{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SV7CVJT4KTTWCNXK6O7R5N26LG","short_pith_number":"pith:SV7CVJT4","canonical_record":{"source":{"id":"1803.06506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-17T13:46:59Z","cross_cats_sorted":[],"title_canon_sha256":"da2494c66687b1dfeca739a8152fc2694cc90dd4acb92a5a3d707c32b569293a","abstract_canon_sha256":"a9b44d7f32a89da38b92d0b9bdab52b16225700739d7313cd9e9602c0741cbb3"},"schema_version":"1.0"},"canonical_sha256":"957e2aa67c54e76136eaf3bf1eb75e59b0a5598bfe9a7d19707592b319983bb6","source":{"kind":"arxiv","id":"1803.06506","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06506","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06506v3","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06506","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"SV7CVJT4KTTW","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SV7CVJT4KTTWCNXK","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SV7CVJT4","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SV7CVJT4KTTWCNXK6O7R5N26LG","target":"record","payload":{"canonical_record":{"source":{"id":"1803.06506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-17T13:46:59Z","cross_cats_sorted":[],"title_canon_sha256":"da2494c66687b1dfeca739a8152fc2694cc90dd4acb92a5a3d707c32b569293a","abstract_canon_sha256":"a9b44d7f32a89da38b92d0b9bdab52b16225700739d7313cd9e9602c0741cbb3"},"schema_version":"1.0"},"canonical_sha256":"957e2aa67c54e76136eaf3bf1eb75e59b0a5598bfe9a7d19707592b319983bb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:30.536539Z","signature_b64":"Fpp/HkxqYr7iniTiF/2o2YunfQeQ+zOFBtvvtDt1d9cWPBd+klN5bU5DymglrnoP4DvVinSbjnhHYcbPZYH7Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"957e2aa67c54e76136eaf3bf1eb75e59b0a5598bfe9a7d19707592b319983bb6","last_reissued_at":"2026-05-18T00:00:30.535871Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:30.535871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.06506","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUGt8QecExbBX7tO/OHqVlTQKwdZ3V21udxt7D+Uo55dG9yppqNCRdyA0jnD7YoSkH3bUZqOVhKXUbFYScfrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T12:47:34.305566Z"},"content_sha256":"4cebb93cd6a9c6c51c3bc8d00f87a4cbc44ece152f109e65bfa2018b2aa8c780","schema_version":"1.0","event_id":"sha256:4cebb93cd6a9c6c51c3bc8d00f87a4cbc44ece152f109e65bfa2018b2aa8c780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SV7CVJT4KTTWCNXK6O7R5N26LG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Unsupervised Visual Grounding Through Semantic Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shreyas Saxena, Syed Ashar Javed, Vineet Gandhi","submitted_at":"2018-03-17T13:46:59Z","abstract_excerpt":"Localizing natural language phrases in images is a challenging problem that requires joint understanding of both the textual and visual modalities. In the unsupervised setting, lack of supervisory signals exacerbate this difficulty. In this paper, we propose a novel framework for unsupervised visual grounding which uses concept learning as a proxy task to obtain self-supervision. The simple intuition behind this idea is to encourage the model to localize to regions which can explain some semantic property in the data, in our case, the property being the presence of a concept in a set of images"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06506","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:00:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tQWw+s8s/XfU2+7vIDNAq6a3g33pLfA9D1NWEWbI2e8NHaTWJwDYJJ0L3byaRVxPDqLk82OmNcmilm/OnGehBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T12:47:34.305933Z"},"content_sha256":"ac85722809ed002e0fe0a1c5ffdb6c9648d8f06ba131728faf54edb4486c8381","schema_version":"1.0","event_id":"sha256:ac85722809ed002e0fe0a1c5ffdb6c9648d8f06ba131728faf54edb4486c8381"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SV7CVJT4KTTWCNXK6O7R5N26LG/bundle.json","state_url":"https://pith.science/pith/SV7CVJT4KTTWCNXK6O7R5N26LG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SV7CVJT4KTTWCNXK6O7R5N26LG/