{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SXJB7TYXUMEYPEEKZEQI4LIES3","short_pith_number":"pith:SXJB7TYX","canonical_record":{"source":{"id":"2510.14792","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T15:27:10Z","cross_cats_sorted":[],"title_canon_sha256":"798a15fa778b44b3c19b111e67adf4cca0418ecc47823666ee34d2c0070fae1a","abstract_canon_sha256":"157e5e99c2f1c29014d305d4ef4f2f8139acdf22d6a82efc9b3ea198639064f5"},"schema_version":"1.0"},"canonical_sha256":"95d21fcf17a30987908ac9208e2d0496fa07358e2cf229c5b805fdbc3db5765f","source":{"kind":"arxiv","id":"2510.14792","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14792","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14792v4","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14792","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"SXJB7TYXUMEY","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"SXJB7TYXUMEYPEEK","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"SXJB7TYX","created_at":"2026-06-24T01:14:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SXJB7TYXUMEYPEEKZEQI4LIES3","target":"record","payload":{"canonical_record":{"source":{"id":"2510.14792","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T15:27:10Z","cross_cats_sorted":[],"title_canon_sha256":"798a15fa778b44b3c19b111e67adf4cca0418ecc47823666ee34d2c0070fae1a","abstract_canon_sha256":"157e5e99c2f1c29014d305d4ef4f2f8139acdf22d6a82efc9b3ea198639064f5"},"schema_version":"1.0"},"canonical_sha256":"95d21fcf17a30987908ac9208e2d0496fa07358e2cf229c5b805fdbc3db5765f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:22.896655Z","signature_b64":"LnUevvlLlNH0Ib5/rS2MjnbXdMOk8sdRheJl4f+S5DLnAsd/ff6mg3kfrZTzKPlJWyy4hICcE4Beg6oWcEj8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95d21fcf17a30987908ac9208e2d0496fa07358e2cf229c5b805fdbc3db5765f","last_reissued_at":"2026-06-24T01:14:22.896138Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:22.896138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.14792","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I+t77lDXSoVq+LigjnZ7y5Kap6KH+QlgMExaNvlu3THdJyRwspj2yAPbo0DZ+B35Nl1i8NyRx9S0s7a8kUa5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T00:24:18.738306Z"},"content_sha256":"61d198ef8fbb41c79c43e0217beae17cc4eecd9f7d966edeb26266b54f4b96a7","schema_version":"1.0","event_id":"sha256:61d198ef8fbb41c79c43e0217beae17cc4eecd9f7d966edeb26266b54f4b96a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SXJB7TYXUMEYPEEKZEQI4LIES3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hojun Choi, Hyunjung Shim, Jaeyo Shin, Youngsun Lim","submitted_at":"2025-10-16T15:27:10Z","abstract_excerpt":"Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to generalize to unseen classes without explicit supervision. However, these methods depend heavily on single-step image-text matching, neglecting the intermediate reasoning steps crucial for interpreting semantically complex visual contexts, such as crowding or occlusion. In this paper, we introduce MSPL, a framework that incorporates multi-step visual reasonin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14792","kind":"arxiv","version":4},"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/2510.14792/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":"2026-06-24T01:14:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x6LA7Fb7qmn3Q9nsKV3r3/p5m3u6OFdGQthCg6rSMVzgk6Go+25OvhikXcWO5OWy27HKP1z+jzAmydJxghk0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T00:24:18.738696Z"},"content_sha256":"d5ac5c592aaaf2c9d2831c7d99e09a7bacf5ca6178313564815cebcc61de9f0f","schema_version":"1.0","event_id":"sha256:d5ac5c592aaaf2c9d2831c7d99e09a7bacf5ca6178313564815cebcc61de9f0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXJB7TYXUMEYPEEKZEQI4LIES3/bundle.json","state_url":"https://pith.science/pith/SXJB7TYXUMEYPEEKZEQI4LIES3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXJB7TYXUMEYPEEKZEQI4LIES3/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":"2026-07-05T00:24:18Z","links":{"resolver":"https://pith.science/pith/SXJB7TYXUMEYPEEKZEQI4LIES3","bundle":"https://pith.science/pith/SXJB7TYXUMEYPEEKZEQI4LIES3/bundle.json","state":"https://pith.science/pith/SXJB7TYXUMEYPEEKZEQI4LIES3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXJB7TYXUMEYPEEKZEQI4LIES3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SXJB7TYXUMEYPEEKZEQI4LIES3","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":"157e5e99c2f1c29014d305d4ef4f2f8139acdf22d6a82efc9b3ea198639064f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T15:27:10Z","title_canon_sha256":"798a15fa778b44b3c19b111e67adf4cca0418ecc47823666ee34d2c0070fae1a"},"schema_version":"1.0","source":{"id":"2510.14792","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.14792","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"arxiv_version","alias_value":"2510.14792v4","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.14792","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"pith_short_12","alias_value":"SXJB7TYXUMEY","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"pith_short_16","alias_value":"SXJB7TYXUMEYPEEK","created_at":"2026-06-24T01:14:22Z"},{"alias_kind":"pith_short_8","alias_value":"SXJB7TYX","created_at":"2026-06-24T01:14:22Z"}],"graph_snapshots":[{"event_id":"sha256:d5ac5c592aaaf2c9d2831c7d99e09a7bacf5ca6178313564815cebcc61de9f0f","target":"graph","created_at":"2026-06-24T01:14:22Z","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/2510.14792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to generalize to unseen classes without explicit supervision. However, these methods depend heavily on single-step image-text matching, neglecting the intermediate reasoning steps crucial for interpreting semantically complex visual contexts, such as crowding or occlusion. In this paper, we introduce MSPL, a framework that incorporates multi-step visual reasonin","authors_text":"Hojun Choi, Hyunjung Shim, Jaeyo Shin, Youngsun Lim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T15:27:10Z","title":"MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.14792","kind":"arxiv","version":4},"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":"sha256:61d198ef8fbb41c79c43e0217beae17cc4eecd9f7d966edeb26266b54f4b96a7","target":"record","created_at":"2026-06-24T01:14:22Z","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":"157e5e99c2f1c29014d305d4ef4f2f8139acdf22d6a82efc9b3ea198639064f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-16T15:27:10Z","title_canon_sha256":"798a15fa778b44b3c19b111e67adf4cca0418ecc47823666ee34d2c0070fae1a"},"schema_version":"1.0","source":{"id":"2510.14792","kind":"arxiv","version":4}},"canonical_sha256":"95d21fcf17a30987908ac9208e2d0496fa07358e2cf229c5b805fdbc3db5765f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95d21fcf17a30987908ac9208e2d0496fa07358e2cf229c5b805fdbc3db5765f","first_computed_at":"2026-06-24T01:14:22.896138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:22.896138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LnUevvlLlNH0Ib5/rS2MjnbXdMOk8sdRheJl4f+S5DLnAsd/ff6mg3kfrZTzKPlJWyy4hICcE4Beg6oWcEj8AQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:22.896655Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.14792","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61d198ef8fbb41c79c43e0217beae17cc4eecd9f7d966edeb26266b54f4b96a7","sha256:d5ac5c592aaaf2c9d2831c7d99e09a7bacf5ca6178313564815cebcc61de9f0f"],"state_sha256":"796defb465447c80b638c8b2cdc809644aee69fd3a6baba15a333723ba49f909"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"trB3MfvqkvCC75FH9etOl26aXaGDo5XykuscclY3epT9S0w7KjQZd4xRTPQAUWvzMBlIauSPrRjyHxUzvOFACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T00:24:18.740815Z","bundle_sha256":"6829c1dc8babcb7a6c05ab26c34e3bbe0be4ec457e85b7347a4deb737b36fc5d"}}