{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:M5BBPSMWXXVBKFHMP5PQ3SDYQJ","short_pith_number":"pith:M5BBPSMW","canonical_record":{"source":{"id":"1611.06641","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-21T03:43:22Z","cross_cats_sorted":[],"title_canon_sha256":"48549f04f786a3130e8dbd7962289b287f73fc0ac18403110520a816803383d2","abstract_canon_sha256":"31a05d223497f67fa00e05d531309f0f5a45d9c8e4a50ce6928652ca3bd13b46"},"schema_version":"1.0"},"canonical_sha256":"674217c996bdea1514ec7f5f0dc878824a4296fab58faf48ec43fea6f1e83129","source":{"kind":"arxiv","id":"1611.06641","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06641","created_at":"2026-05-18T00:38:21Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06641v4","created_at":"2026-05-18T00:38:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06641","created_at":"2026-05-18T00:38:21Z"},{"alias_kind":"pith_short_12","alias_value":"M5BBPSMWXXVB","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"M5BBPSMWXXVBKFHM","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"M5BBPSMW","created_at":"2026-05-18T12:30:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:M5BBPSMWXXVBKFHMP5PQ3SDYQJ","target":"record","payload":{"canonical_record":{"source":{"id":"1611.06641","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-21T03:43:22Z","cross_cats_sorted":[],"title_canon_sha256":"48549f04f786a3130e8dbd7962289b287f73fc0ac18403110520a816803383d2","abstract_canon_sha256":"31a05d223497f67fa00e05d531309f0f5a45d9c8e4a50ce6928652ca3bd13b46"},"schema_version":"1.0"},"canonical_sha256":"674217c996bdea1514ec7f5f0dc878824a4296fab58faf48ec43fea6f1e83129","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:21.100875Z","signature_b64":"aCqYVujHLZqt5LcKp+5ZXaNDCnIJmYB2RhyVWTGL0Lo8p6gpPiAiA0j0eKwUZ+nBraM6nUC1IZIHIm6Ue1fYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"674217c996bdea1514ec7f5f0dc878824a4296fab58faf48ec43fea6f1e83129","last_reissued_at":"2026-05-18T00:38:21.100288Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:21.100288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.06641","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":"2026-05-18T00:38:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6i2T8p7hqEfT7s6iG/dKwcfHUxpL05SeyJ2lvtx/jtzbTxhw3hVf08JuARyldDQEMvDtQbpIZZSVl325kEvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:26:14.756277Z"},"content_sha256":"748abb6f76a6234cd6d4bf1a2e8aac307493d09240b15b7566c28fd7a78f807f","schema_version":"1.0","event_id":"sha256:748abb6f76a6234cd6d4bf1a2e8aac307493d09240b15b7566c28fd7a78f807f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:M5BBPSMWXXVBKFHMP5PQ3SDYQJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arun Mallya, Bryan A. Plummer, Christopher M. Cervantes, Julia Hockenmaier, Svetlana Lazebnik","submitted_at":"2016-11-21T03:43:22Z","abstract_excerpt":"This paper presents a framework for localization or grounding of phrases in images using a large collection of linguistic and visual cues. We model the appearance, size, and position of entity bounding boxes, adjectives that contain attribute information, and spatial relationships between pairs of entities connected by verbs or prepositions. Special attention is given to relationships between people and clothing or body part mentions, as they are useful for distinguishing individuals. We automatically learn weights for combining these cues and at test time, perform joint inference over all phr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06641","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":""},"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":"2026-05-18T00:38:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmTyTr3zqnh5t3JI0i3WP7xS3PDz7HVRM1/2K81ScsL+2ZvCMq26USpjzZyGH5p/OvcNhV79iwQnyeQ0ixLVBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:26:14.756966Z"},"content_sha256":"9dfedeb3a6874cdb5a9797545ecdf2ff7eb6611f14368123a8dc8d44cefa9fa9","schema_version":"1.0","event_id":"sha256:9dfedeb3a6874cdb5a9797545ecdf2ff7eb6611f14368123a8dc8d44cefa9fa9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ/bundle.json","state_url":"https://pith.science/