GGL","canonical_record":{"source":{"id":"2603.23455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-24T17:26:55Z","cross_cats_sorted":[],"title_canon_sha256":"bee6d9e35ad049879313316f8d5643827b0d11470ea169e6a44424f77a667ef5","abstract_canon_sha256":"ca2daf55f294acbd8d65b49f2f85e8720102ac80cad26a9f06ef15be81d299bd"},"schema_version":"1.0"},"canonical_sha256":"8f648f98cbc46d52167f8bfd63bb03d9c72f550e055dc55ea6f5aac848844264","source":{"kind":"arxiv","id":"2603.23455","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.23455","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2603.23455v2","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23455","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"R5SI7GGLYRWV","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"R5SI7GGLYRWVEFT7","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"R5SI7GGL","created_at":"2026-07-01T01:17:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R5SI7GGLYRWVEFT7RP6WHOYD3H","target":"record","payload":{"canonical_record":{"source":{"id":"2603.23455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-24T17:26:55Z","cross_cats_sorted":[],"title_canon_sha256":"bee6d9e35ad049879313316f8d5643827b0d11470ea169e6a44424f77a667ef5","abstract_canon_sha256":"ca2daf55f294acbd8d65b49f2f85e8720102ac80cad26a9f06ef15be81d299bd"},"schema_version":"1.0"},"canonical_sha256":"8f648f98cbc46d52167f8bfd63bb03d9c72f550e055dc55ea6f5aac848844264","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:14.556700Z","signature_b64":"/IYrFuuzO8RMyNkKcjrb3SF6eoln4SNsfJssRynlA8c9P/DzPOmKB05lLpoMRG/91z0uzjhDtXHUuvodsLTOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f648f98cbc46d52167f8bfd63bb03d9c72f550e055dc55ea6f5aac848844264","last_reissued_at":"2026-07-01T01:17:14.556179Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:14.556179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.23455","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":"2026-07-01T01:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwOdF2A/lXogNAcMUB0OaXRCfbPJeLvnYyVxFF949tECj5d0pImlcPDKHnC4jcu9BXxf5ZpJRQ0lGPYEv8BECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T17:20:14.101687Z"},"content_sha256":"7fedab79fa43d621a7c8449cdb73df2f275fdb9c46546026bfe1d93d05013c5b","schema_version":"1.0","event_id":"sha256:7fedab79fa43d621a7c8449cdb73df2f275fdb9c46546026bfe1d93d05013c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R5SI7GGLYRWVEFT7RP6WHOYD3H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Gautam Rajendrakumar Gare, John Galeotti, Matvei Popov, Neehar Peri, Shruti Jain","submitted_at":"2026-03-24T17:26:55Z","abstract_excerpt":"Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still struggle to generalize to out-of-distribution classes, tasks and imaging modalities not typically found in their pre-training. While in-context prompting is a common strategy to improve performance across diverse tasks, we find that it often yields lower detection accuracy than prompting with class names alone. This suggests that current MLLMs cannot yet effectively leverage few-shot visual examples and rich textual d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23455","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/2603.23455/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":"2026-07-01T01:17:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YoIEL/cVdDAta4wkPumJu+PrMyHOyd5OZZp+5XjXhPUp6Tln/Wi+wNf4xKdaAfJl6qmdwTKki2H1UwMcYqTCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T17:20:14.102072Z"},"content_sha256":"bbb23c99e287005b3a55e873aa267bd27210ff10bd6962e3abf3e74e1bcb3185","schema_version":"1.0","event_id":"sha256:bbb23c99e287005b3a55e873aa267bd27210ff10bd6962e3abf3e74e1bcb3185"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H/bundle.json","state_url":"https://pith.science/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H/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":"2026-07-01T17:20:14Z","links":{"resolver":"https://pith.science/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H","bundle":"https://pith.science/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H/bundle.json","state":"https://pith.science/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R5SI7GGLYRWVEFT7RP6WHOYD3H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R5SI7GGLYRWVEFT7RP6WHOYD3H","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":"ca2daf55f294acbd8d65b49f2f85e8720102ac80cad26a9f06ef15be81d299bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-24T17:26:55Z","title_canon_sha256":"bee6d9e35ad049879313316f8d5643827b0d11470ea169e6a44424f77a667ef5"},"schema_version":"1.0","source":{"id":"2603.23455","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.23455","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"arxiv_version","alias_value":"2603.23455v2","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23455","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"pith_short_12","alias_value":"R5SI7GGLYRWV","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"pith_short_16","alias_value":"R5SI7GGLYRWVEFT7","created_at":"2026-07-01T01:17:14Z"},{"alias_kind":"pith_short_8","alias_value":"R5SI7GGL","created_at":"2026-07-01T01:17:14Z"}],"graph_snapshots":[{"event_id":"sha256:bbb23c99e287005b3a55e873aa267bd27210ff10bd6962e3abf3e74e1bcb3185","target":"graph","created_at":"2026-07-01T01:17:14Z","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/2603.23455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detection benchmarks like OdinW-13 and RefCOCO. However, state-of-the-art models still struggle to generalize to out-of-distribution classes, tasks and imaging modalities not typically found in their pre-training. While in-context prompting is a common strategy to improve performance across diverse tasks, we find that it often yields lower detection accuracy than prompting with class names alone. This suggests that current MLLMs cannot yet effectively leverage few-shot visual examples and rich textual d","authors_text":"Deva Ramanan, Gautam Rajendrakumar Gare, John Galeotti, Matvei Popov, Neehar Peri, Shruti Jain","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-24T17:26:55Z","title":"DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23455","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":"sha256:7fedab79fa43d621a7c8449cdb73df2f275fdb9c46546026bfe1d93d05013c5b","target":"record","created_at":"2026-07-01T01:17:14Z","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":"ca2daf55f294acbd8d65b49f2f85e8720102ac80cad26a9f06ef15be81d299bd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-24T17:26:55Z","title_canon_sha256":"bee6d9e35ad049879313316f8d5643827b0d11470ea169e6a44424f77a667ef5"},"schema_version":"1.0","source":{"id":"2603.23455","kind":"arxiv","version":2}},"canonical_sha256":"8f648f98cbc46d52167f8bfd63bb03d9c72f550e055dc55ea6f5aac848844264","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f648f98cbc46d52167f8bfd63bb03d9c72f550e055dc55ea6f5aac848844264","first_computed_at":"2026-07-01T01:17:14.556179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:17:14.556179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/IYrFuuzO8RMyNkKcjrb3SF6eoln4SNsfJssRynlA8c9P/DzPOmKB05lLpoMRG/91z0uzjhDtXHUuvodsLTOBA==","signature_status":"signed_v1","signed_at":"2026-07-01T01:17:14.556700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.23455","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fedab79fa43d621a7c8449cdb73df2f275fdb9c46546026bfe1d93d05013c5b","sha256:bbb23c99e287005b3a55e873aa267bd27210ff10bd6962e3abf3e74e1bcb3185"],"state_sha256":"4b11444068710b5445af1aa8592a052376addfc59cac253ee003a50d70be38c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rbnRtfM0Q9ZQmYgNC1if5hrNjvPVB6En4glEOH/u6GOs0p3otMX2bbDInwAA82sE9A+IiC5tGmzu+Q82uZjzDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T17:20:14.104131Z","bundle_sha256":"05ea035d2e91ef3397935fee9c9ed68b1b03395eac47c58d1fd18279ce3a3cc4"}}