{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SXWHHWAQ2HKOLX7NIQ6TJ2INRP","short_pith_number":"pith:SXWHHWAQ","canonical_record":{"source":{"id":"2009.14558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T10:59:20Z","cross_cats_sorted":[],"title_canon_sha256":"0833e8352775e14daf1344436e1b035c8df4be113594d934d56d546857819cd1","abstract_canon_sha256":"e40e0a7035282537207d1b50f7a735c53d676155eceb592c3cdcd338159945b3"},"schema_version":"1.0"},"canonical_sha256":"95ec73d810d1d4e5dfed443d34e90d8bfcae20259ee60037bac27f79fd4ab69a","source":{"kind":"arxiv","id":"2009.14558","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14558","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14558v1","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14558","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"pith_short_12","alias_value":"SXWHHWAQ2HKO","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"pith_short_16","alias_value":"SXWHHWAQ2HKOLX7N","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"pith_short_8","alias_value":"SXWHHWAQ","created_at":"2026-07-05T01:39:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SXWHHWAQ2HKOLX7NIQ6TJ2INRP","target":"record","payload":{"canonical_record":{"source":{"id":"2009.14558","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T10:59:20Z","cross_cats_sorted":[],"title_canon_sha256":"0833e8352775e14daf1344436e1b035c8df4be113594d934d56d546857819cd1","abstract_canon_sha256":"e40e0a7035282537207d1b50f7a735c53d676155eceb592c3cdcd338159945b3"},"schema_version":"1.0"},"canonical_sha256":"95ec73d810d1d4e5dfed443d34e90d8bfcae20259ee60037bac27f79fd4ab69a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:20.857581Z","signature_b64":"qNZrp0Zd4REiSBjv1lUFecLDke/YhpMblY7N/oEw5Ma6pH5vacHtAmRwnONHzYSLOTVITSqE5hooi+BoTi1oCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95ec73d810d1d4e5dfed443d34e90d8bfcae20259ee60037bac27f79fd4ab69a","last_reissued_at":"2026-07-05T01:39:20.857194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:20.857194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.14558","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":"2026-07-05T01:39:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"htPRjCnaEa3lMmmC41b3FTJ9tCIBJvZMU3F6J7jYC8n48c26spVbb0VyVWhvgHUmfBICrdfpmPsKg/1/bQotBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:47:59.586273Z"},"content_sha256":"927f3ffcf926bf1b0ca98eb3bed9c8c390167db672edbc1f81a6f27db56b85ab","schema_version":"1.0","event_id":"sha256:927f3ffcf926bf1b0ca98eb3bed9c8c390167db672edbc1f81a6f27db56b85ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SXWHHWAQ2HKOLX7NIQ6TJ2INRP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Object Detection from Captions via Textual Scene Attributes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achiya Jerbi, Amir Globerson, Gal Chechik, Jonathan Berant, Roei Herzig","submitted_at":"2020-09-30T10:59:20Z","abstract_excerpt":"Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding boxes. Thus, it is a significant challenge to use cheaper forms of supervision effectively. Recent work has begun to explore image captions as a source for weak supervision, but to date, in the context of object detection, captions have only been used to infer the categories of the objects in the image. In this work, we argue that captions contain much richer information about the image, including attributes of objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14558","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/2009.14558/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":"2026-07-05T01:39:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZX0HzSmhFp0VStFD9nNeaiznQ1ynd/aWsqEMn/y/rN2RiKnnKsTAKgMmN1vMYACDLi8xvlbOAf8dgGP4DUfECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T22:47:59.586804Z"},"content_sha256":"f1f1d6b62a1c65656743dcad0474caa997792468d299337634b59ce83c25f51c","schema_version":"1.0","event_id":"sha256:f1f1d6b62a1c65656743dcad0474caa997792468d299337634b59ce83c25f51c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP/bundle.json","state_url":"https://pith.science/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP/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":"2026-08-19T22:47:59Z","links":{"resolver":"https://pith.science/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP","bundle":"https://pith.science/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP/bundle.json","state":"https://pith.science/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SXWHHWAQ2HKOLX7NIQ6TJ2INRP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SXWHHWAQ2HKOLX7NIQ6TJ2INRP","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":"e40e0a7035282537207d1b50f7a735c53d676155eceb592c3cdcd338159945b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T10:59:20Z","title_canon_sha256":"0833e8352775e14daf1344436e1b035c8df4be113594d934d56d546857819cd1"},"schema_version":"1.0","source":{"id":"2009.14558","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14558","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14558v1","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14558","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"pith_short_12","alias_value":"SXWHHWAQ2HKO","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"pith_short_16","alias_value":"SXWHHWAQ2HKOLX7N","created_at":"2026-07-05T01:39:20Z"},{"alias_kind":"pith_short_8","alias_value":"SXWHHWAQ","created_at":"2026-07-05T01:39:20Z"}],"graph_snapshots":[{"event_id":"sha256:f1f1d6b62a1c65656743dcad0474caa997792468d299337634b59ce83c25f51c","target":"graph","created_at":"2026-07-05T01:39:20Z","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/2009.14558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Object detection is a fundamental task in computer vision, requiring large annotated datasets that are difficult to collect, as annotators need to label objects and their bounding boxes. Thus, it is a significant challenge to use cheaper forms of supervision effectively. Recent work has begun to explore image captions as a source for weak supervision, but to date, in the context of object detection, captions have only been used to infer the categories of the objects in the image. In this work, we argue that captions contain much richer information about the image, including attributes of objec","authors_text":"Achiya Jerbi, Amir Globerson, Gal Chechik, Jonathan Berant, Roei Herzig","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T10:59:20Z","title":"Learning Object Detection from Captions via Textual Scene Attributes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14558","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":"sha256:927f3ffcf926bf1b0ca98eb3bed9c8c390167db672edbc1f81a6f27db56b85ab","target":"record","created_at":"2026-07-05T01:39:20Z","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":"e40e0a7035282537207d1b50f7a735c53d676155eceb592c3cdcd338159945b3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-09-30T10:59:20Z","title_canon_sha256":"0833e8352775e14daf1344436e1b035c8df4be113594d934d56d546857819cd1"},"schema_version":"1.0","source":{"id":"2009.14558","kind":"arxiv","version":1}},"canonical_sha256":"95ec73d810d1d4e5dfed443d34e90d8bfcae20259ee60037bac27f79fd4ab69a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95ec73d810d1d4e5dfed443d34e90d8bfcae20259ee60037bac27f79fd4ab69a","first_computed_at":"2026-07-05T01:39:20.857194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:20.857194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNZrp0Zd4REiSBjv1lUFecLDke/YhpMblY7N/oEw5Ma6pH5vacHtAmRwnONHzYSLOTVITSqE5hooi+BoTi1oCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:20.857581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.14558","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:927f3ffcf926bf1b0ca98eb3bed9c8c390167db672edbc1f81a6f27db56b85ab","sha256:f1f1d6b62a1c65656743dcad0474caa997792468d299337634b59ce83c25f51c"],"state_sha256":"350c91db8581fd080515d6a028c621258cff472b069eb389edd2181a50f94d7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pb4BnNZRehq83mvCO7Mz2qQhDG7CXma9Q4jUJTjK+STCmXNAw9rGAE9o03oK5RNZ5+/XBu9cK5XDpnGcMRDNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T22:47:59.591336Z","bundle_sha256":"ade3f882c9a97440c75e3d8cda89dee8e652ac56cf09b92baed7a92a991c5f8a"}}