{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3S7Q6HRD23J57EHA7SQBKIT54L","short_pith_number":"pith:3S7Q6HRD","canonical_record":{"source":{"id":"2112.08879","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T13:50:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6355f7a505bff5e994562c8183d0886a2a7010c4e4f5b946339267f6ae595f0f","abstract_canon_sha256":"631d446ff4781c33fe411a5f37e5599b0423e9082c94c38a9b1ced28647be2d7"},"schema_version":"1.0"},"canonical_sha256":"dcbf0f1e23d6d3df90e0fca015227de2d3a83b4ca66d1a038b7f3bcece7f4435","source":{"kind":"arxiv","id":"2112.08879","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08879","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08879v5","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08879","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"3S7Q6HRD23J5","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_16","alias_value":"3S7Q6HRD23J57EHA","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_8","alias_value":"3S7Q6HRD","created_at":"2026-07-05T04:42:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3S7Q6HRD23J57EHA7SQBKIT54L","target":"record","payload":{"canonical_record":{"source":{"id":"2112.08879","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T13:50:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6355f7a505bff5e994562c8183d0886a2a7010c4e4f5b946339267f6ae595f0f","abstract_canon_sha256":"631d446ff4781c33fe411a5f37e5599b0423e9082c94c38a9b1ced28647be2d7"},"schema_version":"1.0"},"canonical_sha256":"dcbf0f1e23d6d3df90e0fca015227de2d3a83b4ca66d1a038b7f3bcece7f4435","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:15.819412Z","signature_b64":"cBRbJ3AlNw5ENZwmPnNASCz1+yDMs4zx7HOmUooUKMt8lwR0obGwtftwKBBALvrKx5wh73DlxpqJZTTh2277Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcbf0f1e23d6d3df90e0fca015227de2d3a83b4ca66d1a038b7f3bcece7f4435","last_reissued_at":"2026-07-05T04:42:15.818941Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:15.818941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.08879","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:42:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJ5x0GT0Eqo8iq99uvEQtwG0AAC6n4VhNRdaxmGPhu1qVvCz4+7xUkY2KLlXczQebck1RU0CHBhGmI7/trAgBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:25:45.113737Z"},"content_sha256":"6019774407ff15ea7fc50e9fa6c65ba17e7d03466e005046ae17d61b6a20c2cc","schema_version":"1.0","event_id":"sha256:6019774407ff15ea7fc50e9fa6c65ba17e7d03466e005046ae17d61b6a20c2cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3S7Q6HRD23J57EHA7SQBKIT54L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ayush Jain, Ishita Mediratta, Katerina Fragkiadaki, Nikolaos Gkanatsios","submitted_at":"2021-12-16T13:50:23Z","abstract_excerpt":"Most models tasked to ground referential utterances in 2D and 3D scenes learn to select the referred object from a pool of object proposals provided by a pre-trained detector. This is limiting because an utterance may refer to visual entities at various levels of granularity, such as the chair, the leg of the chair, or the tip of the front leg of the chair, which may be missed by the detector. We propose a language grounding model that attends on the referential utterance and on the object proposal pool computed from a pre-trained detector to decode referenced objects with a detection head, wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08879","kind":"arxiv","version":5},"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/2112.08879/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":"2026-07-05T04:42:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5krS3z3yLdSAEVB9YKQ7VcxlOmm1c1UJm5X2P7/52dPHQIVK0kiiIofDA0ldZSC4pKVr+xCSZhVcqSRR0RdDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:25:45.114554Z"},"content_sha256":"2a1c858e43b9aae8902a86b537b16935b48abfe9ec5d66f5c727ebeb070470fb","schema_version":"1.0","event_id":"sha256:2a1c858e43b9aae8902a86b537b16935b48abfe9ec5d66f5c727ebeb070470fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3S7Q6HRD23J57EHA7SQBKIT54L/bundle.json","state_url":"https://pith.science/pith/3S7Q6HRD23J57EHA7SQBKIT54L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3S7Q6HRD23J57EHA7SQBKIT54L/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":"2026-08-10T06:25:45Z","links":{"resolver":"https://pith.science/pith/3S7Q6HRD23J57EHA7SQBKIT54L","bundle":"https://pith.science/pith/3S7Q6HRD23J57EHA7SQBKIT54L/bundle.json","state":"https://pith.science/pith/3S7Q6HRD23J57EHA7SQBKIT54L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3S7Q6HRD23J57EHA7SQBKIT54L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3S7Q6HRD23J57EHA7SQBKIT54L","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":"631d446ff4781c33fe411a5f37e5599b0423e9082c94c38a9b1ced28647be2d7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T13:50:23Z","title_canon_sha256":"6355f7a505bff5e994562c8183d0886a2a7010c4e4f5b946339267f6ae595f0f"},"schema_version":"1.0","source":{"id":"2112.08879","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08879","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08879v5","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08879","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"3S7Q6HRD23J5","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_16","alias_value":"3S7Q6HRD23J57EHA","created_at":"2026-07-05T04:42:15Z"},{"alias_kind":"pith_short_8","alias_value":"3S7Q6HRD","created_at":"2026-07-05T04:42:15Z"}],"graph_snapshots":[{"event_id":"sha256:2a1c858e43b9aae8902a86b537b16935b48abfe9ec5d66f5c727ebeb070470fb","target":"graph","created_at":"2026-07-05T04:42:15Z","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/2112.08879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most models tasked to ground referential utterances in 2D and 3D scenes learn to select the referred object from a pool of object proposals provided by a pre-trained detector. This is limiting because an utterance may refer to visual entities at various levels of granularity, such as the chair, the leg of the chair, or the tip of the front leg of the chair, which may be missed by the detector. We propose a language grounding model that attends on the referential utterance and on the object proposal pool computed from a pre-trained detector to decode referenced objects with a detection head, wi","authors_text":"Ayush Jain, Ishita Mediratta, Katerina Fragkiadaki, Nikolaos Gkanatsios","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T13:50:23Z","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08879","kind":"arxiv","version":5},"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":"sha256:6019774407ff15ea7fc50e9fa6c65ba17e7d03466e005046ae17d61b6a20c2cc","target":"record","created_at":"2026-07-05T04:42:15Z","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":"631d446ff4781c33fe411a5f37e5599b0423e9082c94c38a9b1ced28647be2d7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-16T13:50:23Z","title_canon_sha256":"6355f7a505bff5e994562c8183d0886a2a7010c4e4f5b946339267f6ae595f0f"},"schema_version":"1.0","source":{"id":"2112.08879","kind":"arxiv","version":5}},"canonical_sha256":"dcbf0f1e23d6d3df90e0fca015227de2d3a83b4ca66d1a038b7f3bcece7f4435","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcbf0f1e23d6d3df90e0fca015227de2d3a83b4ca66d1a038b7f3bcece7f4435","first_computed_at":"2026-07-05T04:42:15.818941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:15.818941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cBRbJ3AlNw5ENZwmPnNASCz1+yDMs4zx7HOmUooUKMt8lwR0obGwtftwKBBALvrKx5wh73DlxpqJZTTh2277Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:15.819412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08879","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6019774407ff15ea7fc50e9fa6c65ba17e7d03466e005046ae17d61b6a20c2cc","sha256:2a1c858e43b9aae8902a86b537b16935b48abfe9ec5d66f5c727ebeb070470fb"],"state_sha256":"2d8e7a643786e7a186488e6eeed52fd65f343478310159b0726334791384085b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wi019BtqfNgfoV1nAAYbIFebR+v1CYRNIH+1eQptUIVNbHM7ckfNd4M8OFf9NTlX9uB2VG0dWYgQpmQTITFjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:25:45.119220Z","bundle_sha256":"5ce0dd6d8c5b02cd58587796326db7232e349186a2c8a53b20f8cb5487b95e5f"}}