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ/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":"2026-05-25T16:26:14Z","links":{"resolver":"https://pith.science/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ","bundle":"https://pith.science/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ/bundle.json","state":"https://pith.science/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M5BBPSMWXXVBKFHMP5PQ3SDYQJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:M5BBPSMWXXVBKFHMP5PQ3SDYQJ","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":"31a05d223497f67fa00e05d531309f0f5a45d9c8e4a50ce6928652ca3bd13b46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-21T03:43:22Z","title_canon_sha256":"48549f04f786a3130e8dbd7962289b287f73fc0ac18403110520a816803383d2"},"schema_version":"1.0","source":{"id":"1611.06641","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.06641","created_at":"2026-05-18T00:38:21Z"},{"alias_kind":"arxiv_version","alias_value":"1611.06641v4","created_at":"2026-05-18T00:38:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06641","created_at":"2026-05-18T00:38:21Z"},{"alias_kind":"pith_short_12","alias_value":"M5BBPSMWXXVB","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"M5BBPSMWXXVBKFHM","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"M5BBPSMW","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:9dfedeb3a6874cdb5a9797545ecdf2ff7eb6611f14368123a8dc8d44cefa9fa9","target":"graph","created_at":"2026-05-18T00:38:21Z","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":"This paper presents a framework for localization or grounding of phrases in images using a large collection of linguistic and visual cues. We model the appearance, size, and position of entity bounding boxes, adjectives that contain attribute information, and spatial relationships between pairs of entities connected by verbs or prepositions. Special attention is given to relationships between people and clothing or body part mentions, as they are useful for distinguishing individuals. We automatically learn weights for combining these cues and at test time, perform joint inference over all phr","authors_text":"Arun Mallya, Bryan A. Plummer, Christopher M. Cervantes, Julia Hockenmaier, Svetlana Lazebnik","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-21T03:43:22Z","title":"Phrase Localization and Visual Relationship Detection with Comprehensive Image-Language Cues"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06641","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":"sha256:748abb6f76a6234cd6d4bf1a2e8aac307493d09240b15b7566c28fd7a78f807f","target":"record","created_at":"2026-05-18T00:38:21Z","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":"31a05d223497f67fa00e05d531309f0f5a45d9c8e4a50ce6928652ca3bd13b46","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-21T03:43:22Z","title_canon_sha256":"48549f04f786a3130e8dbd7962289b287f73fc0ac18403110520a816803383d2"},"schema_version":"1.0","source":{"id":"1611.06641","kind":"arxiv","version":4}},"canonical_sha256":"674217c996bdea1514ec7f5f0dc878824a4296fab58faf48ec43fea6f1e83129","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"674217c996bdea1514ec7f5f0dc878824a4296fab58faf48ec43fea6f1e83129","first_computed_at":"2026-05-18T00:38:21.100288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:21.100288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aCqYVujHLZqt5LcKp+5ZXaNDCnIJmYB2RhyVWTGL0Lo8p6gpPiAiA0j0eKwUZ+nBraM6nUC1IZIHIm6Ue1fYAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:21.100875Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.06641","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:748abb6f76a6234cd6d4bf1a2e8aac307493d09240b15b7566c28fd7a78f807f","sha256:9dfedeb3a6874cdb5a9797545ecdf2ff7eb6611f14368123a8dc8d44cefa9fa9"],"state_sha256":"5005280aead7222855a5ee5ac73f62a9bf62335c1c5e84171249acb45e64bd07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S8fGy3S9WYzKyuKVznzzdeGLaaiPlizH3lhAKRkq16H8fFTOdPl1eQGNXlBHa/CzaS31xodMQ/4Y3ik+s07mAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:26:14.759852Z","bundle_sha256":"822f73b0e03d096f35cda1e15a023aba30c0f6d57233c9a1c97a41c707f22e00"}}