{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:LA7DXHTLFMQLWMAVHEORKHVI4S","short_pith_number":"pith:LA7DXHTL","canonical_record":{"source":{"id":"1511.03745","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-12T01:13:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"89d608b310badc8459e2f8354da4992566eeb9efc3f3ff257ba3e818066a852c","abstract_canon_sha256":"b15ee3273f439d46316bea97a25bc04176eea46d545d63f74a4296c851efba83"},"schema_version":"1.0"},"canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","source":{"kind":"arxiv","id":"1511.03745","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.03745","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"1511.03745v4","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03745","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"LA7DXHTLFMQL","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LA7DXHTLFMQLWMAV","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LA7DXHTL","created_at":"2026-05-18T12:29:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:LA7DXHTLFMQLWMAVHEORKHVI4S","target":"record","payload":{"canonical_record":{"source":{"id":"1511.03745","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-12T01:13:47Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"89d608b310badc8459e2f8354da4992566eeb9efc3f3ff257ba3e818066a852c","abstract_canon_sha256":"b15ee3273f439d46316bea97a25bc04176eea46d545d63f74a4296c851efba83"},"schema_version":"1.0"},"canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:31.213656Z","signature_b64":"i/vAnSiceDv8VwpDNvMW3Me91us04rQrduKLl9aWLVO5ItJhn0fX3lH/lSbkV0s82i1BKeZFNfvYqb2eErw8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","last_reissued_at":"2026-05-18T00:50:31.212976Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:31.212976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.03745","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":"2026-05-18T00:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYPvRu2xl8IdMLhUdNkgp3V0EfImJ8esTUYGdKz+8Qgwk+Jkydag9I4gt2avI5WLimd8SpLmSGxY5U90KGOCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:12:40.079429Z"},"content_sha256":"0e757b4096a7bda4ac2c54c7ce4983e3a87ee8ada5f941f689fcc8d7da7fa191","schema_version":"1.0","event_id":"sha256:0e757b4096a7bda4ac2c54c7ce4983e3a87ee8ada5f941f689fcc8d7da7fa191"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:LA7DXHTLFMQLWMAVHEORKHVI4S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounding of Textual Phrases in Images by Reconstruction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Bernt Schiele, Marcus Rohrbach, Ronghang Hu, Trevor Darrell","submitted_at":"2015-11-12T01:13:47Z","abstract_excerpt":"Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth spatial localization of phrases, thus it is desirable to learn from data with no or little grounding supervision. We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly. During training our approach encodes the phrase using a recurrent network language mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03745","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":"2026-05-18T00:50:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIX3Tf0Z9Z1OLzxkUqu9vdlxY4m8+1QRn9lP6LIiCm3324SbcB8qw+9KyXReScwk6lRPrjvSL94B9ROiPi6zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T10:12:40.079780Z"},"content_sha256":"43a5dbdce372236bd26e75a569307d61ad5f20203ab07ffff96fe3b740a9f4d4","schema_version":"1.0","event_id":"sha256:43a5dbdce372236bd26e75a569307d61ad5f20203ab07ffff96fe3b740a9f4d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/bundle.json","state_url":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/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":"2026-05-19T10:12:40Z","links":{"resolver":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S","bundle":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/bundle.json","state":"https://pith.science/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LA7DXHTLFMQLWMAVHEORKHVI4S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:LA7DXHTLFMQLWMAVHEORKHVI4S","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":"b15ee3273f439d46316bea97a25bc04176eea46d545d63f74a4296c851efba83","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-12T01:13:47Z","title_canon_sha256":"89d608b310badc8459e2f8354da4992566eeb9efc3f3ff257ba3e818066a852c"},"schema_version":"1.0","source":{"id":"1511.03745","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.03745","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"arxiv_version","alias_value":"1511.03745v4","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03745","created_at":"2026-05-18T00:50:31Z"},{"alias_kind":"pith_short_12","alias_value":"LA7DXHTLFMQL","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"LA7DXHTLFMQLWMAV","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"LA7DXHTL","created_at":"2026-05-18T12:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:43a5dbdce372236bd26e75a569307d61ad5f20203ab07ffff96fe3b740a9f4d4","target":"graph","created_at":"2026-05-18T00:50:31Z","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":"Grounding (i.e. localizing) arbitrary, free-form textual phrases in visual content is a challenging problem with many applications for human-computer interaction and image-text reference resolution. Few datasets provide the ground truth spatial localization of phrases, thus it is desirable to learn from data with no or little grounding supervision. We propose a novel approach which learns grounding by reconstructing a given phrase using an attention mechanism, which can be either latent or optimized directly. During training our approach encodes the phrase using a recurrent network language mo","authors_text":"Anna Rohrbach, Bernt Schiele, Marcus Rohrbach, Ronghang Hu, Trevor Darrell","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-12T01:13:47Z","title":"Grounding of Textual Phrases in Images by Reconstruction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03745","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":"sha256:0e757b4096a7bda4ac2c54c7ce4983e3a87ee8ada5f941f689fcc8d7da7fa191","target":"record","created_at":"2026-05-18T00:50:31Z","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":"b15ee3273f439d46316bea97a25bc04176eea46d545d63f74a4296c851efba83","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-11-12T01:13:47Z","title_canon_sha256":"89d608b310badc8459e2f8354da4992566eeb9efc3f3ff257ba3e818066a852c"},"schema_version":"1.0","source":{"id":"1511.03745","kind":"arxiv","version":4}},"canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"583e3b9e6b2b20bb3015391d151ea8e490580eb0902946565465f56bafa99505","first_computed_at":"2026-05-18T00:50:31.212976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:31.212976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i/vAnSiceDv8VwpDNvMW3Me91us04rQrduKLl9aWLVO5ItJhn0fX3lH/lSbkV0s82i1BKeZFNfvYqb2eErw8AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:31.213656Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.03745","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e757b4096a7bda4ac2c54c7ce4983e3a87ee8ada5f941f689fcc8d7da7fa191","sha256:43a5dbdce372236bd26e75a569307d61ad5f20203ab07ffff96fe3b740a9f4d4"],"state_sha256":"3be4177f419850ba108eddbed636a483ee59bd80ee5a2dd921305a5713bcd1ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSeJu++HxEfLwMHHv2teOXw3n9TTusSexAFRCOZJzP7eGHuxiPQjiCQTAiWEaqDAWwUz1z3m5oFEchJQjZ6yDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T10:12:40.081782Z","bundle_sha256":"081c9fb8d4b75a507567bca78f94281c5c37817a05d48692c6ae0ec3d27c4145"}}