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":"2026-06-26T12:47:34Z","links":{"resolver":"https://pith.science/pith/SV7CVJT4KTTWCNXK6O7R5N26LG","bundle":"https://pith.science/pith/SV7CVJT4KTTWCNXK6O7R5N26LG/bundle.json","state":"https://pith.science/pith/SV7CVJT4KTTWCNXK6O7R5N26LG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SV7CVJT4KTTWCNXK6O7R5N26LG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SV7CVJT4KTTWCNXK6O7R5N26LG","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":"a9b44d7f32a89da38b92d0b9bdab52b16225700739d7313cd9e9602c0741cbb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-17T13:46:59Z","title_canon_sha256":"da2494c66687b1dfeca739a8152fc2694cc90dd4acb92a5a3d707c32b569293a"},"schema_version":"1.0","source":{"id":"1803.06506","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.06506","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"arxiv_version","alias_value":"1803.06506v3","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.06506","created_at":"2026-05-18T00:00:30Z"},{"alias_kind":"pith_short_12","alias_value":"SV7CVJT4KTTW","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SV7CVJT4KTTWCNXK","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SV7CVJT4","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:ac85722809ed002e0fe0a1c5ffdb6c9648d8f06ba131728faf54edb4486c8381","target":"graph","created_at":"2026-05-18T00:00:30Z","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"},"paper":{"abstract_excerpt":"Localizing natural language phrases in images is a challenging problem that requires joint understanding of both the textual and visual modalities. In the unsupervised setting, lack of supervisory signals exacerbate this difficulty. In this paper, we propose a novel framework for unsupervised visual grounding which uses concept learning as a proxy task to obtain self-supervision. The simple intuition behind this idea is to encourage the model to localize to regions which can explain some semantic property in the data, in our case, the property being the presence of a concept in a set of images","authors_text":"Shreyas Saxena, Syed Ashar Javed, Vineet Gandhi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-17T13:46:59Z","title":"Learning Unsupervised Visual Grounding Through Semantic Self-Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.06506","kind":"arxiv","version":3},"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":"sha256:4cebb93cd6a9c6c51c3bc8d00f87a4cbc44ece152f109e65bfa2018b2aa8c780","target":"record","created_at":"2026-05-18T00:00:30Z","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":"a9b44d7f32a89da38b92d0b9bdab52b16225700739d7313cd9e9602c0741cbb3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-03-17T13:46:59Z","title_canon_sha256":"da2494c66687b1dfeca739a8152fc2694cc90dd4acb92a5a3d707c32b569293a"},"schema_version":"1.0","source":{"id":"1803.06506","kind":"arxiv","version":3}},"canonical_sha256":"957e2aa67c54e76136eaf3bf1eb75e59b0a5598bfe9a7d19707592b319983bb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"957e2aa67c54e76136eaf3bf1eb75e59b0a5598bfe9a7d19707592b319983bb6","first_computed_at":"2026-05-18T00:00:30.535871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:30.535871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fpp/HkxqYr7iniTiF/2o2YunfQeQ+zOFBtvvtDt1d9cWPBd+klN5bU5DymglrnoP4DvVinSbjnhHYcbPZYH7Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:30.536539Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.06506","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cebb93cd6a9c6c51c3bc8d00f87a4cbc44ece152f109e65bfa2018b2aa8c780","sha256:ac85722809ed002e0fe0a1c5ffdb6c9648d8f06ba131728faf54edb4486c8381"],"state_sha256":"ac2326a22d5bc4ca784d5bf02e48d01d58fb1f38b02c401b8d5500e3c5163f49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZynf/fbXQYMJgKfWVxEemSZRYWWIO9Fe7qzoJXwLtc4HActwzBrXstYZMqjUBuIksG+2jRKz1WWaM2V4231Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T12:47:34.307814Z","bundle_sha256":"d2c75e9acf9062165caeb92caad544e9345322aac94e592df598ecc65b3583b4"}}