{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY","short_pith_number":"pith:QBDSDZ2Y","canonical_record":{"source":{"id":"2103.10702","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"b150d68728ed8bcd3d9cc72c04ad281f7438d36be95a0ec326f96f930454af57","abstract_canon_sha256":"76dd6dd482c9dabc62fbff53045678190ffdf4a0312aa641a74b640e33547d30"},"schema_version":"1.0"},"canonical_sha256":"804721e758d636d9a7450fa324ebb776392b6ed2ddb46e18a507c5aec0b4de80","source":{"kind":"arxiv","id":"2103.10702","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10702","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10702v4","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10702","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"QBDSDZ2Y2Y3N","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"QBDSDZ2Y2Y3NTJ2F","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"QBDSDZ2Y","created_at":"2026-07-05T07:35:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY","target":"record","payload":{"canonical_record":{"source":{"id":"2103.10702","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:31:08Z","cross_cats_sorted":[],"title_canon_sha256":"b150d68728ed8bcd3d9cc72c04ad281f7438d36be95a0ec326f96f930454af57","abstract_canon_sha256":"76dd6dd482c9dabc62fbff53045678190ffdf4a0312aa641a74b640e33547d30"},"schema_version":"1.0"},"canonical_sha256":"804721e758d636d9a7450fa324ebb776392b6ed2ddb46e18a507c5aec0b4de80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:15.347912Z","signature_b64":"AphbCqNbXUYuZvjfwmhV7tyzE7qB9wV2EBaGbwU+QEOyjnLzJAPdvqceslYGc+8FIBpbOyySkw9vNiPkBB+iAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"804721e758d636d9a7450fa324ebb776392b6ed2ddb46e18a507c5aec0b4de80","last_reissued_at":"2026-07-05T07:35:15.347441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:15.347441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.10702","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":"2026-07-05T07:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ioPhQii6IkS1Fw0uYPOYJ7xln1u4YB2lhFdm7iQ6I/hXJahDnbsuGzDezWyIXx7Ez+aBT65ovRnWHKZuHk8SCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:19:32.898056Z"},"content_sha256":"05bc9c07f53451dc9d2861499115fd3fe40a5f6aa3cdbb0d1aaa56d452e89713","schema_version":"1.0","event_id":"sha256:05bc9c07f53451dc9d2861499115fd3fe40a5f6aa3cdbb0d1aaa56d452e89713"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liang, Yawei Luo, Yi Yang, Yu Wu","submitted_at":"2021-03-19T09:31:08Z","abstract_excerpt":"Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos. It essentially requires semantic comprehension and fine-grained video understanding. Existing methods introduce language representation into segmentation models in a bottom-up manner, which merely conducts vision-language interaction within local receptive fields of ConvNets. We argue that such interaction is not fulfilled since the model can barely construct region-level relationships given partial observations, which is contrary to the description logic of natural language/r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10702","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.10702/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":"2026-07-05T07:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HkzOB5ezThX7ht0L6er6HAXOQlJN4spyxW92wioD/zpIodznAqZuW8GwSKEP7C7PrRTpSFYphmnuZNbkJ82LDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:19:32.898672Z"},"content_sha256":"4c4bd3ec89782e19c404645d5227e407f56c36c5ece4d67661833a1dfbd70ae2","schema_version":"1.0","event_id":"sha256:4c4bd3ec89782e19c404645d5227e407f56c36c5ece4d67661833a1dfbd70ae2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY/bundle.json","state_url":"https://pith.science/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY/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":"2026-08-07T12:19:32Z","links":{"resolver":"https://pith.science/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY","bundle":"https://pith.science/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY/bundle.json","state":"https://pith.science/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QBDSDZ2Y2Y3NTJ2FB6RSJ25XOY","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":"76dd6dd482c9dabc62fbff53045678190ffdf4a0312aa641a74b640e33547d30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:31:08Z","title_canon_sha256":"b150d68728ed8bcd3d9cc72c04ad281f7438d36be95a0ec326f96f930454af57"},"schema_version":"1.0","source":{"id":"2103.10702","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10702","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10702v4","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10702","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"QBDSDZ2Y2Y3N","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"QBDSDZ2Y2Y3NTJ2F","created_at":"2026-07-05T07:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"QBDSDZ2Y","created_at":"2026-07-05T07:35:15Z"}],"graph_snapshots":[{"event_id":"sha256:4c4bd3ec89782e19c404645d5227e407f56c36c5ece4d67661833a1dfbd70ae2","target":"graph","created_at":"2026-07-05T07:35:15Z","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/2103.10702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos. It essentially requires semantic comprehension and fine-grained video understanding. Existing methods introduce language representation into segmentation models in a bottom-up manner, which merely conducts vision-language interaction within local receptive fields of ConvNets. We argue that such interaction is not fulfilled since the model can barely construct region-level relationships given partial observations, which is contrary to the description logic of natural language/r","authors_text":"Chen Liang, Yawei Luo, Yi Yang, Yu Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:31:08Z","title":"ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10702","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":"sha256:05bc9c07f53451dc9d2861499115fd3fe40a5f6aa3cdbb0d1aaa56d452e89713","target":"record","created_at":"2026-07-05T07:35:15Z","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":"76dd6dd482c9dabc62fbff53045678190ffdf4a0312aa641a74b640e33547d30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-19T09:31:08Z","title_canon_sha256":"b150d68728ed8bcd3d9cc72c04ad281f7438d36be95a0ec326f96f930454af57"},"schema_version":"1.0","source":{"id":"2103.10702","kind":"arxiv","version":4}},"canonical_sha256":"804721e758d636d9a7450fa324ebb776392b6ed2ddb46e18a507c5aec0b4de80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"804721e758d636d9a7450fa324ebb776392b6ed2ddb46e18a507c5aec0b4de80","first_computed_at":"2026-07-05T07:35:15.347441Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:35:15.347441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AphbCqNbXUYuZvjfwmhV7tyzE7qB9wV2EBaGbwU+QEOyjnLzJAPdvqceslYGc+8FIBpbOyySkw9vNiPkBB+iAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:35:15.347912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.10702","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05bc9c07f53451dc9d2861499115fd3fe40a5f6aa3cdbb0d1aaa56d452e89713","sha256:4c4bd3ec89782e19c404645d5227e407f56c36c5ece4d67661833a1dfbd70ae2"],"state_sha256":"85e090f759f3d6acae91e778b468d4fe1918cb2bafd517d6732ad7b1d4caf5d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J5klc+6cOAlw36JlQZrVhCE6CenwoPSDfLRC5YHg7GwM6jQLvAlDyUB4DUrzq8/+RoHOkqqPNYh4JvC4CfchAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:19:32.903022Z","bundle_sha256":"25e85d415b6b1caeeb563699a530e6afa4231be84b6f48ba18b36f6398ed0324"}}